UTS - Bu Dewi2)

TUGAS UTS
MATA KULIAH EVIDENCE BASED

PEMANTAUAN KESEHATAN IBU DAN JANIN
Dosen Pengampu : Dewi Nopiska Lilis, M.Keb
Disusun Oleh :
CANDRA WIDHI ANJANI

PO71241230564
KERINCI
PROGRAM STUDI SARJANA TERAPAN KEBIDANAN POLTEKKES

KEMENKES JAMBI
TAHUN 2023
PEMANTAUAN KESEHATAN IBU DAN JANIN : LITERATURE
REVIEW
CANDRA WIDHI ANJANI

PROGRAM STUDY SARJANA TERAPAN POLTEKKES KEMENKES JAMBI
E-mail: candrawidhianjani10@gmail.com
ABSTRAK
Pemeriksaan kehamilan rutin memberikan informasi perkembangan janin dan kesehatan ibu
hamil. Kegiatan tersebut dinamakan ante natal care (ANC). Perkembangan janin sesuai,
berlebih atau kurang dari perhitungan usia kehamilan diketahui dengan akurat melalui
pemeriksaan ultra sono grafi (USG). Pengawalan kehamilan lebih informatif, diharapkan
mendapatkan outcome bayi saat lahir bugar, ibu hamil pun cepat pulih. Tujuan untuk
meningkatkan kesadaran ibu hamil melakukan ANC secara rutin. Jenis penelitian yang di
gunakan dalam beberapa penelitian ini adalah cross sectional yaitu dengan melihat kolerasi
atau hubungan dari pemantauan keehatan ibu dan janin. Pemantauan kesehatan ibu dan janin
harus dilakukan secara teratur agar ibu hamil dapat terhindar dari kehamilan beresiko seperti
terkena anemia, pre eklamsia, eklamsia, solusio plasenta dan lain-lain. Pemeriksaan ante natal
care (ANC) merupakan pemeriksaan kehamilan secara berkala dan bertujuan untuk
meningkatkan kesehatan fisik dan mental pada ibu hamil (bumil) secara optimal.
ABSTRACT
Routine pregnancy checks provide information on fetal development and the health of
pregnant women. This activity is called ante natal care (ANC). The development of the fetus
is appropriate, excess or less than the calculated gestational age, known accurately through
ultra sonography (USG) examination. Pregnancy control is more informative, it is hoped that
the baby's outcome will be healthy at birth, and the pregnant mother will recover quickly.
The aim is to increase awareness of pregnant women carrying out ANC regularly. The type
of research used in several of these studies is cross sectional, namely by looking at the
correlation or relationship between maternal and fetal health monitoring. Monitoring the
health of the mother and fetus must be carried out regularly so that pregnant women can
avoid risky pregnancies such as anemia, pre-eclampsia, eclampsia, placental abruption and
others. Ante-natal care (ANC) examinations are regular pregnancy examinations and aim to
optimally improve the physical and mental health of pregnant women.
PENDAHULUAN Goldfield dari hasil penelitiannya, bahwa
seorang wanita yang merasa tidak puas
Kematian maternal secara global dengan tubuhnya menunjukkan adanya
berdasarkan data World Health gejala depresi yang lebih berat, seperti
Organization (WHO) mengalami anhedonia, harga diri negatif, dan
penurunan 43% dari perkiraan 532.000 tingginya angka depresi dari pada yang
pada tahun 1990 menjadi 303.000 pada memiliki kepuasan tinggi (Gani et al.,
tahun 2015. Penyebab kematian maternal 2014)
menurut WHO disebabkan oleh Pemeriksaan ante natal care (ANC)
perdarahan, infeksi, hipertensi dalam merupakan pemeriksaan kehamilan secara
kehamilan, komplikasi dalam persalinan, berkala dan bertujuan untuk meningkatkan
dan aborsi tidak aman.2 Penyebab kesehatan fisik dan mental pada ibu hamil
kematian maternal di Indonesia tahun 2011 (bumil) secara optimal. Ibu hamil
adalah hipertensi dalam kehamilan, diharapkan mampu menghadapi masa
perdarahan dan infeksi. Berdasarkan hasil persalinan, nifas, persiapan pemberian ASI
Survei Demografi Kesehatan Indonesia eksklusif, dan kembalinya kesehatan alat
(SDKI) tahun 2012, AKI mencapai reproduksi dengan wajar. Pemeriksaan
359/100.000 kelahiran hidup (Kemenkes kehamilan saat ini dilakukan minimal
RI, 2012). enam kali selama masa kehamilan, yaitu 1
Kehamilan merupakan suatu proses kali pemeriksaan pada trimester pertama, 2
bergabungnya sperma dan ovum untuk kali pemeriksaan pada trimester kedua, dan
menciptakan suatu sel tunggal yang 3 kali pemeriksaan pada trimester ketiga
disebut dengan zigot, yang kemudian (Aziz, 2020).
menggandakan diri berkali-kali melalui Tujuan secara umum yang hendak dicapai
pembelahan sel untuk menjadi lahir. dengan pemeriksaan ANC secara rutin
Dalam banyak masyarakat definisi medis yang disampaikan oleh Kemenkes RI
dan legal kehamilan dibagi dalam tiga tahun 2018 adalah: (1) Memantau
periode trimester untuk melihat kehamilan dengan mengetahui kesehatan
perkembangan fisiologis dan psikologis ibu dan tumbuh kembang janin; (2)
kehamilan (Janiwarty, 2013). Perubahan Mengetahui sejak dini kemungkinan
psikologi setiap trimester pada wanita adanya komplikasi kehamilan, termasuk
hamil tidak terlepas dari dampak adanya riwayat penyakit dan tindakan
perubahan yang khas dalam segi fisik dari pembedahan; (3) Meningkatkan dan
setiap proses kehamilan yang dialami mempertahankan kesehatan ibu dan bayi;
wanita hamil. Uraian terhadap (4) Mempersiapkan proses persalinan yang
perkembangan psikologi di atas aman, sehingga dapat melahirkan bayi
menunjukkan adanya perubahan “citra dengan selamat serta meminimalkan trauma
tubuh” pada ibu hamil atau yang dalam yang mungkin terjadi saat persalinan; (5)
istilah asing disebut body image. Citra Menurunkan angka kematian dan angka
tubuh (body image) merupakan gambaran kesakitan ibu; (6) Mempersiapkan peran
mental seseorang terhadap bentuk dan ibu dan keluarga saat kelahiran anak agar
ukuran tubuhnya; bagaimana seseorang anak menjalani tumbuh kembang yang
mempersepsi dan memberikan penilaian normal; dan (7) Mempersiapkan ibu
atas apa yang dia rasakan terhadap ukuran melewati masa nifas dengan baik dan
dan bentuk tubuhnya, dan atas bagaimana memberikan ASI eksklusif pada bayi.
kira-kira penilaian orang lain terhadap Pemeriksaan ANC dapat dilakukan di
dirinya (Gani et al., 2014). Perubahan puskesmas, klinik, ataupun rumah sakit,
citra tubuh (body image) menghasilkan dan dapat dilayani oleh bidan, perawat,
sikap positif dan negatif pada setiap dokter umum, maupun Dokter Spesialis
wanita. Wanita yang memiliki citra tubuh Obstetri dan Ginekologi (Dokter Spesialis
negatif atau ketidakpuasan terhadap Kebidanan Dan Kandungan) (Kemenkes
tubuhnya, akan lebih mudah mengalami RI, 2018).
depresi dari pada yang merasa puas akan Pelayanan kesehatan pada ibu hamil tidak
tubuhnya. Seperti yang diungkapan dapat dipisahkan dengan pelayanan
persalinan, pelayanan nifas dan pelayanan hypnosis dan pemantauan kesejahteraan
kesehatan bayi baru lahir. Kualitas janin. Serta sebagai upaya menciptakan
pelayanan antenatal yang diberikan akan image positif dalam diri ibu hamil. Agar
mempengaruhi kesehatan ibu hamil dan para ibu hamil mampu mencintai setiap
janinnya, ibu bersalin dan bayi baru lahir perubahan pada dirinya dan janin di dalam
serta ibu nifas. Dalam pelayanan antenatal kandungannya
terpadu, tenaga kesehatan harus dapat Implikasinya adalah para ibu-ibu hamil
memastikan bahwa kehamilan mampu menerapkan hypnosis ini secara
berlangsung normal, mampu mendeteksi mandiri, sehingga dapat meningkatkan
dini masalah dan penyakit yang dialami kemampuan ibu hamil dalam deteksi dini
ibu hamil, melakukan intervensi secara resiko kehamilan.
adekuat sehingga ibu hamil siap untuk Penyuluhan memberikan peningkatan
menjalani persalinan normal. Setiap kesadaran bumil tentang pentingnya
kehamilan, dalam perkembangannya pemeriksaan ANC. Adanya peningkatan
mempunyai risiko mengalami penyulit nilai postes dibandingkan nilai pretes
atau komplikasi. Oleh karena itu, menunjukkan materi penyuluhan disimak
pelayanan antenatal harus dilakukan dengan baik oleh para peserta. Peningkatan
secara rutin, sesuai standar dan terpadu nilai rerata, nilai tertinggi, dan nilai
untuk pelayanan antenatal yang terendah masing-masing mencapai 75%,
berkualitas (Ningsih & Dewi, 2017). 25%, dan 100%. Dengan ketaatan bumil
Kesehatan ibu meliputi kesehatan pada melakukan ANC diharapkan kesejahteraan
masa kehamilan dan persalinan. Setiap bumil dan perkembangan janin dapat
tahap selama kehamilan harus menjadi terpantau dengan cermat, sehingga
pengalaman positif, memastikan bahwa diharapkan bumil akan melahirkan bayi
perempuan dan bayinya mencapai potensi yang segar bugar dan pulihnya kembali
kesehatan dan kesejahteraan mereka bumil akan lebih cepat untuk bisa
sepenuhnya. Namun, hal ini tidak selalu beraktifitas kembali. Saran untuk
dapat dicapai. Menurut UNFPA (Dana keberlanjutan pengabdian adalah untuk bisa
Populasi Perserikatan Bangsa-Bangsa), secara berkesinambungan melakukan
sekitar 800 wanita meninggal setiap hari kegiatan serupa dalam cakupan yang lebih
karena sebab-sebab yang tidak dapat luas di tahun-tahun mendatang. Dengan
dihindari terkait kehamilan dan demikian sasaran bumil akan lebih banyak
persalinan, sehingga penting untuk yang terlayani.
memantau kesehatan ibu dan janin selama Dalam penelitian tersebut, kami
kehamilan. Banyak sensor dan perangkat menemukan bahwa wanita hamil
yang dapat dipakai telah dikembangkan mempertimbangkan untuk menggunakan
untuk memantau kesehatan janin dan ibu sensor ponsel dan melaporkan tidak ada
serta aktivitas fisik (Anika & Masudul, masalah privasi. Menurut Runkle et al.,
2023). tujuh dari sepuluh wanita setuju untuk
mengubah perilaku atau gaya hidup mereka
METODE PENELITIAN selama kehamilan setelah menerima
rekomendasi atau pesan dari smartphone
Jenis penelitian yang di gunakan dalam melalui sensor yang dapat dikenakan.
beberapa penelitian ini adalah cross Sebagian besar penelitian yang kami
sectional yaitu dengan melihat kolerasi sebutkan menerapkan metode Pembelajaran
atau hubungan dari pemantauan keehatan Mesin dan Pembelajaran Mendalam pada
ibu dan janin. sinyal yang telah diproses sebelumnya
untuk mendeteksi atau mengevaluasi
HASIL DAN PEMBAHASAN kinerja. Akurasi dalam penelitian ini adalah
sekitar 80% hingga 90%, yang menurut
artikel tersebut dapat diterima. Jadi, kami
Dari penelitian ini, kami menemukan dapat menyatakan bahwa sensor yang dapat
adanya peningkatan pengetahuan dan dikenakan berkontribusi signifikan terhadap
keterampilan ibu hamil tentang kesehatan ibu selama kehamilan. Meskipun
membangun body image terintegrasi terdapat permintaan dan kebutuhan akan
monitor atau sensor layanan kesehatan gerakan janin sehingga terjadi
yang dapat dipakai, masih terdapat hubungan khusus antara ibu dan
beberapa keterbatasan dan tantangan. janinnya. Ibu dapat dilatih dalam
Meningkatkan akurasi, pengujian dalam keheningannya untuk merasakan
kondisi hidup bebas, meningkatkan tingkat gerakan janin.
kenyamanan sensor yang dapat dikenakan, 3. Pemantauan kesehatan ibu dan janin
dan pemantauan terus menerus dan harus dilakukan secara teratur agar ibu
memanjang memerlukan pengembangan hamil dapat terhindar dari kehamilan
lebih lanjut dari sensor dan perangkat yang beresiko seperti terkena anemia, pre
dapat dikenakan. Jika tantangan ini dapat eklamsia, eklamsia, solusio plasenta
diatasi, sensor yang dapat dikenakan dapat dan lain-lain.
berkontribusi besar dalam mengurangi
angka kematian akibat komplikasi UCAPAN TERIMA KASIH
kehamilan atau kehamilan masalah
kesehatan ibu lainnya. Puji syukur penulis panjatkan kehadirat
Aplikasi pemantauan FECG portabel Allah SWT karena atas limpahan rahmat
berbasis rumah Skor PPV, ACC, dan F1 dan karunia-Nya sehingga penelitianini
dari pekerjaan ini sedikit lebih tinggi dapat terselesaikan. Tak lupa pula penulis
dibandingkan hasil deteksi QRS janin mengucapkan terima kasih kepada semua
yang dapat diterapkan untuk pemantauan pihak yang telah memberikan dukungan
kesehatan dalam berbagai postur baik berupa tenaga pikiran mapun materi.
(terlentang, duduk, dan berdiri) dari
wanita hamil. Hasilnya menunjukkan DAFTAR PUSTAKA
bahwa kualitas sinyal AECG pada posisi
telentang dan postur duduk mempunyai Anika Alim & Masudul H. Imtiaz (2023)
kinerja yang lebih baik dibandingkan Wearable Sensors for the Monitoring
dengan postur berdiri. of Maternal Health—A Systematic
Review.
KESIMPULAN https://creativecommons.org/licenses/
by/ 4.0/
1. Usia ibu hamil yang mengikuti ANC Aziz, M. A. et al. (2020). Rekomendasi
terpadu mayoritas berkisar 26-30 Penanganan Infeksi Virus Corona
tahun. Di usia tersebut merupakan (Covid-19) Pada Maternal (Hamil,
usia produktif sehingga perlu Bersalin Dan Nifas) Revisi 2. Jakarta.
perhatian khusus utamanya saat hamil Penerbit:Pokja Infeksi Saluran
oleh tenaga kesehatan. Bidan Reproduksi Perkumpulan Obstetri
memberikan asuhan yang Dan Ginekologi Indonesi a Tahun2020,
berkesinambungan agar harapan 3–15.
perempuan dan pelayanan yang https://pogi.or.id/publish/rekomendasi
diberikan oleh tenaga kesehatan -penanganan-infeksivirus-corona-
bersinergi dengan baik. Selain covid-19-pada-maternal/
itu bidan dan ibu juga perlu menjalin Dewi Andariya Ningsih. “Partnership
hubungan yang baik agar tercipta Dalam Pelayanan Kebidanan.”
partner pemberi dan penerima Proceeding book (2015).
layanan kesehatan yang sesuai. Innama Sakinah (2022) Anc Terpadu Untuk
Pemberian modul ibu hamil juga Kesejahteraan Ibu Dan Janin Jurnal
sangat berpengaruh terhadap Pengabdian Kepada
pengetahuan ibu hamil terkait Masyarakat Vol.1, No.12, Mei 2022.
kesejahteraan diri dan janin yang di http://bajangjournal.com/index.php/J-
kandung. ABDI
2. Ibu berperan penting untuk Ivanna Beru Brahmana et al (2022)
menciptakan kehamilan sehat karena Penyuluhan Pentingnya Ante Natal Care
janin sesungguhnya berada dalam Pada Ibu Hamil Dalam Upaya Pemantauan
pengaruh dan pemantauan ibu. Ibu Kesejahteraan Janin.
dapat dilatih untuk merasakan
http://journal.ummat.ac.id/index.php/jmm
Kemenkes, RI. Profil Kesehatan
Indonesia
2012, 2012.
Ningsih, Dewi Andariya. “Continuity of
Care Kebidanan.” OKSITOSIN :
Jurnal Ilmiah Kebidanan 4, no.
2
(2017): 67–77.
RI, Kemenkes. Pedoman Pelayanan
Antenatal Terpadu, 2018.
Septiyaningsih, R., Kusumawati, D. D.,
Yunadi, F. D., & Indratmoko, S.
(2020). Edukasi dan Deteksi Dini
Komplikasi Kehamilan dengan
Pemeriksaan Laboratorium. Poltekita:
Jurnal Pengabdian Masyarakat, 1(2),
43–49.
https://doi.org/10.33860/pjpm.v1i2.98
S. Venkatasubramanian
(2022) Ambulatory Monitoring
of Maternal and Fetal using Deep
Convolution Generative Adversarial
Network for Smart Health Care IoT
System. Vol. 13, No. 1, 2022.
Yuwei Zhang, Aihua Gu, Zhijun Xiao,
Yantao Xing, Chenxi Yang, Jianqing
Li and Chengyu Liu (2022) Wearable
Fetal ECG Monitoring System from
Abdominal
Electrocardiography Recording.
https://
doi.org/10.3390/bios12070475
WHO. Trends in Maternal Mortality :
1990 to 2015. World Health
Organization, 2014
3299
J-Abdi Jurnal Pengabdian Kepada
Masyarakat
Vol.1, No.12, Mei 2022
ANC TERPADU UNTUK KESEJAHTERAAN IBU DAN JANIN
Oleh
Innama Sakinah
Program Studi Sarjana dan Pendidikan Profesi Bidan Fakultas Ilmu Kesehatan,
Universitas Faletehan Serang
E-mail: innamasakinah@gmail.com
Article History: Abstract: Universitas Faletehan ikut andil dengan upaya

Received: 03-03-2022 meningkatkan derajat kesehatan ibu dan anak terutama pada
Revised: 14-03-2022 kelompok yang paling rentan yaitu ibu hamil, bersalin, dan bayi
Accepted: 26-03-2022 pada masa perinatal dalam kegiatan Pemantauan kesehatan ibu
hamil di wilayah UPTD Puskesmas Taktakan Kota Serang dengan
Keywords: kegiatan ANC Terpadu sebagai wujud pengabdian kepada
ANC Terpadu, Ibu Hamil masyarakat. Pelaksanaan kegiatan ini dilaksanakan di ruang KIA
dan Laboratorium UPTD Puskesmas Taktakan. Sasaran dalam
kegiatan ini adalah ibu hamil di wilayah Taktakan. Di dalam
melakukan pemeriksaan Antenatal terpadu, tenaga kesehatan
memberikan layanan terstandar dengan 10 T yaitu Timbang berat
badan dan ukur tinggi badan, Ukur tekanan darah, Ukur lingkar
lengan atas/LILA (Nilai status gizi), Ukur tinggi fundus uteri,
Tentukan presentasi janin dan denyut jantung janin (DJJ, Skrining
Status Imunisasi Tetanus dan berikan Imunisasi Tetanus Toxoid
(TT) bila diperlukan, Beri Tablet tambah darah (Fe), Periksa
laboratorium (rutin & khusus). Tatalaksana/penanganan kasus
Temu wicara (konseling).nAlasan dilakukan pemeriksaan secara
terpadu diatas, maka setiap ibu hamil akan terdeteksi secara dini
bila terjadi hal-hal yang tidak diinginkan pada ibu hamil maka
akan dapat dilakukan tindakan
antisipasi dan penanggulangan secara dini.
PENDAHULUAN
Peran serta Program Studi Sarjana dan Pendidikan Profesi Bidan Fakultas Ilmu Kesehatan Universitas
Faletehan Serang selaku perguruan tinggi dalam menjalankan tridarma perguruan tinggi salah satunya
adalah pengabdian masyarakat, mendekatkan diri kepada masyarakat sehingga dapat mengenal,
mengetahui dan merasakan permasalahan yang dihadapi oleh masyarakat. Fakultas Ilmu Kesehatan
Universitas Faletehan sebagai perguruan tinggi bidang kesehatan dengan Tridarma Perguruan Tinggi
mengabdikan keilmuan dan keterampilan sebagai wujud nyata membantu membangun masyarakat
melalui strategi pengabdian masyarakat. Pengabdian masyarakat sebagai suatu bentuk kerja nyata
dimasyarakat dan keuntungan bagi masyarakat dapat mengadopsi strategi sebagai
http://bajangjournal.com/index.php/J-ABDI ISSN: 2797-9210 (Print) | 2798-2912(Online)

3300
J-Abdi
Jurnal Pengabdian Kepada Masyarakat
Vol.1, No.12 Mei 2022
upaya meningkatkan derajat kesehatan.

Bentuk pengabdian masyarakat pada kegiatan ini adalah pemeriksaan ANC Terpadu bekerjasama
dengan UPTD Puskesmas Taktakan Kota Serang dengan tema “ANC Terpadu“. Masalah
kesehatan keluarga merupakan salah satu masalah yang perlu mendapat perhatian. Masalah
kesehatan keluarga sangat erat hubungannya dengan kondisi seorang ibu yang merupakan salah
satu pembina keluarga. Seorang ibu tidak dapat melepaskan diri dari risiko hamil dan melahirkan.
Keadaan tersebut dapat memengaruhi kesehatan dan kondisi seorang ibu yang dapat
mempengaruhi kesehatan keluarga. Peran ibu sangat besar artinya dalam sebuah keluarga sehingga
kesehatan dan keselamatan seorang ibu haruslah menjadi prioritas utama. Ibu adalah penerus
keturunan dari generasi ke generasi. Dari rahim seorang ibu dilahirkan putra putri terbaik negeri.
Namun yang perlu dikaji adalah masih tingginya AKI (Angka Kematian Ibu)1.
Kematian maternal secara global berdasarkan data World Health Organization (WHO) mengalami
penurunan 43% dari perkiraan 532.000 pada tahun 1990 menjadi 303.000 pada tahun 2015.
Penyebab kematian maternal menurut WHO disebabkan oleh perdarahan, infeksi, hipertensi dalam
kehamilan, komplikasi dalam persalinan, dan aborsi tidak aman. 2 Penyebab kematian maternal di
Indonesia tahun 2011 adalah hipertensi dalam kehamilan, perdarahan dan infeksi. Berdasarkan
hasil Survei Demografi Kesehatan Indonesia (SDKI) tahun 2012, AKI mencapai 359/100.000
kelahiran hidup.3
Berbagai upaya untuk penurunan angka kematian ibu dan bayi terus dilakukan, salah satu upaya
untuk penurunan angka kematian ibu yang dikembangkan adalah dalam bentuk ANC terpadu.
ANC terpadu adalah berupa kegiatan yang dilakukan terhadap ibu hamil dengan mengintegrasikan
berbagai program yang terkait dengan kemungkinan yang akan dialami oleh seorang ibu dan
berdampak pada keselamatan ibu dan bayinya. Pelayanan antenatal terpadu merupakan pelayanan
antenatal komprehensif dan berkualitas yang diberikan kepada semua ibu hamil secara terpadu
dengan program lain yang memerlukan intervensi selama kehamilannya.4.
Pelayanan kesehatan pada ibu hamil tidak dapat dipisahkan dengan pelayanan persalinan,
pelayanan nifas dan pelayanan kesehatan bayi baru lahir. Kualitas pelayanan antenatal yang
diberikan akan mempengaruhi kesehatan ibu hamil dan janinnya, ibu bersalin dan bayi baru lahir
serta ibu nifas. Dalam pelayanan antenatal terpadu, tenaga kesehatan harus dapat memastikan
bahwa kehamilan berlangsung normal, mampu mendeteksi dini masalah dan penyakit yang
dialami ibu hamil, melakukan intervensi secara adekuat sehingga ibu hamil siap untuk menjalani
persalinan normal. Setiap kehamilan, dalam perkembangannya mempunyai risiko mengalami
penyulit atau komplikasi. Oleh karena itu, pelayanan antenatal harus dilakukan secara rutin, sesuai
standar dan terpadu untuk pelayanan antenatal yang berkualitas. 5
Di dalam melakukan pemeriksaan Antenatal terpadu, tenaga kesehatan memberikan layanan
terstandar dengan 10 T yaitu Timbang berat badan dan ukur tinggi badan, Ukur
1
Justina Fatbinan, Masni, and Hj A Ummu Salmah, “Faktor Resiko Kematian Maternal Di RSUD Piere Paolo
Magreti Saumlaki Kabupaten Maluku Tenggara Barat” 1 (2013).
2
WHO, Trends in Maternal Mortality : 1990 to 2015, World Health Organization, 2014.
3
RI Kemenkes, Profil Kesehatan Indonesia 2012, 2012.
4
Kemenkes RI, Pedoman Pelayanan Antenatal Terpadu, 2012.
5
Kemenkes, Pedoman Pelayanan ANC Terpadu, 2010.
ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

3301
Masyarakat
Vol.1, No.12, Mei 2022
tekanan darah, Ukur lingkar lengan atas/LILA (Nilai status gizi), Ukur tinggi fundus uteri, Tentukan
presentasi janin dan denyut jantung janin (DJJ, Skrining Status Imunisasi Tetanus dan berikan Imunisasi
Tetanus Toxoid (TT) bila diperlukan, Beri Tablet tambah darah (Fe), Periksa laboratorium (rutin &
khusus). Tatalaksana/penanganan kasus Temu wicara (konseling). Alasan dilakukan pemeriksaan
secara terpadu diatas, maka setiap ibu hamil akan terdeteksi secara dini bila terjadi hal-hal yang tidak
diinginkan pada ibu hamil maka akan dapat dilakukan tindakan antisipasi dan penanggulangan secara
dini. 6
METODE
Pokok Kegiatannya yaitu Pemeriksaan Kehamilan, Sasaran terdiri dari Ibu Hamil di wilayah UPTD
Puskesmas Taktakan Kota Serang, Pelaksana bidan, dokter gigi, dokter umum, laboratorium, Tempat di
ruang KIA dan laboratorium UPTD Puskesmas Taktakan Kota Serang, hari/tanggal Jumat/13 Desember
2019. Tujuan Pelaksanaan kegiatan ini untuk memenuhi hak setiap ibu hamil memperoleh pelayanan
antenatal yang berkualitas sehingga mampu menjalani kehamilan dengan sehat, bersalin dengan selamat,
dan melahirkan bayi yang sehat, menyediakan pelayanan antenatal terpadu, komprehensif dan
berkualitas, termasuk konseling kesehatan dan gizi ibu hamil, konseling KB dan pemberian ASI,
mendeteksi secara dini kelainan/penyakit/gangguan yang diderita ibu hamil, melakukan intervensi
terhadap kelainan/penyakit/gangguan pada ibu hamil sedini mungkin.
NO. KEGIATAN HASIL ALOKASI WAKTU
1. Registrasi Daftar hadir 2 menit
2. Anamnese Identitas 3 menit
3. Pemeriksaan Fisik terdiri dari: 15 menit
a. Berat Badan dan tinggi badan
b. Mengukur TTV a. Nilai BB dan TB
c. Mengukur LILA
d. Mengukur Tinggi Fundus Uteri b. Nilai TTV
(TFU) c. Nilai LILA
e. Pengecekan presentasi janin d. Nilai TFU
f. Pengecekan DJJ
e. Hasil Presentasi Janin
f. Hasil DJJ
4. Pemeriksaan Laboratorium terdiri 10 menit
dari:
a. Pemeriksaan Hb a. Nilai Hb
b. Pengecekan golongan darah b. Nilai Golongan darah
c. Pemeriksaan Protein Urine c. Nilai Protein Urine
d. Pemeriksaan glukosa urine
d. Nilai Glukosa Urine
5. Pemeriksaan gigi dan mulut Nilai gigi dan mulut 5 menit
6. USG Nilai USG 5 menit
7. Pemberian Tablet Fe Tablet Fe 2 menit
8. Temu wicara / Konseling 5 menit
Keterangan :
1. Pemberian Imunisasi TT tidak dilakukan karena semua ibu hamil yang datang pada saat
ANC Terpadu sudah melakukan TT
2. Pemeriksaan VDRL (Veneral Disease Research Lab.) tidak dilakukan karena semua ibu
hamil yang datang sudah beberapa kali melakukan kunjungan pemeriksaan di Bidan.
6
RI, Pedoman Pelayanan Antenatal Terpadu.

3302
J-Abdi
Vol.1, No.12 Mei 2022
3. Perawatan Payudara, Senam Hamil tidak dilakukan karena sudah dilakukan seminggu
sebelumnya di posyandu setempat
4. Pemberian Obat Malaria tidak diberikan kepada Bumil karena semua ibu hamil di daerah
Sumberrejo adalah warga pribumi dan bukan pendatang dari daerah malaria serta tidak ada
gejala malaria yakni panas tinggi disertai mengigil dan hasil apusan darah yang positif.
5. Pemberian Kapsul Minyak Yodium tidak diberikan karena semua ibu hamil yang berada di
Desa Taktakan tidak ada kasus gangguan akibat kekurangan Yodium
HASIL
Kegiatan ini pada tanggal 13 Desember 2019. Peserta yang mengikuti kegiatan ini sebanyak 15 ibu
hamil. Usia peserta yang mengikuti kegiatan ini yaitu bervariasi, paling muda berusia 18 tahun dan
yang paling tua berusia 43 tahun seperti ditunjukkan pada Tabel
1. Ada beberapa keluhan dari ibu hamil yaitu pusing dan batuk. Hasil pemeriksaan tekanan darah
terhadap 15 ibu hamil sebagian besar dalam batas normal. Hasil pemeriksaan hemoglobin sebagian
besar mengalami penurunan dari pemeriksaan sebelumnya seperti ditunjukkan pada tabel 2. Untuk
hasil pemeriksaan glukosa dan protein urine terhadap 15 ibu hamil semuanya menunjukkan bahwa
hasilnya normal. Pemeriksaan gigi yang dilakukan oleh dokter gigi ada beberapa ibu hamil yang
ada karies di giginya. Dan pada saat dilakukan USG oleh dokter ditemukan 1 orang terdapat
benjolan lain di abdomen sehingga setelahnya dilakukan tindak lanjut oleh dokter dan bidan.
Ibu Hamil Berdasarkan Usia
15-20 Tahun
21- 25 tahun
26 - 30 Tahun
31 - 35 Tahun
36 - 40 Tahun
41 - 45 Tahun
Tabel 1. Usia Ibu Hamil

3303
Masyarakat
Vol.1, No.12, Mei 2022
Hasil Pemeriksaan Hb
4
Hasil Pemeriksaan Hb
3
0
Hb > 11 gram Hb 9 -10 Hb 7 - 8,9 Hb < 7 gram
gram gram
Tabel 2. Hasil Pemeriksaan Hb Ibu Hamil
DISKUSI
Usia ibu hamil yang mengikuti ANC terpadu mayoritas berkisar 26-30 tahun. Di usia tersebut
merupakan usia produktif sehingga perlu perhatian khusus utamanya saat hamil oleh tenaga kesehatan.
Bidan memberikan asuhan yang berkesinambungan agar harapan perempuan dan pelayanan yang
diberikan oleh tenaga kesehatan bersinergi dengan baik. 7 selain itu bidan dan ibu juga perlu menjalin
hubungan yang baik agar tercipta partner pemberi dan penerima layanan kesehatan yang sesuai. 8
Pemberian modul ibu hamil juga sangat berpengaruh terhadap pengetahuan ibu hamil terkait
kesejahteraan diri dan janin yang di kandung. 9
Hasil pemeriksaan Hb mayoritas dengan hasil 9-10 gram sehingga dapat disimpulkan kondisi ibu hamil
dalam keadaan anemia ringan sehingga perlu pemantauan lanjut agar bisa naik kadarnya. Bidan perlu
melakukan asuhan berkala kepada ibu hamil karena asuhan kebidanan yang tepat yaitu berpusat pada
perempuan agar dapat eminimalisir masalah yang muncul saat menjalani proses kehamilan 10
7
Dewi Andariya Ningsih, “Continuity of Care Kebidanan,” OKSITOSIN : Jurnal Ilmiah Kebidanan 4, no. 2 (2017): 67–77.
8
Dewi Andariya Ningsih, “Partnership Dalam Pelayanan Kebidanan,” Proceeding book (2015).
9
Dewi Andariya Ningsih, “Pengembangan Modul ‘Peduli Ibu Hamil’ Di Desa Sumberejo Banyuputih Situbondo,”
JOMIS (Journal of Midwifery Science) 4 (2020): 55–62.
10
Dewi Andariya Ningsih, Midwifery Women Center Care Pada Masa Nifas Dalam Buku Asuhan Kebidanan Pada Masa
Pandemi Covid-19, ed. PhD Qorinah Estiningtyas Sakilah Adnani, M.Keb and Diajeng Ragil Pangestuti (Malang: CV
Penulis Cerdas Indonesia, 2021), https://drive.google.com/file/d/18SXFDo5VC58S6HNoVTghykHXh8dHROQN/view?
usp=sharing.

Journal of Community Engagement in Health
http://jceh.org https://doi.org/10.30994/jceh.v4i1.137
ISSN: 2620-3758 (print); 2620-3766 (online) Vol.4 No.1. Mar 2021. Page.167-174
KESIMPULAN
Dari hasil yang diperoleh terdapat usia ibu hamil yang berisiko tinggi dalam
kehamilan, penurunan kadar Hb ibu hamil. Oleh karena itu harus terdapat solusi
untuk mengatasi hal terbut yang tertuang dalam rencana tindak lanjut berupa:
1. Konseling untuk ibu hamil terkait kontrasepsi lanjutan setelah melahirkan
2. Menyarankan ibu hamil untukl selalu memeriksakan kehamilannya
3. Pemberian tablet Fe dan konseling cara mengkonsumsinya
4. Konseling gizi seimbang
5. Kerjasama dengan UPTD Puskesmas Taktakan untuk melakukan pengawasan
secara kompherensif pada ibu hamil.
PENGAKUAN/ACKNOWLEDGEMENTS
Terimakasih kepada Fakultas Ilmu Kesehatan Universitas Faletehan Serang atas
dukungan yang diberikan sehingga kegiatan pengabdian masyarakat ini berjalan
lancar. Selain itu kami ucapkan terimakasih kepada Kepala UPTD Puskesmas
Taktakan serta masyakat Taktakan yang sudah berpartisipasi dalam kegiatan ini.
DAFTAR REFERENSI
[1] Dewi Andariya Ningsih. “Partnership Dalam Pelayanan Kebidanan.” Proceeding
book
(2015).
[2] Fatbinan, Justina, Masni, and Hj A Ummu Salmah. “Faktor Resiko Kematian
Maternal Di RSUD Piere Paolo Magreti Saumlaki Kabupaten Maluku
Tenggara Barat” 1 (2013).
[3] Kemenkes. Pedoman Pelayanan ANC Terpadu, 2010.
[4] Kemenkes, RI. Profil Kesehatan Indonesia 2012, 2012.
[5] Ningsih, Dewi Andariya. “Continuity of Care Kebidanan.” OKSITOSIN :
Jurnal Ilmiah Kebidanan 4, no. 2 (2017): 67–77.
[6] ———. Midwifery Women Center Care Pada Masa Nifas Dalam Buku
Asuhan Kebidanan Pada Masa Pandemi Covid-19. Edited by PhD Qorinah
Estiningtyas Sakilah Adnani, M.Keb and Diajeng Ragil Pangestuti. Malang:
CV Penulis Cerdas Indonesia, 2021.
https://drive.google.com/file/d/18SXFDo5VC58S6HNoVTghykHXh8dHROQ
N/view?u sp=sharing.
[7] ———. “Pengembangan Modul ‘Peduli Ibu Hamil’ Di Desa Sumberejo
Banyuputih Situbondo.” JOMIS (Journal of Midwifery Science) 4 (2020): 55–
62.
[8] RI, Kemenkes. Pedoman Pelayanan Antenatal Terpadu, 2012.
[9] WHO. Trends in Maternal Mortality : 1990 to 2015. World Health Organization,
2014.
167
168
J-Abdi
Vol.1, No.12 Mei 2022
Membangun Body Image Ibu Hamil Terintegrasi Hypnosis

Dalam Upaya Pemantauan Kesejahteraan Janin
Elita Vasra, Asri Noviyanti*
Poltekkes Kemenkes Palembang, Indonesia
* Correspondent Author: noviyantiasri4@gmail.com
ABSTRAK
Perubahan psikologi setiap trimester pada wanita hamil tidak terlepas dari dampak
perubahan yang khas dalam segi fisik dari setiap proses kehamilan yang dialami wanita
hamil. Uraian terhadap perkembangan psikologi di atas menunjukkan adanya perubahan
“citra tubuh” pada ibu hamil atau yang dalam istilah asing disebut body image.
Perubahan citra tubuh (body image) menghasilkan sikap positif dan negatif pada setiap
wanita. Wanita yang memiliki citra tubuh negatif atau ketidakpuasan terhadap tubuhnya,
akan lebih mudah mengalami depresi dari pada yang merasa puas akan tubuhnya. Ibu
berperan penting untuk menciptakan kehamilan sehat karena janin sesungguhnya berada
dalam pengaruh dan pemantauan ibu. Ibu dapat dilatih untuk merasakan gerakan janin
sehingga terjadi hubungan khusus antara ibu dan janinnya. Ibu dapat dilatih dalam
keheningannya untuk merasakan gerakan janin. Adapun tujuan kegiatan ini adalah untuk
meningkatnya keyakinan dan kepercayaan diri ibu hamil, kecemasan ibu hamil dalam
kehamilan dan persalinan, kemampuan ibu hamil dalam melakukan hypnosis, kemampuan
ibu hamil dalam melakukan pemantauan kesejahteraan janin. Pelaksanaan dilakukan pada
ibu hamil trimester II dan III pada tanggal 12 Oktober 2020. Hasil yang dicapai dalam
kegiatan adalah meningkatnya kemampuan ibu hamil dalam melakukan hypnosis dan
pemantauan kesejahteraan janin. Luaran yang dicapai adalah adanya peningkatan
keterampilan ibu hamil tentang hypnosis dan pemantauan kesejahteraan janin.
Kata Kunci: Body Image, Ibu hamil, Kesejahteraan janin
Received: December 5, 2020

Revised: January 10, 2020
Accepted: February 27, 2021
This is an open-acces article distributed under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
PENDAHULUAN
Kehamilan merupakan suatu proses bergabungnya sperma dan ovum untuk
menciptakan suatu sel tunggal yang disebut dengan zigot, yang kemudian menggandakan
diri berkali-kali melalui pembelahan sel untuk menjadi lahir. Dalam banyak masyarakat
definisi medis dan legal kehamilan dibagi dalam tiga periode trimester untuk melihat
perkembangan fisiologis dan psikologis kehamilan (Janiwarty, 2013)
Perubahan psikologi setiap trimester pada wanita hamil tidak terlepas dari dampak
perubahan yang khas dalam segi fisik dari setiap proses kehamilan yang dialami wanita
ISSN:hamil. Uraian
2797-9210 terhadap
(Print) perkembangan
| 2798-2912(Online) psikologi di atas menunjukkan adanya perubahan
http://bajangjournal.com/index.php/J-ABDI
“citra tubuh” pada ibu hamil atau yang dalam istilah asing disebut body image. Citra
tubuh (body image) merupakan gambaran mental seseorang terhadap bentuk dan ukuran
tubuhnya; bagaimana seseorang mempersepsi dan memberikan penilaian atas apa yang dia
rasakan terhadap ukuran dan bentuk tubuhnya, dan atas bagaimana kira-kira penilaian
orang lain terhadap dirinya (Gani et al., 2014)
Perubahan citra tubuh (body image) menghasilkan sikap positif dan negatif pada
setiap wanita. Wanita yang memiliki citra tubuh negatif atau ketidakpuasan terhadap
tubuhnya, akan lebih mudah mengalami depresi dari pada yang merasa puas akan tubuhnya.
Seperti yang diungkapan Goldfield dari hasil penelitiannya, bahwa seorang wanita yang
merasa tidak puas dengan tubuhnya menunjukkan adanya gejala depresi yang lebih
berat, seperti anhedonia, harga diri negatif, dan tingginya angka depresi dari pada
yang memiliki kepuasan tinggi (Gani et al., 2014). Penelitian serupa juga mengatakan,
bahwa investasi disfungsional citra tubuh (body image) dapat merusak kesejahteraan pada
psikologis wanita salah satunya yaitu depresi (Kartikasari, 2013).
Depresi selalu melanda mereka yang sedang hamil, tetapi sering dari mereka tidak
pernah menyadari depresi, ini karena mereka menganggap kejadian ini merupakan hal yang
lumrah terjadi pada mereka, padahal jika tidak ditangani dengan baik dapat mempengaruhi
kesehatan ibu dan bayi (Kurniawan et al., 2013)
Berdasarkan Profil Kesehatan Indonesia, Angka Kematian Bayi di Indonesia pada tahun
2017 mencapai 24 kematian /1000 kelahiran. Angka tersebut masih jauh dari target SDGs
(Sustainable Development Goals) Tahun 2030 yakni 12 / 1000 kelahiran. Oleh sebab masih
dibutuhkan upaya-upaya kesehatan yang mendukung untuk dapat mencapai target SDGs
Tahun 2030 (Kemenkes, 2018)
Sumatera Selatan memiliki angka kematian bayi yang cukup tinggi. Pada tahun 2017,
angka kematian bayi di Sumatera Selatan mencapai 637 kasus. Dan kota Palembang
menyumbang 29 kasus kematian bayi pada tahun 2017. Penyebab kematian bayi
disebabkan oleh penyebeb langsung dan tidak langsung yang semuanya membutuhkan
intervensi efektif untuk meningkatkan kelangsungan hidup dan kesehatan bayi (Dinkes
Kota Palembang, 2018)
Oleh sebab itu, peran ibu sangat penting dalam penurunan AKB tersebut. Hal tersebut tidak
hanya dari faktor persalinan tetapi keterampilan ibu mengenali kondisi janin selama dalam
kandungan juga sangat berperan penting dalam menilai keadaan janin (Dinkes Kota
Palembang, 2018)
Ibu berperan penting untuk menciptakan kehamilan sehat karena janin sesungguhnya
berada dalam pengaruh dan pemantauan ibu. Ibu dapat dilatih untuk merasakan gerakan
janin sehingga terjadi hubungan khusus antara ibu dan janinnya. Ibu dapat dilatih dalam
keheningannya untuk merasakan gerakan janin (Holmes, 2011)
Penanda kesejahteraan janin meliputi denyut jantung janin, gerak napas janin, gerak badan
janin, tonus otot janin, serta jumlah air ketuban. Denyut jantung janin dapat dideteksi pada
janin berusia 6 minggu dengan alat ultrasonografi transvaginal. Bila janin diatas usia 14
minggu, denyut jantung janin dapat dideteksi dengan alat penghitung denyut jantung janin
berupa stetoskop Laenec atau Doppler (Holmes, 2011)
Janin sudah bisa beraktivitas sejak usia 10 minggu dimana keempat ekstremitas janin sudah
jelas terbentuk. Ibu dapat merasakan gerakan janin sekurang-kurangnya pada usia 20
minggu dimana janin sudah memiliki berat diatas 400 gram sehingga persepsi gerakannya
sudah cukup besar untuk dapat dirasakan (Soetjiningsih, 2012)
Gerakan janin secara terus-menerus dapat dirasakan oleh ibu sehingga kondisi janin dapat
terus-menerus dinilai dan dirasakan oleh ibu. Gerak janin juga dapat dilihat dengan
169
170
J-Abdi
Vol.1, No.12 Mei 2022
ultrasonografi. Aktivitas janin yang dapat dilihat dengan alat ultrasonografi berupa gerak
janin, gerak napas janin, tonus otot janin. Hal itu dapat diamati dengan alat ultrasonografi
dua dimensi, tiga dimensi, atau empat dimensi. Aktivitas janin yang real time atau sedang
berlangsung dapat dilihat dengan ultrasonografi. Jumlah volume air ketuban dapat dilihat
dengan alat ultrasonografi. Air ketuban dapat menggambarkan sistem pencernaan janin,
sistem pernapasan janin, sirkulasi plasenta/ari-ari, serta adanya kelainan pada janin
(Cunningham, 2007)
Janin yang bergerak menandakan proses kehidupan. Janin yang bergerak
menunjukkan sirkulasi darah yang membawa makanan dan nutrisi ibu ke janin berlangsung
baik sehingga janin memiliki energi untuk bergerak. Janin yang bergerak menunjukkan
aktivitas motorik, hubungan saraf-saraf sensorik dan motorik terintegrasi dengan baik.
Janin yang bergerak menunjukkan kematangan susunan saraf pusat dan otak janin. Janin
yang bergerak menunjukkan jumlah air ketuban yang cukup sehingga energi berupa gerak
janin dapat ditransmisikan ke dinding perut ibu. Janin yang bergerak merupakan hal yang
sangat berharga. Terlebih lagi janin yang bergerak membuat ibu dan ahli kandungan
merasa bahagia (Dewi, 2011)
Bila ada masalah pada janin, gerakan janin mula-mula akan berkurang. Persepsi ibu
terhadap gerakan janin yang berkurang dapat dilatih. Peran ibu dalam merasakan gerakan
janinnya sangatlah penting. Jangan sepelekan janin yang tidak bergerak karena
sesungguhnya gerak janin menunjukkan kesejahteraan janin. Janin yang tidak bergerak
dapat berarti janin dalam keadaan tidak sejahtera (Dewi, 2011)
Penelitian sebelumnya menyatakan bahwa ibu yang dilakukan hypnosis pada saat
kehamilan dan persalinan akan melahirkan bayi dengan APGAR Score yang baik/ normal
(Ngaziz et al., 2012)
Penelitian juga mendapatkan hasil bahwa dengan dilakukan hypno selama kehamilan, ibu
hamil merasa lebih tenang dan kecemasan menjadi berkurang. Relaksasi dengan disertai
gentlebirthing akan mendapatkan hasil yang lebih maksimal. Afirmasi yang didapatkan ibu
dapat meningkatkan kepedulian ibu terhadap janin yang sedang dikandung, sehingga ibu
mampu menilai sendiri frekuesi gerakan janin yang merupakan indikator kesejahtraan janin
dalam kandungan (Kusbandiyah, 2013)
Pembekalan dan pembentukan body image pada ibu hamil akan berperan dalam
menciptakan kehamilan yang sehat untuk menciptakan generasi yang cerdas. Dengan
demikian ibu akan peduli dan menikmati kehamilannya (Poejiastuti, 2014)
Adapun tujuan dalam kegiatan ini adalah meningkatnya keyakinan dan kepercayaan diri
ibu hamil, kecemasan ibu hamil dalam kehamilan dan persalinan, kemampuan ibu hamil
dalam melakukan hypnosis, kemampuan ibu hamil dalam melakukan pemantauan
kesejahteraan janin.
Praktik Mandiri Bidan (PMB) Lismarini merupakan salah satu PMB yang telah
melaksanakan kelas ibu hamil secara rutin. Akan tetapi pemanfaatan hypnosis pada kelas
ibu hamil belum digunakan secara maksimal. Salah satu kendalanya adalah masih ada
tenaga kesehatan yang belum mengikuti pelatihan hypnosis pada kehamilan. Berdasarkan
analisis tersebut, maka dilakukan kegiatan pengabdian masyarakat dengan judul
“membangun body image ibu hamil terintegrasi hypnosis dalam upaya pemantauan
kesejahteraan janin”
BAHAN DAN METODE

ISSN:Kegiatan
2797-9210pengabdian http://bajangjournal.com/index.php/J-ABDI
kepada masyarakat
(Print) | 2798-2912(Online) dilaksanakan di Praktik Mandiri Bidan
(PMB)
Lismarini Kota Palembang pada tanggal 12 Oktober 2020. Adapun kegiatan yang
dilakukan yaitu tahap persiapan (Perizinan kegiatan pengabdian kepada masyarakat,

Persiapan media dan alat, memastikan jumlah ibu hamil yang akan ikut dalam pelaksanaan
kelas ibu hamil , mempersiapkan jadwal pelaksanaan pada ibu hamil serta mempelajari
materi yang akan disampaikan), Tahap Pelaksanaan (pretest untuk mengetahui
pengetahuan ibu tentang hypnosis dan cara pemantauan kesejahteraan janin, praktek teknik
melakukan self hpnosis, praktik cara menilai kesejahteraan janin) dan tahap evaluasi (post
test untuk mengevaluasi pengetahuan dan kemampuan ibu dalam menilai kesejahteraan
janin).
HASIL
Berdasarkan hasil kegiatan pengabdian masyarakat yang dilakukan didapatkan hasil
yaitu:
1. Karakteristik Peserta
Gambar 1. Distribusi Usia Responden
Hasil kegiatan pengabdian kepada masyarakat didapatkan bahwa sebagian besar

karakteristik responden berdasarkan umur didapatkan responden yang berada pada
kelompok umur diatas 20 tahun yaitu sebanyak 26 peserta (69%). Sedangkan
kelompok usia dibawah 20 tahun 11 orang (31%).
Jika diamati dari tingkat usia, maka sebagian besar responden berada pada usia
reproduktif. Hal ini berpengaruh kepada kesehatan dan keterampilan peserta. Hal ini
sejalan dengan teori yang dikemukakan oleh Notoatmodjo (2012) bahwa usia
berpengaruh terhadap daya tangkap dan pola pikit seseorang. Semakin bertambah usia
seseorang maka akan semakin berkembang pula daya tangkap dan pola pikirnya
sehingga pengetahuan yang diperolahnya akan semakin membaik.
2. Pendidikan
Gambar 2. Distribusi Pendidikan Responden

tingkat pendidikan peserta ini adalah SMA sebanyak 20 responden (56%).
171
172
J-Abdi
Vol.1, No.12 Mei 2022
Teori yang menyatakan bahwa pendidikan berarti bimbingan yang diberikan seseorang
kepada orang lain terhadap suatu hal agar mereka dapat memahami. Tidak dapat
dipungkiri bahwa makin tinggi pendidikan seseorang semakin mudah pula mereka
menerima informasi, dan pada akhirnya makin banyak pula pengetahuan yang
dimilikinya. Sebaliknya, jika seseorang tingkat pendidikannya rendah, akan
menghambat perkembangan sikap seseorang terhadap penerimaan, informasi dan nilai-
nilai yang baru diperkenalkan (Arikunto, 2006)
Selain itu menurut teori yang dikemukakan oleh Notoatmodjo tahun 2012 bahwa jalur
pendidikan formal akan membekali seseorang dengan dasar-dasar pengetahun, teori
dan logika, pengetahuan umum, kemampuan analisis serta pengembangan kepribadian
3. Paritas
Gambar 3. Distribusi Paritas Responden

paritas peserta adalah multigravida yaitu 23 orang (64%). Sesuai dengan penelitian
Budiarti dkk (2018) bahwa terdapat hubungan paritas terhadap pengetahuan dan
keterampilan ibu hamil dalam mengelola kehamilan.
4. Pengetahuan ibu hamil sebelum dilakukan pelatihan

Pengetahuan ibu hamil sebelum dilakukan pelatihan didapatkan hasil bahwa
sebagian besar ibu hamil memiliki tingkat pengetahuan yang kurang dalam memantau
kesejahteraan janin dan melakukan self hypnosis.
Gambar 4. Pengetahuan Responden Sebelum Dilakukan Intervensi
Hal ini disebabkan oleh minimnya informasi mengenai teknik self hypnosis dan
memantau kesejahteraan janin. Para ibu hamil hanya mampu mengetahui kesejahteraan
janin dengan merasakan gerakan janin. Tetapi ibu belum memahami kapan dan
bagaimana
ISSN: 2797-9210 teknik
(Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI
mengukur kesejahteraan janin tersebut.
5. Pengetahuan ibu hamil setelah dilakukan pelatihan

Setelah diberikan pelatihan maka terjadi peningkatan pengetahuan dan
keterampilan dari yang semula tidak memiliki pengetahuan dan keterampilan menjadi
memiliki pengetahuan dan keterampilan tentang melakukan self hypnosis dan
memantau kesejahteraan janin.
Gambar 5. Pengetahuan Responden Setelah Dilakukan Intervensi
Pemanfaatan self hypnosis pada kehamilan sangat berpengaruh kepada peningkatan

body image ibu dalam menghadapi kehamilan dan persalinan. Dan ibu hamil mampu
mengelola kehamilannya dan mampu memantau kesejahteraan janinnya.
PEMBAHASAN
1. Edukasi membangun body image terintegrasi hypnosis dan pemantauan kesejahteraan
janin
Pelaksanaan kegiatan edukasi membangun body image terintegrasi hypnosis dan
pemantauan kesejahteraan janin pada kehamilan di Praktik Mandiri Bidan (PMB)
Lismarini telah dilaksanakan dengan lancar. Kegiatan ini dilakukan diawali dengan
pretest pengetahuan hypnosis dan pemantauan kesejahteraan janin. Kemudian
dilanjutkan dengan edukasi body image terintegrasi hypnosis dan pemantauan
kesejahteraan janin sebagaimana ditunjukkan pada gambar 6. Tujuannya adalah untuk
memberikan pengetahuan ibu hamil tentang manfaat hypnosis dan pemantauan
kesejahteraan janin ini dalam upaya menciptakan image positif dalam diri ibu hamil.
Agar para ibu hamil mampu mencintai setiap perubahan pada dirinya dan janin di dalam
kandungannya. Dengan hal ini diharapkan ibu hamil mampu melaksanakannya secara
mandiri di rumah masing-masing agar para ibu hamil mendapatkan hasil yang
maksimal.
173
174
J-Abdi
Vol.1, No.12 Mei 2022
Gambar 6. Edukasi membangun body image terintegrasi hypnosis dan pemantauan

kesejahteraan janin
Gambar 7. Media lefleat edukasi membangun body image terintegrasi hypnosis dan
pemantauan kesejahteraan janin
2. Praktek membangun body image terintegrasi hypnosis dan pemantauan kesejahteraan

janin
Tahapan setelah pelaksanaan edukasi adalah tahapan praktek/ simulasi tentang
membangun body image terintegrasi hypnosis dan pemantauan kesejahteraan janin yang
benar. Hal ini membuat para ibu hamil terlibat secara langsung dalam kegiatan praktek
ini. Praktek/ simulasi ini dipandu dan di dampingi oleh fasilitator agar pelaksananaan
membangun body image terintegrasi hypnosis dan pemantauan kesejahteraan janin ini
dapat dipraktekkan dengan benar sehingga meningkatkan kemampuan ibu dalam
melaksanakan hypnosis secara mandiri dan rutin sebagaimana ditunjukkan pada gambar
8.
Gambar 8. Praktek membangun body image terintegrasi hypnosis dan pemantauan

kesejahteraan janin yang Benar oleh Fasilitator sebagai Pendamping
KESIMPULAN
Kegiatan pengabdian kepada masyarakat yang dilaksanakan di Praktik Mandiri Bidan
(PMB) Lismarini Kota Palembang terlaksana dengan baik yaitu meliputi edukasi
membangun body image terintegrasi hypnosis dan pemantauan kesejahteraan janin dan
ISSN:praktek membangun
2797-9210 body image terintegrasi
(Print) | 2798-2912(Online) hypnosis dan pemantauan kesejahteraan janin
http://bajangjournal.com/index.php/J-ABDI
JMM (Jurnal Masyarakat
Mandiri)
yang didampingi oleh fasilitator. Hasil dari kegiatan pengabdian masyarakat ini adalah adanya peningkatan
pengetahuan dan keterampilan ibu hamil tentang membangun body image terintegrasi hypnosis dan
pemantauan kesejahteraan janin. Serta sebagai upaya menciptakan image positif dalam diri ibu hamil. Agar
para ibu hamil mampu mencintai setiap perubahan pada dirinya dan janin di dalam kandungannya
Implikasinya adalah para ibu-ibu hamil mampu menerapkan hypnosis ini secara mandiri, sehingga dapat
meningkatkan kemampuan ibu hamil dalam deteksi dini resiko kehamilan.
REFERENSI
Cunningham. (2007). Obstetri William (8th ed.). EGC.
Dewi, T. (2011). Asuhan Kehamilan Untuk Kebidanan. Salemba Medika.
Dinkes Kota Palembang. (2018). Profil Kesehatan Kota Palembang Tahun 2017.
Gani, R., Bidjuni, H., & Lolong, J. (2014). Hubungan Perubahan Citra Tubuh (Body Image) Dengan Depresi
Pada Ibu Hamil Trimester Ii Dan Trimester Iii Dipuskesmas Tilango Kabupaten Gorontalo. Jurnal
Keperawatan UNSRAT, 2(2), 107337.
Holmes, P. (2011). Buku Ajar Ilmu Kebidanan. EGC.
Janiwarty. (2013). Pendidikan Psikologi Untuk Bidan. Rapha Publishing.
Kartikasari, N. Y. (2013). Body dissatisfaction terhadap psychological well. Jurnal Ilmiah Psikologi
Terapan, 1(2), 304–323.
Kemenkes. (2018). Survey Demografi Kesehatan Indonesia 2017.
Kurniawan, E. S., Ratep, N., Bagian, W. W., Smf, /, Fakultas, P., Universitas, K., / U., Sakit, R., Pusat, U., &
Denpasar, S. (2013). Faktor Penyebab Depresi Pada Ibu Hamil Selama Asuhan Antenatal Setiap
Trimester Factors Lead To Depresion During Antenatal Care Every Trimester of Pregnant Mother. E-
Jurnal Medika Udayana, perinatal Depressive, 1–13. http://ojs.unud.ac.id/index.php/
eum/article/viewFile/4936/3726#page=3&zoom=auto,-12,508
Kusbandiyah, J. (2013). Analisis Implementasi Program Kelas Ibu Hamil oleh Bidan Puskesmas di Kota
Malang. Journal of Chemical Information and Modeling, 53(9), 1689–1699.
Ngaziz, L., Widyawati, M., & Mulyati, L. (2012). http://jurnal.unimus.ac.id. Jurnal Kebidanan.
Poejiastuti, A. (2014). Konsep Kehamilan Sehat Upaya Mencetak Generasi Cerdas.
Artikel Kesehatan Nasional.
Soetjiningsih. (2012). Tumbuh Kembang Anak. EGC.

2951
Ivanna Beru Brahmana, Penyuluhan Pentingnya Ante...
http://journal.ummat.ac.id/index.php/jmm
Vol. 6, No. 4, Agustus 2022, Hal. 2950-2960
e-ISSN 2614-5758 | p-ISSN 2598-8158
: https://doi.org/10.31764/jmm.v6i4.9315
PENYULUHAN PENTINGNYA ANTE NATAL CARE PADA IBU HAMIL

DALAM UPAYA PEMANTAUAN KESEJAHTERAAN JANIN
Ivanna Beru Brahmana1, Nisrina Nurrohmah2, Nur Sabrina Barin Putri3, Bintang
Mukti Asmara Jati4, Muhammad Ganang Garnida5,
Ufita Dauma Ummi Nusuka Wardhani6
1
Bagian Obstetri & Ginekologi, Program Studi Pendidikan Dokter, Fakultas Kedokteran & Ilmu Kesehatan,
Universitas Muhammadiyah Yogyakarta, Indonesia
2,3,4,5,6
Mahasiswa Program Studi Pendidikan Kedokteran, Panitia TBM Alert 2022, Fakultas Kedokteran & Ilmu
Kesehatan, Universitas Muhammadiyah Yogyakarta, Indonesia
ivanna@umy.ac.id1 , nisrinanuur@gmail.com2 , nursabrinabp@gmail.com3 , intersia30@gmail.com4 ,
ganang.gar@gmail.com5, ufita1902@gmail.com6
ABSTRAK
Abstrak: Pemeriksaan kehamilan rutin memberikan informasi perkembangan janin dan kesehatan ibu
hamil. Kegiatan tersebut dinamakan ante natal care (ANC). Perkembangan janin sesuai, berlebih atau
kurang dari perhitungan usia kehamilan diketahui dengan akurat melalui pemeriksaan ultra sono grafi
(USG). Pengawalan kehamilan lebih informatif, diharapkan mendapatkan outcome bayi saat lahir
bugar, ibu hamil pun cepat pulih. Tujuan untuk meningkatkan kesadaran ibu hamil melakukan ANC
secara rutin. Metode berupa penyuluhan ibu hamil yang bertempat tinggal di sekitar wilayah kampus
Universitas Muhammadiyah Yogyakarta, yang melibatkan peran serta mahasiswa Prodi Pendidikan
Dokter FKIK UMY yang tergabung dalam panitia TBM Alert tahun 2022. Pengabdian diikuti 38
peserta. Rerata nilai pretes 40, dengan nilai tertinggi dan terendah adalah 80 dan nol. Setelah diberikan
penyuluhan terdapat peningkatan rerata nilai postes, nilai tertinggi, dan nilai terendah masing-masing
70, 100, dan 20. Peningkatan nilai rerata, nilai tertinggi, dan nilai terendah masing-masing mencapai
75%, 25%, dan 100%. Penyuluhan memberikan peningkatan pengetahuan ibu hamil tentang pentingnya
ANC, terlihat dari peningkatan nilai postes yang berarti materi penyuluhan disimak dengan baik oleh
para peserta.
Kata Kunci: ante natal care; ibu hamil; penyuluhan.
Abstract: Routine pregnancy check-ups provide information on fetal development and the health of
pregnant women. This activity is called ante natal care (ANC). Fetal development according to, excess
or less than the calculation of gestational age is known accurately through ultrasound examination.
Pregnancy control is more informative, it is hoped that the baby will be born fit, and pregnant women
will recover quickly. The aim is to increase awareness of pregnant women doing ANC regularly. The
method is in the form of counseling for pregnant women who live around the Yogyakarta
Muhammadiyah University campus area, which involves the participation of students from the
Medical Education Study Program, FKIK UMY who are members of the TBM Alert committee in
2022. The service was attended by 38 participants. The mean pretest score was 40, with the highest
and lowest scores being 80 and zero. After being given counseling, there was an increase in the
average posttest score, the highest score, and the lowest score, respectively, by 70, 100, and 20. The
increase in the average, highest and lowest scores reached 75%, 25%, and 100%, respectively.
Counseling provides increased knowledge of pregnant women about the importance of ANC, as seen
from the increase in post-test scores, which means that the participants listened to the counseling
materials well.
Keywords: ante natal care; pregnant mother; counseling.
Article History:
Received: 21-06-2022
Revised : 14-07-2022
Accepted: 21-07-2022 This is an open access article under the
Online : 28-08-2022 CC–BY-SA
license
295
1
JMM (Jurnal Masyarakat
Mandiri)
A. LATAR BELAKANG
Pemeriksaan ante natal care (ANC) merupakan pemeriksaan kehamilan
secara berkala dan bertujuan untuk meningkatkan kesehatan fisik dan mental
pada ibu hamil (bumil) secara optimal. Ibu hamil diharapkan mampu
menghadapi masa persalinan, nifas, persiapan pemberian ASI eksklusif, dan
kembalinya kesehatan alat reproduksi dengan wajar. Pemeriksaan kehamilan
saat ini dilakukan minimal enam kali selama masa kehamilan, yaitu 1 kali
pemeriksaan pada trimester pertama, 2 kali pemeriksaan pada trimester kedua,
dan 3 kali pemeriksaan pada trimester ketiga (Aziz, 2020).
Tujuan secara umum yang hendak dicapai dengan pemeriksaan ANC secara
rutin yang disampaikan oleh Kemenkes RI tahun 2018 adalah: (1) Memantau
kehamilan dengan mengetahui kesehatan ibu dan tumbuh kembang janin; (2)
Mengetahui sejak dini kemungkinan adanya komplikasi kehamilan, termasuk
adanya riwayat penyakit dan tindakan pembedahan;
(3) Meningkatkan dan mempertahankan kesehatan ibu dan bayi; (4)
Mempersiapkan proses persalinan yang aman, sehingga dapat melahirkan bayi
dengan selamat serta meminimalkan trauma yang mungkin terjadi saat
persalinan; (5) Menurunkan angka kematian dan angka kesakitan ibu;
(6) Mempersiapkan peran ibu dan keluarga saat kelahiran anak agar anak
menjalani tumbuh kembang yang normal; dan (7) Mempersiapkan ibu melewati
masa nifas dengan baik dan memberikan ASI eksklusif pada bayi. Pemeriksaan
ANC dapat dilakukan di puskesmas, klinik, ataupun rumah sakit, dan dapat
dilayani oleh bidan, perawat, dokter umum, maupun Dokter Spesialis Obstetri
dan Ginekologi (Dokter Spesialis Kebidanan Dan Kandungan) (Kemenkes RI,
2018).
Pemeriksaan ANC merupakan upaya lain untuk menurunkan angka
kematian ibu (AKI) karena melahirkan. Dengan melakukan ANC, adanya
gangguan yang mungkin terjadi saat kehamilan dapat terdeteksi sehingga
mencegah terjadinya komplikasi pada saat kehamilan maupun persalinan.
Cakupan ANC mencatat kunjungan-1 (K1) dan kunjungan-4 (K4). Catatan K1
adalah cakupan bumil yang pertama kali ANC, yang menunjukkan indikator
akses. Catatan K4 adalah cakupan bumil dengan ANC minimal empat kali
sesuai distribusi waktu dan sesuai standar yang menggambarkan tingkat
perlindungan bumil di suatu wilayah (Dinas Kesehatan DIY, 2020). Cakupan K-
4 wilayah Kabupaten Bantul sebesar 86,4% menduduki dua terbawah
dibandingkan kabupaten lain di wilayah Propinsi Daerah Istimewa Yogyakarta
(DIY) (Dinas Kesehatan DIY, 2020).
Universitas Muhammadiyah Yogyakarta (UMY) berada di wilayah
Kabupaten Bantul, untuk itu Prodi Pendidikan Dokter Fakultas Kedokteran
& Ilmu Kesehatan (PSPD FKIK) melalui kegiatan Tim Bantuan Medis Asy-
Syifaa’ Life Rescue Emergency Team (TBM Alert) berkontribusi untuk
meningkatkan kesadaran bumil melakukan ANC dengan memeriksakan
kehamilan mereka secara rutin. Hal tersebut
2952 | JMM (Jurnal Masyarakat Mandiri) | Vol. 6, No. 4, Agustus 2022, hal. 2950-2960
sekaligus menjadi tujuan pengabdian ini dan solusi dari permasalahan mitra
pengabdian. Mitra pengabdian adalah bumil yang bertempat tinggal di sekitar
kampus UMY, yang termasuk wilayah Kabupaten Bantul di mana cakupan
K-4 menduduki dua terbawah di Propinsi DIY. Mitra diutamakan yang
tergolong tingkat ekonomi menengah ke bawah, diprioritaskan pemegang Kartu
Indonesia Sehat Penerima Bantuan Iuran (KIS PBI). Persentase penduduk di
daerah perkotaan dan pedesaan yang memiliki jaminan kesehatan menurut
karakteristik pada tahun 2019 di Propinsi DIY sebanyak 80,08%(BPS, 2019).
Kegiatan pengabdian serupa pernah dilakukan pengabdi lima tahun yang lalu,
namun bertempat di lokasi lain. Dalam kegiatan pengabdian tersebut,
penyuluhan juga memberikan hasil terjadi peningkatan pengetahuan ibu hamil
tentang pentingnya ANC bagi bumil (Brahmana, 2022).
B. METODE PELAKSANAAN
Kegiatan pengabdian melalui tahapan perencanaan, pelaksanaan, dan
evaluasi.
1. Perencanaan Kegiatan
Perencanaan pengabdian meliputi: menentukan tema kegiatan, narasumber,
sasaran/peserta kegiatan, waktu dan tempat kegiatan, serta bentuk kegiatan.
Berdasarkan permasalahan mitra, maka ditentukan tema kegiatan mengenai
pentingnya ANC dilakukan secara rutin oleh bumil dengan narasumber dosen
FKIK UMY Bagian Kebidanan & Kandungan. Peserta kegiatan sebagai mitra
adalah bumil yang bertempat tinggal di sekitar kampus UMY atau dalam
wilayah Kecamatan Kasihan, Kabupaten Bantul. Pengabdian diharapkan dapat
menjaring 50 bumil terutama yang tergolong tingkat ekonomi menengah ke
bawah, diprioritaskan pemegang KIS PBI. Bentuk kegiatan berupa penyuluhan
dengan materi ANC sesuai dengan kompetensi narasumber. Oleh karena masih
dalam kondisi Covid- 19, maka kegiatan dilakukan secara online melalui zoom
meeting, direncanakan hari Minggu, 27 Februari 2022, jam 08.45 – 10.30 WIB.
2. Pelaksanaan Kegiatan
Kegiatan pengabdian berhasil dilaksanakan pada hari Minggu, 27 Februari
2022, jam 08.45 - 10.30 WIB, melalui zoom meeting. Peserta pengabdian
adalah bumil yang bersedia mengikuti kegiatan pengabdian melalui zoom
meeting sebanyak 38 orang. Materi yang disampaikan berjudul “Penyuluhan
Kehamilan” berupa presentasi power point (PPT) oleh narasumber dr. Ivanna
Beru Brahmana, SpOG(K) sebagai dosen tetap sekaligus pengabdi dalam
kegiatan ini.

2953
3. Evaluasi Kegiatan
Evaluasi dilakukan setelah pengabdian selesai dilaksanakan secara
keseluruhan. Dalam hal ini termasuk merekap nilai pretes dan postes peserta
pengabdian terhadap pertanyaan-pertanyaan yang diberikan. Pretes dilakukan
sebelum penyampaian materi, sedangkan postes dilakukan setelah penyampaian
materi. Dengan demikian nilai postes menggambarkan adakah peningkatan
kesadaran peserta pengabdian terhadap materi yang disampaikan oleh
narasumber. Keberhasilan kegiatan dinilai dengan adanya peningkatan nilai
postes terhadap nilai pretes peserta.
C. HASIL DAN PEMBAHASAN

Pengabdian terlaksana pada hari Minggu, 27 Februari 2022, jam 08.45 -
10.30 WIB, melalui zoom meeting, dengan peserta pengabdian sebanyak 38
orang. Panitia memperkirakan dapat menjaring peserta sebanyak 50 orang
bumil. Setidaknya didapatkan 76% capaian peserta, menunjukkan antusiasme
bumil untuk menimba ilmu dari materi penyuluhan karena lebih dari 75% dari
rencana, seperti terlihat pada Gambar 1 dan Gambar 2.
Gambar 1. Flyer pengabdian
Gambar 1 menampilkan flyer pengabdian, di mana semula kegiatan

pengabdian akan dilakukan dalam dua bentuk kegiatan yaitu penyuluhan ANC
melalui zoom meeting dan pemeriksaan USG gratis pada seluruh peserta bumil.
Adanya kemungkinan risiko berkerumum dan mengantri lama saat
pemeriksaan USG gratis, maka akhirnya kegiatan kedua tersebut dibatalkan,
oleh karena masih adanya risiko ancaman Covid-19. Panitia juga menyediakan
virtual background pengabdian dalam zoom
295
3
meeting. Virtual background digunakan oleh seluruh peserta selama kegiatan

online berlangsung. Langkah-langkah tersebut merupakan pelaksanaan dari
perencanaan kegiatan yang telah dijabarkan, seperti terlihat pada Gambar 2.
Gambar 2. Penyampaian materi “Penyuluhan Kehamilan” oleh

narasumber
Langkah-langkah berikut merupakan penjabaran dari pelaksanaan kegiatan

pengabdian. Gambar 2 menunjukkan narasumber menyampaikan materi
penyuluhan secara online dengan menggunakan presentasi PPT. Hal-hal yang
ditekankan oleh narasumber antara lain: 1. Perlunya minimal 6x pemeriksaan
ANC pada ibu hamil, di mana minimal 2x pemeriksaan dilakukan oleh dokter.
Apabila kondisi kehamilan mengalami suatu gangguan atau ketidaksesuaian
dengan usia kehamilan, maka bumil bisa menambah jumlah kunjungan ANC.
Dalam kondisi Omicron seperti saat ini, kunjungan ANC bisa juga dilakukan
melalui telemedicine (Aziz, 2020);
2. Pentingnya bumil mengonsumsi minimal 90 tablet penambah darah. Prevalensi
bumil menderita anemia secara global di seluruh dunia berkisar 38,2%, dengan
prevalensi tertinggi terjadi di Asia Tenggara dan Afrika, masing-masing sebesar
48,7% dan 46,3% (WHO, 2016); 3. Pentingnya mengonsumsi calcium yang
diresepkan oleh dokter saat ANC. Defisiensi calcium bisa berisiko terjadinya
preeklampsia (WHO, 2016), suatu kejadian hipertensi/penyakit tekanan darah tinggi
yang diderita bumil karena kehamilannya, walaupun pada saat tidak hamil bumil
tersebut tidak menderita hipertensi/penyakit tekanan darah tinggi; dan 4. Dengan
melakukan ANC rutin akan terdeteksi secara dini permasalahan kesehatan pada ibu
dan gangguan tumbuh kembang janin termasuk risiko stunting. Hal yang
menggembirakan adalah Kabupaten Bantul Propinsi DIY tidak termasuk salah satu
dari 100 kabupaten/kota prioritas intervensi yang tercatat prevalensi stunting
(TNP2K, 2017). Dengan menaati anjuran dokter saat ANC, diharapkan ibu dan
janin sehat dan sejahtera.

2955
Penyuluhan serupa juga dilakukan di Pontianak, dengan pemberian materi
pentingnya pemeriksaan kehamilan dengan didahului pretes dan diakhiri dengan
postes. Hal yang membedakan adalah peserta pengabdian selain bumil, juga
dihadiri oleh kader kesehatan, selain itu kegiatan berupa pemutaran video
tutorial pemeriksaan kehamilan di masa pandemi Covid-
19 serta pembagian poster edukasi mengenai pentingnya pendampingan bumil
(Riana et al., 2021). Materi penyuluhan tentang pengertian dan manfaat ANC
terpadu juga dilakukan di Mojokerto. Hal yang membedakan, pengabdian
tersebut dilakukan selama 4x pertemuan, setiap hari Selasa dan Rabu, sesuai
dengan hari kunjungan bumil di Puskesmas Mojosari. Sasaran adalah bumil
yang memeriksakan kehamilan dalam 4x pertemuan tersebut, dengan total
jumlah peserta 40 orang (Hety et al., 2021).
Pentingnya pemahaman bumil tentang risiko anemia, selaras dengan
pentingnya bumil mengetahui golongan darah mereka. Pengabdian di
Tasikmalaya melakukan pemeriksaan golongan darah pada bumil, untuk
antisipasi seandainya dibutuhkan transfusi saat persalinan nanti, maka bumil
sudah mengetahui golongan darah masing-masing. Hasil pemeriksaan
menunjukkan bumil dengan golongan darah A, B, O, dan AB masing-masing
sebesar 21%, 29%, 36% dan 14% (Meri, 2020). Pengabdian dengan materi
penyuluhan anemia dalam kehamilan dan pentingnya mengonsumsi tablet Fe
dilakukan di Cilacap. Pemeriksaan kehamilan yang dilakukan dalam
pengabdian tersebut berupa pemeriksaan laboratorium dengan mengukur kadar
Hb dan pemeriksaan urine (Septiyaningsih et al., 2020). Pengabdian dengan
melakukan pemeriksaan Hb dan golongan darah juga dilakukan di Bireuen,
dengan hasil didapatkan 13,33% (2/15) bumil menderita anemia, sedangkan
golongan darah A, B, O masing-masing 3, 4,
8 orang, dan tidak ada bumil yang bergolongan darah AB (Nurhidayati,
2020).
Preeklampsia merupakan salah satu penyakit berisiko tinggi yang perlu
diwaspadai pada saat kehamilan. Ibu hamil terdeteksi menderita hipertensi/penyakit
tekanan darah tinggi saat ANC, padahal mereka tidak mengalaminya saat tidak
hamil. Untuk itu ketrampilan petugas kesehatan tentang cara memeriksa tekanan
darah sangat diperlukan. Hal inilah yang menjadi kegiatan pengabdian di Metro
dengan melatih kader posyandu tentang ketrampilan dasar pengukuran tekanan
darah dan LILA (Riyanto et al., 2020), seperti terlihat pada Gambar 3 dan
Gambar 4.
295
5
Gambar 3. Beberapa peserta rise hand mengajukan pertanyaan
Gambar 4. Peserta pengabdian menyimak materi
Gambar 3 dan Gambar 4 menunjukkan antusiasme peserta menyimak

materi dan mengajukan pertanyaan. Terdapat 23 pertanyaan yang diajukan,
dijawab secara langsung oleh narasumber. Beberapa pertanyaan yang diajukan
antara lain: (1) Usia kehamilan saya 10 minggu, mengeluhkan mual dan
muntah, saat muntah kadang-kadang sampai muntah darah, apakah hal ini masih
wajar atau berbahaya?; (2) Umur kehamilan saya 36 minggu dengan ukuran
lingkar lengan atas (LILA) 23, apakah bisa melakukan persalinaan normal?;
dan (3) Usia kehamilan saya
24 minggu, apakah kepala janin harus sudah di bawah? Satu per satu
pertanyaan-pertanyaan tersebut dijawab oleh narasumber. Dengan
demikian diharapkan peserta semakin memahami pentingnya melakukan
pemeriksaan ANC secara rutin dan melaksanakannya dalam kehamilan ini.
Dengan kondisi pandemi yang belum berakhir seperti saat ini,
pengabdian pada bumil dengan mengingatkan untuk tetap menjaga pola
hidup bersih dan sehat dan menerapkan protokol kesehatan (prokes)
sangatlah penting. Pola hidup bersih dan sehat dalam hal ini dengan
memberikan demonstrasi 7 langkah cuci tangan pakai sabun (Lestari et al.,
2021), seperti terlihat pada Gambar 5.

2957
100
80 Rerata
60 Nilai Tertinggi
40
Nilai Terendah
20
0
Nilai Pretes Nilai Postes
Gambar 5. Nilai Pretes dan Postes Peserta Pengabdian
Evaluasi kegiatan pengabdian seperti tampak pada Gambar 5 yang

menunjukkan nilai pretes dan postes peserta pengabdian terhadap pertanyaan
yang diajukan oleh panitia pengabdian. Keseluruhan kriteria penilaian postes
mengalami peningkatan dibandingkan nilai pretes. Rerata nilai naik menjadi 70
dari 40, nilai tertinggi menjadi 100 dari 80, dan nilai terendah menjadi 20 dari
nol. Hasil ini menunjukkan bahwa materi yang disampaikan dapat disimak
dengan baik oleh peserta pengabdian dan pemberian penyuluhan mampu
meningkatkan pengetahuan peserta. Pemberian penyuluhan juga dapat
meningkatkan pengetahuan peserta merupakan hasil pengabdian penyuluhan
kehamilan di Pontianak (Riana et al., 2021).
Kegiatan penyuluhan ini melibatkan para mahasiswa dari PSPD FKIK
UMY yang tergabung dalam TBM Alert, yang menunjukkan peran aktif
mahasiswa mengaplikasikan ilmu mereka langsung kepada masyarakat. Selain
itu akan meningkatkan kepedulian mahasiswa terhadap masyarakat sekitar,
terutama yang menyangkut permasalahan kesehatan. Di samping para
mahasiswa berupaya melatih diri mampu berkomunikasi secara langsung
kepada masyarakat sebagai tindakan pelayanan mereka kelak. Hal ini
dikarenakan ilmu kedokteran juga memiliki seni berkomunikasi, untuk itu
pengabdian ini sekaligus sebagai upaya untuk melatih diri.
Secara umum pengabdian berupa penyuluhan ini berjalan lancar, mulai dari
tahapan perencanaan dan pelaksanaan, yang terlihat dari 76% (38/50) peserta
bersedia mengikuti pengabdian. Pada tahap evaluasi didapatkan adanya kendala
batalnya kegiatan pemeriksaan USG gratis, dikarenakan kekhawatiran panitia
terhadap situasi Omicron yang masih berisiko saat ini. Dengan adanya 38 orang
peserta, ditambah total panitia sebanyak 30 orang, risiko terjadi kerumunan dan
lamanya mengantri, berisiko terjadinya penularan Omicron. Dengan kondisi
tersebut, kegiatan kedua berupa pemeriksaan USG gratis ditiadakan. Peserta
pengabdian dianjurkan untuk bisa melakukan pemeriksaan USG ke fasilitas
pelayanan kesehatan (yankes) setempat. Dengan kartu KIS PBI yang mereka
miliki
295
7
maka pemeriksaan USG di fasilitas yankes yang ditunjuk pun akan bebas dari
biaya pemeriksaan.
Kegiatan pengabdian serupa lima tahun yang lalu dilakukan pengabdi
bertempat di RS PKU Gamping Yogyakarta berupa penyuluhan pemeriksaan
ANC pada bumil diikuti dengan pemeriksaan USG gratis. Hal yang berbeda
dengan pelaksanaan penyuluhan saat itu adalah dahulu penyuluhan dilakukan
dengan offline/tatap muka dan diikuti oleh 26 orang peserta. Pengabdian saat ini
menunjukkan adanya penambahan keikutsertaan peserta dengan materi serupa,
peserta tetap berantusias menambah pengetahuannya meski dilakukan secara
online melalui zoom meeting. Kemungkinan justru hal ini dirasakan sebagai
suatu kemudahan dibandingkan harus hadir offline, dan sebagai suatu
perkembangan teknologi saat ini dibandingkan dengan lima tahun yang lalu
(Brahmana, 2022).
100
90
80
70
60 Puas/Bermanfaat
50
40
Tidak Puas/tidak
30
bermanfaat
20
10
0
Kepuasan Manfaat
Gambar 6. Kepuasan dan manfaat pelaksanaan pengabdian
Gambar 6 menunjukkan 100% peserta merasakan puas terhadap

pelaksanaan penyuluhan pengabdian dengan materi yang sesuai dengan
kehamilan mereka. Di samping terjawabnya pertanyaan-pertanyaan peserta oleh
narasumber, juga dalam kondisi online pun mereka tetap bisa mendapatkan
pengetahuan yang bermanfaat dalam pengawalan kehamilan mereka. Hal ini
terlihat dari diagram tersebut, di mana 100% peserta merasakan bahwa
penyuluhan pengabdian ini bermanfaat bagi mereka. Batalnya pemeriksaan
USG gratis tidak menyurutkan keinginan peserta untuk melakukan pemeriksaan
USG di yankes setempat sesuai dengan anjuran panitia pengabdian. Hal serupa
juga terjadi di kabupaten Gowa, di mana adanya pengabdian penyuluhan
kehamilan juga disambut dengan senang oleh peserta pengabdian (Hasnah et
al., 2021).

2959
D. SIMPULAN DAN SARAN

Simpulan dari pengabdian adalah penyuluhan memberikan peningkatan
kesadaran bumil tentang pentingnya pemeriksaan ANC. Adanya peningkatan
nilai postes dibandingkan nilai pretes menunjukkan materi penyuluhan disimak
dengan baik oleh para peserta. Peningkatan nilai rerata, nilai tertinggi, dan nilai
terendah masing-masing mencapai 75%, 25%, dan 100%. Dengan ketaatan
bumil melakukan ANC diharapkan kesejahteraan bumil dan perkembangan
janin dapat terpantau dengan cermat, sehingga diharapkan bumil akan
melahirkan bayi yang segar bugar dan pulihnya kembali bumil akan lebih cepat
untuk bisa beraktifitas kembali. Saran untuk keberlanjutan pengabdian adalah
untuk bisa secara berkesinambungan melakukan kegiatan serupa dalam cakupan
yang lebih luas di tahun-tahun mendatang. Dengan demikian sasaran bumil
akan lebih banyak yang terlayani.
UCAPAN TERIMA KASIH

Kami ucapkan terimakasih yang sebesar-besarnya kepada Panitia TBM Alert
PSPD FKIK UMY yang telah menyelenggarakan dan mendanai pengabdian ini.
Kami ucapkan terimakasih juga kepada para bumil yang telah berkenan hadir
sebagai peserta pengabdian dan berperan aktif dalam seluruh rangkaian kegiatan
pengabdian.
DAFTAR RUJUKAN
Aziz, M. A. et al. (2020). Rekomendasi Penanganan Infeksi Virus Corona (Covid-19)
Pada Maternal (Hamil, Bersalin Dan Nifas) Revisi 2. Jakarta. Penerbit:Pokja
Infeksi Saluran Reproduksi Perkumpulan Obstetri Dan Ginekologi Indonesi a
Tahun2020, 3–15. https://pogi.or.id/publish/rekomendasi-penanganan-infeksivirus-
corona-covid-19-pada-maternal/
BPS. (2019). Katalog: 4201005 Profil Statistik Kesehatan 2019. Profil Statistik
Kesehatan, 1–431. www.bps.go.id. Jakarta. Penerbit: Badan Pusat Statistik.
Brahmana, I. (2022). Pengabdian Edukasi Ibu Hamil Dan Pemeriksaan USG
Gratis. Selaparang Jurnal Pengabdian Masyarakat Berkemajuan, 6(1), 189–
194. http://journal.ummat.ac.id/index.php/jpmb/article/view/7929
Dinas Kesehatan DIY. (2020). Profil Kesehatan D.I Yogyakarta tahun 2020. Profil
Kesehatan Daerah Istimewa Yogyakarta Tahun 2020 , 76.
http://www.dinkes.jogjaprov.go.id/download/download/27. Yogyakarta.
Penerbit: web Dinas Kesehatan
Hasnah, H., Nurhidayah, N., Fadhilla Gani, N., Risnah, R., Arbianingsih, A.,
Huriati, H., Hadrayani, E., Ulfah Azhar, M., & Muthaharah, M. (2021).
Strategi Pendidikan Kesehatan pada Ibu Hamil di Masa Pandemi. Jurnal
Pengabdian Kesehatan Komunitas, 1(2), 108–117.
https://doi.org/10.25311/jpkk.vol1.iss2.959
Hety, D. S., Anggreni, D., & Susanti, I. Y. (2021). Upaya Peningkatan Status
Kesehatan Pada Ibu Hamil Melalui ANC Terpadu Di Masa New Normal Di
Puskesmas Mojosari Kecamatan Mojosari Kabupaten Mojokerto. Jurnal
Pengabdian Masyarakat Al-Rsyad, 3(1), 112–121.
Kemenkes RI. (2018). Pentingnya Pemeriksaan Kehamilan (ANC) di Fasilitas
Kesehatan. Https://Promkes.Kemkes.Go.Id/, 4, 1–2.
https://promkes.kemkes.go.id/pentingnya-pemeriksaan-kehamilan-anc-di-
295
9
fasilitas-kesehatan. Tanggal akses: 13 Februari 2022.

Lestari, D., Sulistiawati, F., & Naelasari, D. N. (2021). Sosialisasi Perilaku Hidup
Bersih dan Sehat serta Gizi Seimbang pada Ibu Hamil untuk Meningkatkan
Imunitas pada Masa Pandemi Covid-19. Abdinesia: Jurnal Pengabdian Kepada
Masyarakat, 1(2), 47–51.
Meri. (2020). Pemeriksaan Golongan Darah Bagi Ibu Hamil di Wilayah Kerja
Puskesmas Kahuripan Kota Tasikmalaya. Jurnal Pengabdian Masyarakat
(JUPEMAS), 1(1), 1–4.
Nurhidayati, S. S. (2020). Pemeriksaan Hamil, Golongan Darah dan Hb pada Ibu Hamil
di Klinik Pratiwi Medical Center (PMC) Kecamatan Peusangan Kabupaten
Bireuen. Rambideun: Jurnal Pengabdian Kepada Masyarakat, 3(2), 42–44.
Riana, E., Susanti, T., Ananda, N. R., & Anisa, R. (2021). Pendampingan Ibu
Hamil Di Era Pandemi Covid-19 Dalam Upaya Peningkatan Cakupan Pelayanan
Ibu Hamil Di Puskesmas Karya Mulia Pontianak. Selaparang Jurnal
Pengabdian Masyarakat Berkemajuan, 4(2), 122.
https://doi.org/10.31764/jpmb.v4i2.4066
Riyanto, Islamiyati, & Herlina. (2020). Pemberdayaan Kader Posyandu melalui
Peningkatan Pengetahuan Deteksi Dini Ibu Hamil Resiko Tinggi dan
Keterampilan Pengukuran Tekanan Darah dan Lingkar Lengan Atas di Keurahan
Tejosari Kecamatan Metro Timur. Bantenese : Jurnal Pengabdian Masyarakat,
2(2), 98–109. https://doi.org/10.30656/ps2pm.v2i2.2810
Septiyaningsih, R., Kusumawati, D. D., Yunadi, F. D., & Indratmoko, S. (2020).
Edukasi dan Deteksi Dini Komplikasi Kehamilan dengan Pemeriksaan
Laboratorium. Poltekita: Jurnal Pengabdian Masyarakat , 1(2), 43–49.
https://doi.org/10.33860/pjpm.v1i2.98
TNP2K. (2017). 100 Kabupaten/Kota Prioritas untuk Intervensi Anak Kerdil (Stunting).
Tim Nasional Percepatan Penanggulangan Kemiskinan , 1, 14–15.
http://www.tnp2k.go.id/images/uploads/downloads/Binder_Volume1.pdf
WHO. (2016). WHO Recommendations on antenatal care for a positive pregnancy
experience. WHO. Geneva. Penerbit: WHO Press.

biosensors
Article
Wearable Fetal ECG Monitoring System from Abdominal
Electrocardiography Recording
Yuwei Zhang 1,2, Aihua Gu 1,3,
*, Zhijun Xiao 2, Yantao Xing 2
, Chenxi Yang 2
, Jianqing Li 2
and Chengyu Liu 2,*
1
The State Key Laboratory of Bioelectronics, School of Biological Sciences and Medical Engineering,
Southeast University, Nanjing 210096, China; zhangyuwei@seu.edu.cn
2
The State Key Laboratory of Bioelectronics, School of Instrument Science and Engineering,
Southeast University, Nanjing 210096, China; zhijunxiao@seu.edu.cn (Z.X.); 230198304@seu.edu.cn (Y.X.);
chenxiyang@seu.edu.cn (C.Y.); ljq@seu.edu.cn (J.L.)
3
State Key Laboratory of Reproductive Medicine, Institute of Toxicology, School of Public Health,
Nanjing Medical University, Nanjing 211166, China
* Correspondence: aihuagu@njmu.edu.cn (A.G.); chengyu@seu.edu.cn (C.L.)
Abstract: Fetal electrocardiography (ECG) monitoring during pregnancy can provide crucial infor-
mation for assessing the fetus’s health status and making timely decisions. This paper proposes a
portable ECG monitoring system to record the abdominal ECG (AECG) of the pregnant woman,
comprising both maternal ECG (MECG) and fetal ECG (FECG), which could be applied to fetal heart
rate (FHR) monitoring at the home setting. The ECG monitoring system is based on data acquisition
circuits, data transmission module, and signal analysis platform, which consists of low input-referred noise,
high input impedance, and high resolution. The combination of the adaptive dual threshold (ADT) and
the independent component analysis (ICA) algorithm is employed to extract the FECG from the AECG
signals. To validate the performance of the proposed system, AECG is recorded and analyzed of
pregnant women in three different postures (supine, seated, and standing). The result shows that the
proposed system can record the AECG in different postures with good signal quality and high accuracy
in fetal ECG and heart rate information. Sensitivity (Se), positive predictive accuracy (PPV), accuracy
Citation: Zhang, Y.; Gu, A.; Xiao, Z.; (ACC), and their harmonic mean (F1) are utilized as the metrics to evaluate the performance of the fetal
Xing, Y.; Yang, C.; Li, J.; Liu, C. QRS (fQRS) complexes extraction. The average Se, PPV, ACC, and F1 score are 99.62%, 97.90%,
Wearable Fetal ECG Monitoring
97.40%, and 98.66% for the fQRS complexes extraction„ respectively. This paper shows the proposed
System from Abdominal
system has a promising application in fetal health monitoring.
Electrocardiography Recording.
Biosensors 2022, 12, 475. https://
Keywords: fetal; electrocardiography (ECG); health status; monitoring system; fetal heart rate (FHR)
doi.org/10.3390/bios12070475
Received: 31 May 2022

Accepted: 28 June 2022
Published: 30 June 2022 1. Introduction
Publisher’s Note: MDPI stays neutral Perinatal complications contribute to approximately 40% of the total perinatal and
with regard to jurisdictional claims in maternal deaths, whereas heart defect is an important factor in perinatal stillbirth world- wide
published maps and institutional affil- [1]. Therefore, monitoring the status of the fetal heart rate (FHR) is of paramount importance
iations. during pregnancy or delivery [2].
Currently, as the gold standard for FHR monitoring, cardiotocography (CTG) provides a
visual representation of FHR and uterine contractions. Nevertheless, CTG only provides an
estimate of the FHR and is prone to signal loss and cannot be used for a long time. Doppler
Copyright: © 2022 by the authors. ultrasound is routinely employed during pregnancy and delivery [3]. However, ultrasound is not
Licensee MDPI, Basel, Switzerland. passive and requires frequent repositioning of the ultrasound transducer. Thus, to monitor the
This article is an open access article fetus’s health during daily life, a comfortable, safe, long-term fetal monitoring system that can be
distributed under the terms and used conveniently is needed.
conditions of the Creative Commons Studies reveal that a fetal electrocardiogram (FECG) estimates the fetal heart move-
Attribution (CC BY) license (https:// ment, which has the potential to provide rhythm information and morphology, such as the PR
creativecommons.org/licenses/by/ 4.0/).
and QT intervals or ST segments [4]. FECG monitoring is a convenient scheme for early
Biosensors 2022, 12, 475. https://doi.org/10.3390/bios12070475 https://www.mdpi.com/journal/biosensors

296
1
Biosensors 2022, 12, 2 of 15
475
detection and diagnosis of fetal congenital heart disease and distress [5]. In practice, the
FECG signals can be collected in two strategies: fetal scalp electrocardiography (SECG) and
maternal abdomen electrocardiography (AECG). SECG is capable of providing accurate
FECG morphology and fetal heart rate (FHR). Nevertheless, SECG is invasive, expensive,
and requires skilled personnel. In contrast, AECG is inexpensive, convenient, and has no
harm to the mother and the fetus during the pregnancy. Additionally, AECG can work earlier
weeks (>20 weeks) while SECG monitors the fetus’s health during labor exclusively. Therefore,
developing a non-invasive FECG (NI-FECG) monitoring system is essential for early heart
disease detection, which can improve the effectiveness of appropriate treat- ment for the
fetus. At the present, non-invasive physiological measurement has gradually become a new
trend [6].
Currently, several devices are available that can acquire FECG signals [7–15], such as
Avalon (with wireless transducer) [7] and AN24 [8]. In addition, Fanelli et al. [10] developed
remote fetal care to monitor fetal health during pregnancy. The monitoring system could help
pregnant women monitor the status of themselves and their fetuses at home. Le et al. [11]
designed a home-based mobile maternal and fetal ECG acquisition, which includes a cloud
assistant. Yuan et al. [12] established a fetal ECG monitoring system based on the android
smartphone. Galli et al. [13] developed a fetal heart rate monitoring using multiple dry electrodes.
There are two main technology challenges in implementing a home-based NI-FECG
monitoring system. The first challenge comes from the feasible hardware acquisition module
of the wearable FECG monitoring system that ensures the maternal AECG signal is
continuously collected in different states. Secondly, accurate and real-time waveform
analysis requires professional knowledge to be properly employed to the AECG signal of the
pregnant woman.
Wearable ECG monitoring is produced by the traditional ECG detection fusion materials,
electronics, information, artificial intelligence, and other emerging technologies, which is
increasingly prevalent in the push toward autonomous health monitoring [16–20]. It can be worn
by pregnant women to obtain the AECG signals and to realize continuous and long-term
dynamic monitoring of pregnant women. The collected maternal AECG signals incorporate lots of
noise interference such as baseline drift, power line, electromyography (EMG), mother’s
breathing interference, and motion artifacts [21]. In particular, the amplitude of the maternal
ECG (MECG) is often several times that of the FECG in the ECG signal detected from the
abdomen, which makes the extraction of the FECG quite difficult [22].
Although significant progress has been made in ECG signal processing in the past few
years, the analysis of the FECG signal is still in the early stages of development. Sev- eral
works of literature were presented on the location of the fetal QRS (fQRS) complexes
utilizing the AECG recordings [23]. The methods proposed in the literature include convo-
lutional neural network (CNN) [24], template subtraction (TS) [25], the least mean square
(LMS) adaptive filter (AF), the recursive least square (RLS) adaptive filter [26], Kalman fil-
tering (KF) [27], independent component analysis (ICA) [28], periodic component analysis
(πCA) [29], principal component analysis (PCA), wavelet transform (WT), the echo state
neural network (ESN), and fusion of different methods (FUSE method) [30], etc.
This paper aims to design a portable, home-based, FECG monitoring system, which can
be used for continuous monitoring of fetal health. The contributions of this work are as
follows.
1. Considering that fetal ECG is very weak and vulnerable to noise, a high-precision, low-
noise portable ECG measure device is designed and optimized to collect pregnant women’s
abdominal ECG signals in different states (supine, seated, and standing posture). The
system consists of biocompatible electrode materials, noise suppression design and
amplification circuit, data transmission, and storage module;
2. A major prerequisite in non-invasive AECG recordings analysis is the accurate ex-
traction of FECG signals in the presence of background noise and maternal artifacts.
We present an effective algorithm for AECG signal analysis, including signal

475
pre-processing, maternal QRS location, maternal ECG subtraction, and fetal QRS
complex detection.
This paper is organized as follows. Section 2 presents the design of the FECG monitoring
system briefly. Section 3 illustrates the algorithm for signal analysis. Section 4 details the
experiment designs and results. Section 5 demonstrates the discussion. Finally, the
conclusion is drawn.
2. Design of FECG Monitoring System

The diagram of the fetal monitoring system frame is presented in Figure 1. The
monitoring system mainly includes a data acquisition module, data transmission module,
signal storage module, and signal analysis platform. Electrodes will be attached to the skin in
a certain way for the collection of pregnant women’s AECG signals. The signal acquisition
module filters and amplifies the AECG signals (including maternal ECG signals and fetal
ECG signals) and converts them from an analog signal to a digital signal. The signal
transmission module transmits the abdominal ECG signals to the PC interface by Bluetooth
or stores them in a memory card. The signal analysis platform displays the AECG waveform
and processes and analyzes the AECG data.
Figure 1. The diagram of the fetal monitoring system frame. (A) Electrode placement. (B) Postures of the
subject. (C) Monitoring system. (D) Hardware prototype.
2.1. Electrode
The electrode is an important medium for connecting pregnant women’s abdomen and
signal conditioning circuits. Its performance directly affects the quality of the collected signals
and the comfort and reliability of the pregnant women during the use of the equipment. To
accurately and effectively collect the fetal ECG signal and ensure that the signal has a high
signal-to-noise ratio (SNR), the electrode demands meet specific performance indicators. The
AgCl electrode has good conductivity, low noise, and a stable baseline, which can ensure
high-quality signal acquisition.
It is investigated that three linearly independent ECG electrodes can be used to
construct a surface ECG vector map [31]. The electrode placement is designed with three
acquisition channels, a reference point, and a left leg drive. Determine the reference
electrode point 5 cm below the center of the pregnant woman’s navel. Three acquisition
electrodes draw a triangle around the navel. The left leg drive electrode is on the right side of
the participant. This configuration is chosen for the reason that it maximizes the SNR [32].
3
475
2.2. Signal Acquisition Module

When recording fetal ECG detection, instantaneous high voltage may be generated due to the
influence of the external environment, causing damage to the entire hardware circuit. In addition,
a lot of electromagnetic interference exists in the working environment of ECG acquisition
equipment. A buffer is designed to increase input impedance and improve load capacity and
noise immunity. Simultaneously, a preprocessing circuit is added to the hardware acquisition
system composed of a second-order passive low-pass filter and a limiting circuit, which plays
a crucial role in eliminating high-frequency interference and overvoltage protection.
The fetal ECG signal is relatively weak, and the amplitude of the fetal ECG is varied from
10 µV to 60 µV. It is susceptible to maternal interference, myoelectric interference, and power
frequency interference [33]. Therefore, the hardware acquisition system is required to have low
noise, high input impedance, and a high common-mode rejection ratio
(CMRR). The data acquisition module of this system is implemented with an analog front
end ADS1299 (Texas Instruments, Dallas, TX, USA), which includes a programmable gain
amplifier (PGA), high-precision analog to digital converter (ADC), and right leg drive (RLD).
Input referred noise, input impedance, and CMRR of the ADS1299 are 1 µVpp, 1000 MΩ,
and −110 dB, respectively, which meets the requirements of the acquisition system.
The AECG acquisition process is often subject to common-mode interference intro- duced
by the power line or other interference sources. The RLD circuit detects the common- mode
component in the input signal and feeds it back to the human body, thereby canceling the
common-mode voltage, reducing the displacement current, and effectively suppressing the
common-mode interference. The STM32F103 chip is used as the microcontroller unit (MCU) of
the monitoring system. The chip has high performance (72 MHz operating frequency, single-
cycle multiplication instructions, and hardware partition instruction), low power consumption
(0.19 mW/MHz), and rich peripherals. The technical information of the proposed hardware
system is shown in Table 1. The sampling rate of the acquisition system is Fs = 500 Hz, and the
data are recorded with a resolution of 24 bits.
Table 1. The technical information of the proposed hardware system.
Parameter Value
Sampling rate 500 Hz
Input voltage −185–185 mV
ADC resolution 24 bits
Gain 24
Power supply 3.7 V 1000 mAh
Input referred noise 2.4 µVpp
Input impedance 1000 MΩ
Size 55 mm × 55 mm
3. Algorithm for Signal Analysis

The framework of the proposed approach undertaken in this work includes three steps:
(1) Signal pre-processing. The AECG signals are processed for removing these invalid
values by spline interpolation method; signal quality assessment (SQA) for AECG to get a
better-quality signal based on SampEn; signal noise canceling (SNC) for AECG by
eliminating power line interference, baseline drift, and impulsive artifacts based on Notch
filter, Butterworth filter, and median filter, respectively. (2) A source separation algorithm is
applied to MECG subtraction for the FECG signal extraction. (3) Fetal QRS complexes
detection algorithm is performed on the filtered residual signals containing FECG signal. The
structure block diagram of fQRS location using the algorithm proposed in this paper is presented
in Figure 2.

475
Figure 2. The structure block diagram of the fetal ECG extraction and fQRS location using the
algorithm proposed in this work. (a) Signal Pre-processing. (b) Canceling Maternal QRS Complex.
(c) Detecting Fetal HR.
Furthermore, the other dataset employed in this work is from PhysioNet/Computing in

Cardiology Challenge 2013 Database (PCDB) [34]. The PCDB consists of 447 recordings
from five different databases. Seventy-five AECG recordings are included in training set A.
Each recording contains four channels of AECG signals, and they are 60 s long and sampled at 1
kHz with 16-bit resolution. Reference annotations are generated by experts referring to direct
FECG signals, obtained from fetal scalp electrodes.
3.1. Signal Preprocessing

3.1.1. Signal Quality Assessment
AECG signal may contain invalid values because of human body movement. There-
fore, the signal needs to be preprocessed to remove these invalid values. The cubic spline
interpolation is applied to eliminate invalid values in this work. It is a challenging task for
fQRS complexes detection from the original AECG signals due to a variety of noise. Signal
quality assessment (SQA) plays a crucial role in physiological signal processing and
inaccurate characteristic estimation [35]. The sample entropy (SampEn) has been a vital tool
in SQA for ECG signal processing for the selection of the waveform, with reference to the
article from Liu [36]. The calculation process of SampEn is summarized below:
For RR segment x(i) (1 ≤ i ≤ N), given the parameters m and r, firstly form the vector
sequences Xm:
i
Xmi = {x(i), x(i + 1), . . . , x(i + m − 1)}, 1 ≤ i ≤ N − m (1)
where the vector Xim represents m consecutive x(i) values. The definition of the distance
between Xm and X mbased on the maximum absolute difference is below:
i j
h i
dm = d Xm, Xm = max |x(i + k) − x(j + k)| (2)
i,j i j
0<k<m−1
For each X , express B (r) as (N − m)−1 times the number of Xm (1 ≤ j ≤ N − m)

m m
i i j
that meets dm ≤ r. Similarly, denote Am (r) as (N − m)−1 times the number of Xm+1 that
i,j i j
meets dmi,j ≤ r for all 1 ≤ i ≤ N − m.
The definition of SampEn is as follows:
N−m N−m
SampEn(m, r, N) = − ln( ∑ m
A i (r)/ ∑ Bm (r)) (3)
i=1 i=1 i
where m is the embedding dimension, r represents the tolerance threshold, and N is the time-
series length.
5
475
At first, the AECG signal in each channel is divided into six non-overlapping segments (10 s
for each segment), and the average of their corresponding SampEn values is returned as the
SampEn result of the current channel. Then, the signal quality is evaluated by comparing the
SampEn value in each channel with a constant threshold, which is set to
1.5 for AECG recordings. The average SampEn value is greater than 1.5 for the channels that
are regarded as poor quality and are excluded. The signal of the channel whose mean
sampEn is less than 1.5 is regarded as good quality signal and is reserved. If less than two
channels are of good quality, the two channels with the penultimate and the smallest SampEn
values are reserved.
3.1.2. Signal Noise Canceling

The original AECG signals usually contain power line interference, baseline drift, and
impulsive artifacts. Power line interference includes a sinusoidal component at a frequency of
around 50 Hz, which significantly affects signal quality. Baseline drift is mainly caused by
human movement and breathing, and it is manifested in lots of AECG signals. These noises
have a harmful influence on the analysis and processing of the signal. The notch filter is
utilized to remove the power line interference in this work [37]. The combination of
Butterworth filter and median filter is applied to eliminate baseline drift and impulsive
artifacts. The power line interference, baseline drift, and impulsive artifacts of the AECG are
mostly eliminated after the signal noise-canceling step.
3.2. Maternal QRS Detection and Mother Cycles Subtraction

3.2.1. Maternal QRS Detection
The primary step for the R complex location is preprocessing, which consists of wavelet
transform analysis, absolute value transformation, and low-pass filtering step. The
preprocessing here is to convert the original ECG signal into a signal composed of a single
pattern of peaks. Compared with the original signal, the preprocessed signal is more
convenient for detection. After performing the preprocessing steps on the signal, the adaptive
dual threshold (ADT) algorithm is employed to locate the R-wave peak of the signal [38,39].
The ADT approach sets a high threshold (thr_H) and a low threshold (thr_L) to extract the R
wave. If thr_L is smaller than lim_L, then thr_L = lim_L thr_L = lim_L. If P is greater than
thr_L, and P is smaller than thr_H, then thr_L = 0.45 × P and thr_H can be described as:
thr_H = thr_L + |P − mean(P_prior)|/2 (4)
If P is greater than thr_L, then thr_L and thr_H can be expressed as:
thr_L = 0.3 × mean(P_prior) (5)

thr_H = 0.7 × mean(P_prior) (6)
where P is the amplitude of the current peak value, P_prior represents the sum of the
amplitude of the stored 10 peaks before the current peak value, and lim_L and lim_H are the
two empirical constants obtained after multiple trials, representing the lower limits of the two
threshold changes, respectively.
3.2.2. Mother Cycles Subtraction

It is well known that maternal ECG (MECG) is a major component of the AECG signal
and masks fetal ECG signals. Thus, it is necessary to effectively cancel the MECG signal.
Blind source separation (BSS) is described as solving the problem of separating or estimating
the source waveform from the sensor array without knowing the characteristics of the
transmission channel. The BSS method assumes that the source signals are statistically
independent, so the independent components of the original signal can be obtained from the
multi-channel AECG signal. The independent component analysis (ICA) approach is one
of the commonly used methods in BSS, and it is also one of the most promising methods in
current blind source separation. The ICA method is capable of eliminating
475
the high-order statistical correlation in the observed signal by achieving the maximum value
of the objective function of a certain contrast function and realizing blind source separation
[40].
The correct application of ICA requires meeting the following conditions: (1) The signal
source is statistically independent; (2) The number of measurement signals is greater than the
number of signal sources. The mother’s myocardium is far away from the abdominal leads, and
the MECG is the strongest and the most common independent component. Therefore, it can meet
the conditions for the ICA application. The ICA approach is exploited to separate the MECG
from the other components.
The source signals S are expressed as follows:
S(k) = S1(k), S2(k), . . . , Si(k) (7)
where S(k) is the independent source signal such as MECG, FECG, and noise, k is the time
instant, and i denotes the number of sources.
The observation signal X (the AECG recording) obtained from the sensor nodes is:
x(k) = x1(k), x2(k), . . . , xj(k) (8)
where j represents the number of AECG recordings utilized.

The observation signal x is preprocessed including de-averaging and whitening before using
the ICA algorithm. The process of removing the mean value is to subtract the mean value vector
m = E{x} of the signal from the observed signal so that the observed signal becomes a zero-mean
variable.
The extraction of the FECG signal is following the equation:
x(k) = AS(k) (9)
where A is the mixing matrix, which represents the mixing matrix of x after transformations and
observations.
Generally, the signal source S is acquired by constructing the inverse matrix W of the
mixing matrix A. By constructing the W matrix (W = S−1), the estimated independent
components Y of the source signal can be obtained.
Y = WS = WAS (10)
The residual signal (FECG signal) is obtained by subtracting the maternal cycle tem-
plate signal from the AECG signal by a combination of the ADT and the ICA algorithm
(ADT-ICA-based method).
3.3. Fetal QRS Complex Detection

The residual signal may still contain residual noise components, which may potentially
affect the estimation and correct identification of fetal QRS complexes. In this work, the
wavelet adaptive threshold de-noising method is applied to remove the noise components of the
FECG signal. Noise can be effectively removed and a clearer FECG waveform can be gained
through this step. Meanwhile, the JADE algorithm is adopted to process the residual signal.
Due to the implementation of the JADE algorithm, the FECG signals exhibit enhanced and
more pronounced peaks, thus aiding the fetal QRS detection process.
Despite previous steps eliminating noise and artifacts, the power of the fetal complex is still
small and mixed with residual noise, resulting in a poor SNR. It weakens the reliability of the
criteria for a priori selection of the best channel for fetal ECG detection. The fetal QRS
complex location step is performed on the extracted fetal ECG components. Fetal QRS
complexes are detected with an adaptive threshold of derivative amplitude, and it is
automatically initialized and recursively updated at every new detection [41]. The algorithm
searches for the maximum value of the weighted derivative signal. The weights are defined
by the trapezoidal window to enhance the samples close to the predicted QRS
7
475
complex’s location. The fQRS complex detection procedure is applied to all channels. At
last, the best estimate of fQRS is selected based on the prior knowledge of typical fetal RR
values.
4. Experiments and Results

4.1. Experiment Design
The three subjects in this work are from the First Affiliated Hospital of Nanjing Medical
University. The detailed demographic information of this experiment is presented in Table 2.
Additionally, informed consent is obtained from each pregnant woman in this experiment. The
subject experimental protocol is approved by the Ethics Committee and the study number is 2020-
SRFA-183.
Table 2. The detailed demographic information of the subjects in this experiment.
Statistical Information Age (Years) Height (cm) Weight (kg)

Average 29 159 65
Standard Deviation 1.8 1.2 5.4
The experiment is designed in a laboratory similar to a home environment to verify the

proposed monitoring system can measure fetal signals in different states, including supine, seated,
and standing postures. The experiment protocol of this work consists of three steps. At first,
pregnant women are asked to maintain in a supine situation for four minutes. The subjects are then
asked to sit and monitor AECG signals for another two minutes. Finally, the subjects change to a
standing posture and are monitored for an additional two minutes. The pregnant women are
around 37 weeks.
4.2. Evaluation Performance

In the context of NI-FECG extraction, a matching window of 50 ms is applied with each
fetal QRS location annotated by experts as a center to evaluate the error of fQRS complexes
detection (i.e., fQRS within a ±50 ms window) [42]. If the detected fQRS location is in the
matching window, it illustrates that the detected fQRS is the correct value. The performance of
this study is evaluated in terms of sensitivity (Se), positive predictive accuracy (PPV), accuracy
(ACC), and their harmonic mean (F1), following the guideline of the ANSI/AAMI, as defined
below:
TP
Se = TP + FN
(11)
TP
PPV =
TP + FP (12)
TP
ACC =
TP + FP + FN (13)
PPV ∗ Se 2TP
F1 = 2 ∗ PPV + Se (14)
=
2TP + FN + FP
where TP is the number of True Positive that match the fetal QRS marked by experts (correctly
detected fetal QRS complexes), FP stands for False Positive (wrongly detected fetal QRS
complexes), and FN represents False Negative (missed detected fetal QRS complexes).
Bland–Altman graph is a simple and intuitive way of illustrating the consistency of
data. The basic idea of the Bland–Altman method is to calculate the mean difference between the
two sets of measurement results and take the 95% agreement limit as the mean difference (1.96
SD). Therefore, the Bland–Altman plot could be employed to further evaluate the accuracy value
of the detected fetal heart rate. The 95% limit is expected to be chosen to test the difference
between the estimated fetal heart rate values of the proposed method and the reference
annotations.
475
4.3. Results
Our method has been implemented in Matlab 2019b (MathWorks Inc., Natick, MA,
USA). The dataset collected in this experiment (DS-database) consists of eight AECG
recordings (r01–r12) from three different subjects. Each recording contains 2-min long three
AECG signal channels for a total of 3309 fQRS waves. The reference annotations are
generated by the experts. The collected AECG signal of subject A, who simulated supine
posture, is shown in Figure 3. It can be seen that the quality of the AECG signal is good, and
a clear fQRS can be observed.
Figure 3. The collected AECG signal of subject A, who simulated supine posture (DS-database).
(a) AECG signal with 120 s length interval. (b) AECG signal with 5 s length interval. (b) is a zoom of
(a).
Figure 4 shows the original AECG recording and the filtered AECG after SNC. It can
be seen that the AECG waveform becomes cleaner after this step. Part of the result of the
extraction process of the MECG signal, mQRS location, fetal ECG signal, and fQRS location
is shown in Figure 5. It can be seen that the MECG signal and FECG signal are well
separated. An example result of mQRS and fQRS estimation using the proposed algorithm
on the raw AECG signal is illustrated in Figure 5a. The figure manifests that the mQRS and
fQRS wave positions are correctly located, respectively. A visual display of extracted MECG
along with the result of mQRS location is exhibited in Figure 5b. In this Figure, we can see
the complete MECG signal and correct mQRS position. In addition, the residual signal (i.e.,
fetal ECG signal) with the location of the estimated fetal R peaks and the truth value
annotations of fetal R peaks by the experts is presented in Figure 5c. We are capable of
obtaining that the estimated fetal R peak matches the reference annotation.
9
475
Figure 4. The original AECG recording and the filtered AECG after SNC (DS—database).
Figure 5. Part of the result of the extraction process of MECG signal, mQRS location, fetal ECG
signal, and fQRS location (DS-database). (a) An example result of mQRS and fQRS estimation on the
raw AECG signal. The ‘+’ represents the mQRS location position, and the ‘*’ represents the fQRS
location position. (b) A MECG template signal is extracted and mQRS location on the extracted
MECG signal. The ‘+’ represents the mQRS location position. (c) A FECG template signal is extracted
and fQRS location on the extracted MECG signal. The ‘*’ indicates the fQRS location position using
the algorithm, and the ‘o’ denotes the truth value annotated by the expert.
The Bland–Altman statistical analysis method for the estimated fetal heart rate values of the
proposed method and the reference annotations (recording r02 and r09) is displayed in Figure 6.
ISSN: 2797-9210 (Print) The
| 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI
results show that most of the values lie within the 95% interval for the recording of r02 and
r09. Performance metrics of the fQRS detection using this method on
475
the DS-database are summarized in Table 3. We can obtain the correct number of fQRS wave
detections, and the number of errors detected for each AECG recording. The average diagnostic
Se, PPV, ACC, and F1 score are 99.62%, 97.90%, 97.40%, and 98.66%, respectively.
(a) (b)
Figure 6. Bland-Altman plot for recording r02 and r09 using the proposed method (DS-database).
(a) Bland–Altman plot for recording r02. (b) Bland-Altman plot for recording r09.
Table 3. Performance metrics of the fQRS detection using this method.
Subject Recording Position TP FP FN Se (%) PPV (%) ACC (%) F1 (%)

r01 Supine 282 3 1 99.65 98.95 98.60 99.30
r02 Supine 281 0 0 100 100 100 100
A r03 Seated 280 1 0 100 99.64 99.64 99.82
r04 Standing 260 15 7 97.38 94.55 92.20 95.94
r05 Supine 267 4 1 99.63 98.53 98.16 99.07
r06 Supine 284 8 2 99.30 97.26 96.60 98.27
B r07 Seated 274 0 0 100 100 100 100
r08 Standing 275 17 2 99.28 94.18 93.54 96.66
r09 Supine 275 2 2 99.28 99.28 98.57 99.28
r10 Supine 271 3 2 99.27 98.91 98.19 99.09
C r11 Seated 273 4 1 99.64 98.56 98.20 99.09
r12 Standing 269 14 0 100 95.05 95.05 97.46
Intuitive results of Se, PPV, ACC, and F1 score of all the subjects in supine, seated, and
standing postures are shown in Figure 7. It demonstrates that the average Se, PPV, ACC, and
F1 score in spine posture are 99.52%, 98.82%, 98.35%, and 99.17% with a standard deviation of
0.28%, 0.82%, 0.96%, and 0.49%, respectively. When the subjects changed their posture
from supine to seated, the mean Se, PPV, ACC, and F1 score are 99.88%, 99.4%, 99.28%, and
99.64% with a standard deviation of 0.21%, 0.75%, 0.95%, and 0.48%, respectively. In the
standing position, the mean Se, PPV, ACC, and F1 score are 98.89%, 94.59%, 93.60%, and
96.69% with a standard deviation of 1.35%, 0.44%, 1.43%, and 0.76%, respectively. Compared
to the results in the standing position, the results in supine and seated postures perform better.
The results in the seated positions performed slightly better than the results in the supine
position.
11
475
Figure 7. Intuitive results of Se, PPV, ACC, and F1 score of all the subjects in supine, seated, and
standing postures (DS-database).
5. Discussion
In this work, we develop a portable, home-based FECG monitoring system that can be
used to monitor pregnant women and fetuses’ health. The combination of ADT and the
ICA algorithm is implemented to realize the FECG waveform and fetal heart rate
extraction. The Monica AN24 and Avalon fetal monitoring systems are capable of acquiring
FECG signals. However, those two devices are not the most convenient solutions for home-
based monitoring owing to the demand for professional skills and knowledge to utilize the
acquisition device [9]. Compared to the home-based monitoring solutions that were previously
mentioned, our FECG monitoring system has done signal acquisition verification and fetal
heart rate analysis in different postures (supine, seated, and standing). It is worth mentioning
that we can see the FECG signal clearly from the displayed AECG signal in Figure 3. The
result in Figure 5 proves that the extracted FECG signals from the collected AECG signals are
relatively clear and usable, and thus can serve as a valuable source of information for fetal health
state monitoring. It needs to be emphasized that the quality of the AECG signal is of paramount
importance for reliable morphological analysis of pregnant women and fetuses. Therefore, it
also puts forward higher requirements for the acquisition module of the monitoring system.
Furthermore, to satisfy the reliability of the subsequent signal analysis, SampEn is applied to
assess the quality of the AECG signal. Subsequently, we extracted the FECG signal from
the preprocessed AECG data in the database and collaborated with experts to annotate the
fQRS, ensuring the accuracy of
the data annotation.
Table 3 demonstrates the diagnostic PPV, ACC, and F1 score of r04 (standing) are
94.55%, 92.20%, and 95.94%, respectively. The diagnostic PPV, ACC, and F1 score of r08
(standing) are 94.18%, 93.54%, and 96.66%, respectively. In addition, the diagnostic PPV,
ACC, and F1 score of r12 (standing) are 95.05%, 95.05%, and 97.46%, respectively. The
signal fetal R wave detection results in the standing posture are worse than those in the
supine and seated states, which might be related to the relatively poor signal quality in the
standing posture. In the standing state, the fetus has more space and more time for
movement, resulting in poor signal quality.
Table 4 summarizes the performance of PPV, ACC, and F1 score on the PCDB and DS-
database between our work and other popular approaches. As shown in Table 4, the result of
this work outperformed the approaches of CNN, TS, AF, and FUSE method. According to
statistical analysis, the proposed approach truly detects 3291 (TP) fetal QRS complexes and
wrongly detects 18 (FP) fetal QRS complexes for all AECG recordings from the DS-
database. Diagnostic Se, PPV, ACC, and F1 score are 99.46%, 97.89%, 95.86%, and 98.67%
from the DS-database, respectively. Furthermore, the proposed approach truly detects 9210
(TP) fetal QRS complexes and wrongly detects 372 (FP) fetal QRS complexes for all AECG
recordings from the PCDB database. Diagnostic PPV, ACC, and F1 score are
475
96.12%, 96.20%, 92.67%, and 96.16% from the PCDB database, respectively. The average PPV,
ACC, and F1 score from this work is slightly higher than the fetal QRS detection result of the TS
algorithm and FUSE method. Meanwhile, the experimental result of this work is significantly
higher than the fetal QRS location result of the CNN and AF approach. It also proves that the
proposed approach will greatly improve the accuracy of detection of the fetal QRS complexes.
Table 4. Comparison of performance metrics for fetal QRS detection of different subjects in different methods.
Database Approach Se (%) PPV (%) ACC (%) F1 (%)

TS [25]
CNN [24] -
76.00 -
82.00 -- 93.90
78.00
PCDB FUSE method [30] 95.90 96.00 - 0.9600
This work 96.12 96.20 92.67 96.16
TS [25] 98.37 96.59 93.40 97.47
DS-database AF [26] 90.18 92.87 86.69 91.51
This work 99.46 97.89 95.86 98.67
The adaptive filter method is theoretically more suitable, but the result closely depends on
the presence of a signal in chest leads and the setting of the adaptive filter. Additionally, optimal
filter settings may vary with the position of the fetus in the uterus and the mother’s gestational
week, etc. The non-adaptive approach provides the superiority of using only abdominal electrodes
without thoracic electrodes. In our future study, we focus on utilizing a combination of adaptive
and non-adaptive methods for fetal ECG signal analysis and R wave extraction. It is worth
knowing that the hybrid method should be able to accurately extract fetal signals and perform
better in the analysis of the fetal signal.
The present work has only tested short-term recordings in three postures (supine, seated,
and standing), and consistent signal quality over longer monitoring periods has not been
experimentally demonstrated. Moreover, the number of subjects is small, and a power
analysis conducted is not performed.
6. Conclusions
In this study, we develop a portable, home-based FECG monitoring application system that
can be applied to health monitoring in different postures (supine, seated, and standing) of pregnant
women. The result reveals that the quality of the AECG signal in supine and seated postures
performs better than that of standing posture. The combination of ADT and the ICA algorithm
is incorporated for FECG signal extraction with JADE algorithm for enhanced quality of the
FECG, which can provide an accurate and reliable FHR estimation. The fetal health monitoring
system contributes in terms of medical resources and physician time. The system is suitable for
pregnant women and has certain application prospects.
In the future, the data collection of more participants will be carried out to verify
the practicability of the wearable fetal monitoring system in a 24-h or long-term monitoring
system.
Author Contributions: Conceptualization, A.G., C.L. and Y.Z.; methodology, Y.Z. and C.Y.; software,
Y.X.; validation, Z.X., Y.X. and Y.Z.; formal analysis, C.Y.; investigation, Y.Z.; resources, Z.X.;
data curation, Y.X.; writing—original draft preparation, Y.Z.; writing—review and editing, C.L., A.G., C.Y.
and Y.Z.; visualization, Y.Z.; funding acquisition, C.L. and J.L. All authors have read and agreed
to the published version of the manuscript.
Funding: This work was supported by the National Key Research and Development Program of
China (2019YFE0113800), the National Natural Science Foundation of China (62171123, 62001111,
62071241, 62101120, and 81871444), and the Natural Science Foundation of Jiangsu Province of China
(BK20190014, BK20192004, BK20200364, and BK20210208).
13
475
Institutional Review Board Statement: The study was conducted in accordance with the Declaration of
Helsinki and approved by the Ethics Committee of the First Affiliated Hospital of Nanjing Medical
University, understudy number 2020-SRFA-183.
Informed Consent Statement: Informed consent was obtained from all subjects involved in the study.
Data Availability Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest.
References
1. World Health Organization. Maternal and Perinatal Health. 2016. Available online: https://www.who.int/maternal_child_
adolescent/topics/maternal/maternal_perinatal/en/ (accessed on 20 February 2017).
2. Kovács, F.; Torok, M.; Habermajer, I. A rule-based phonocardiographic method for long-term fetal heart rate monitoring. IEEE
Trans. Biomed. Eng. 2000, 47, 124–130. [CrossRef] [PubMed]
3. Barnett, S.B.; Maulik, D. Guidelines and recommendations for safe use of Doppler ultrasound in perinatal applications. J. Matern.-
Fetal Neonatal. Med. 2001, 110, 75–84. [CrossRef]
4. Lai, K.C.; Shynk, J.J. A successive cancellation algorithm for fetal heart-rate estimation using an intrauterine ECG signal. IEEE
Trans. Biomed. Eng. 2002, 49, 943–954. [PubMed]
5. Di Maria, C.; Liu, C.; Zheng, D.; Murray, A.; Langley, P. Extracting fetal heart beats from maternal abdominal recordings: Selection of
the optimal principal components. Physiol. Meas. 2014, 35, 1637–1664. [CrossRef]
6. Xiao, Z.; Xing, Y.; Yang, C.; Li, J.; Liu, C. Non-Contact electrocardiograms acquisition method based on capacitive coupling. IEEE
Instru. Meas. Mag. 2022, 25, 53–61. [CrossRef]
7. Avalon Fetal Monitor. Available online: https://www.usa.philips.com/healthcare/resources/landing/avalon (accessed on 30 July
2019).
8. Monica. Introducing the Monica AN24. Available online: http://www.monicahealthcare.com/products/ (accessed on 30 July
2019).
9. Yang, C.; Antoine, C.; Young, B.K. A pilot study on fetal heart rate extraction from wearable abdominal inertial sensors. IEEE
Sens. J. 2019, 19, 10773–10781. [CrossRef]
10. Fanelli, A. Tele Fetal Care: Development of Wearable System for Fetal Monitoring during Pregnancy. Ph.D. Thesis, Politecnico di
Milano, Milano, Italy, April 2013.
11. Le, T.; Fortunato, J.; Maritato, N. Home-based mobile fetal/maternal electrocardiogram acquisition and extraction with cloud
assistance. In Proceedings of the 2019 IEEE MTTS International Microwave Biomedical Conference (IMBioC), Nanjing, China, 6–
8 May 2019; pp. 1–4.
12. Yuan, L.; Yuan, Y.; Zhou, Z.; Bai, Y.; Wu, S. A fetal ECG monitoring system based on the android smartphone. Sensors 2019, 19,
446. [CrossRef]
13. Galli, A.; Peri, E.; Zhang, Y.; Vullings, R.; van der Ven, M.; Giorgi, G.; Ouzounov, S.; Harpe, P.J.A.; Mischi, M. Dedicated
Algorithm for Unobtrusive Fetal Heart Rate Monitoring Using Multiple Dry Electrodes. Sensors 2021, 21, 4298. [CrossRef]
14. Sharma, M.; Ritchie, P.; Ghirmai, T.; Cao, H.; Lau, M.P.H. Unobtrusive acquisition and extraction of fetal and maternal ECG in the
home setting. In Proceedings of the 2017 IEEE Sensors, Glasgow, UK, 29 October–1 November 2017; pp. 1–3.
15. Steinberg, C.; Philippon, F.; Sanchez, M.; Fortier-Poisson, P.; O’Hara, G.; Molin, F.; Sarrazin, J.F.; Nault, I.; Blier, L.; Roy, K.; et
al. A Novel Wearable Device for Continuous Ambulatory ECG Recording: Proof of Concept and Assessment of Signal
Quality. Biosensors 2019, 9, 17. [CrossRef]
16. Arquilla, K.; Devendorf, L.; Webb, A.K.; Anderson, A.P. Detection of the Complete ECG Waveform with Woven Textile Electrodes.
Biosensors 2021, 11, 331. [CrossRef]
17. Xing, Y.; Zhang, Y.; Xiao, Z.; Yang, C.; Li, J.; Cui, C.; Wang, J.; Chen, H.; Li, J.; Liu, C. An Artifact-Resistant Feature SKNAER
for Quantifying the Burst of Skin Sympathetic Nerve Activity Signal. Biosensors 2022, 12, 355. [CrossRef] [PubMed]
18. Majumder, S.; Mondal, T.; Deen, M.J. Wearable Sensors for Remote Health Monitoring. Sensors 2017, 17, 130. [CrossRef] [PubMed]
19. Xing, Y.; Zhang, Y.; Yang, C.; Li, J.; Li, Y.; Cui, C.; Li, J.; Cheng, H.; Fang, Y.; Cai, C.; et al. Design and Evaluation of an
Autonomic Nerve Monitoring System Based on Skin Sympathetic Nerve Activity. Biomed. Signal Process. Control. 2022, 76, 103681.
[CrossRef]
20. Liu, C.; Yang, M.; Di, J.; Xing, Y.; Li, Y.; Li, J. Wearable ECG: History, Key Technologies and Future Challenges. Chin. J.
Biomed. Eng. 2019, 38, 641–652.
21. Silva, I.; Behar, J.; Zhu, T.T.; Oster, J.; Clifford, G.D.; Moody, G.B. Noninvasive fetal ECG: The PhysioNet/Computing in
Cardiology challenge 2013. In Proceedings of the Computing in Cardiology (CinC), Zaragoza, Spain, 22–25 September 2013; pp.
149–152.
22. Behar, J.; Andreotti, F.; Zaunseder, S.; Li, Q.; Oster, J.; Clifford, G.D. An ECG model for simulating maternal-foetal activity
mixtures on abdominal ECG recordings. Physiol. Meas. 2014, 35, 1537–1549. [CrossRef]
23. Clifford, G.D.; Silva, I.; Behar, J.; Moody, G.B. Editorial: Non-invasive fetal ECG analysis. Physiol. Meas. 2014, 35, 1521–1536.
[CrossRef]
24. ISSN:W.;
Zhong, 2797-9210 (Print)
Liao, L.; Guo, X. A deep learning approachhttp://bajangjournal.com/index.php/J-ABDI
| 2798-2912(Online) for fetal QRS complex detection. Physiol. Meas. 2018, 39, 045004. [CrossRef]
(IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 13, No. 1, 2022
25. Martens, S.; Rabotti, C.; Mischi, M.; Sluijter, R. A robust fetal ECG detection method for abdominal recordings. Physiol. Meas.
2007, 28, 373–388. [CrossRef]
26. Widrow, B.; Glover, J.; McCool, J.; Kaunitz, J.; Williams, C.; Hearn, R.; Zeidler, J.; Dong, E.; Goodlin, R. Adaptive noise canceling: Principles and
applications. Proc. IEEE 1976, 63, 1692–1716. [CrossRef]
27. Akhbari, M.; Niknazar, M.; Jutten, C.; Shamsollahi, M.B.; Rivet, B. Fetal electrocardiogram R-peak detection using robust tensor decomposition and
extended Kalman filtering. In Proceedings of the Computing in Cardiology (CinC), Zaragoza, Spain, 22–25 September 2013; pp. 189–192.
28. Varanini, M.; Tartarisco, G.; Billeci, L.; Macerata, A.; Pioggia, G.; Balocchi, R. A multi-step approach for non-invasive fetal ECG analysis. In
Proceedings of the Computing in Cardiology (CinC), Zaragoza, Spain, 22–25 September 2013; pp. 281–284.
29. Sameni, R.; Jutten, C.; Shamsollahi, M.B. Multichannel electrocardiogram decomposition using periodic component analysis.
IEEE Trans. Biomed. Eng. 2008, 55, 1935–1940. [CrossRef]
30. Behar, J.; Oster, J.; Clifford, G.D. Combining and benchmarking methods of foetal ecg extraction without maternal or scalp electrode data. Physiol.
Meas. 2014, 35, 1569–1589. [CrossRef] [PubMed]
31. Mcsharry, P.E.; Clifford, G.D.; Tarassenko, L. Dynamical model for generating synthetic electrocardiogram signals. IEEE Trans. Biomed. Eng. 2003,
50, 289–294. [CrossRef] [PubMed]
32. Rooijakkers, M.J.; Song, S.; Rabotti, C.; Oei, S.G.; Bergmans, J.W.; Cantatore, E.; Mischi, M. Influence of electrode placement on signal quality for
ambulatory pregnancy monitoring. Comput. Math. Methods Med. 2014, 2014, 960980. [CrossRef] [PubMed]
33. Crowe, J.A.; Harrison, A.; Hayes-Gill, B.R. The feasibility of long-term fetal heart rate monitoring in the home environment using maternal abdominal
electrodes. Physiol. Meas. 1995, 16, 195–202. [CrossRef]
34. Goldberger, A.L.; Amaral, L.A.; Glass, L.; Hausdorff, J.M.; Ivanov, P.C.; Mark, R.G.; Mietus, J.E.; Moody, G.B.; Peng, C.K.; Stanley, H.E.
PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 2000, 101, 215–220.
[CrossRef]
35. Liu, C.; Zhang, X.; Zhao, L.; Liu, F.; Chen, X.; Yao, Y.; Li, J. Signal quality assessment and lightweight QRS detection for wearable ECG SmartVest
system. IEEE Internet Things J. 2018, 6, 1363–1374. [CrossRef]
36. Liu, C.; Li, P.; Zhao, L.; Maria, C.D.; Zhang, H.; Chen, Z. A multi-step method with signal quality assessment and fine-tuning procedure to locate
maternal and fetal qrs complexes from abdominal ecg recordings. Physiol. Meas. 2014, 35, 1665–1683. [CrossRef]
37. Hamilton, P.S. A comparison of adaptive and nonadaptive filters for reduction of power line interference in the ECG. IEEE Trans. Biomed. Eng. 1996, 43,
105–109. [CrossRef]
38. Han, D.; Bashar, S.K.; Lázaro, J.; Mohagheghian, F.; Peitzsch, A.; Nishita, N.; Ding, E.; Dickson, E.L.; DiMezza, D.; Scott, J.; et al. A Real-Time
PPG Peak Detection Method for Accurate Determination of Heart Rate during Sinus Rhythm and Cardiac Arrhythmia. Biosensors 2022, 12, 82.
[CrossRef]
39. Qin, Q.; Li, J.; Yue, Y.; Liu, C. An adaptive and time-efficient ECG R-peak detection algorithm. J. Healthc. Eng. 2017, 2017, 5980541. [CrossRef]
40. Radek, M.; Radana, K.; Janusz, J. Comparative Effectiveness of ICA and PCA in Extraction of Fetal ECG from Abdominal Signals: Toward Non-
invasive Fetal Monitoring. Front. Physiol. 2018, 9, 648.
41. Pan, J.; Tompkins, W.J. A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 1985, 32, 230–236. [CrossRef] [PubMed]
42. Behar, J.; Andreotti, F.; Zaunseder, S.; Oster, J.; Clifford, G.D. A practical guide to non-invasive foetal electrocardiogram extraction and analysis. Physiol.
Meas. 2016, 37, R1–R35. [CrossRef] [PubMed]
Vol. 13, No. 1, 2022
Ambulatory Monitoring of Maternal and Fetal using

Deep Convolution Generative Adversarial Network
for Smart Health Care IoT System
S. Venkatasubramanian
Department of Computer Science
Saranathan College of Engineering, Trichy-620012, India
Abstract—With the increase in the number of high-risk

pregnancies, it is important to monitor the health of the fetus
Although the fetus is located inside the body of a pregnant
during pregnancy. Major advances in the field of study have led woman, the most devoted protector of the fetus is only the
to the development of intelligent automation systems that enable pregnant woman. Without the help of external technology, a
clinicians to predict and determine the monitoring of Maternal mother will not be able to know the FH even when it is life-
and Fetal Health (MFH) with the aid of the Internet of Things threatening. Therefore, to study the MH, monitoring the fetal
(IoT). This paper provides a solution for monitoring high-risk is an important tool [7]. Fetal monitoring is reliable, safe, and
MHF based on IoT sensors, data analysis-based feature easy to operate, which is widely practiced by MCH
extraction, and an intelligent system based on the Deep organizations across India [8-10]. However, the fetal
Convolutional Generative Adversarial Network (DCGAN) monitoring used by most hospitals still traces deficiencies.
classifier. Various clinical indicators such as heart rate of MF, First, the information cannot be shared. Monitor results must
oxygen saturation, blood pressure, and uterine tonus of maternal be printed in most hospitals, making them unsuitable for
are monitored continuously. Many data sources produce large storage and easy to lose, and sharing tracking information and
amounts of data in different formats and ratios. The smart health advice from multiple individuals may not feel timely.
analytics system proposes to extract several features and measure
linear and non-linear dimensions. Finally, a DCGAN has been These factors make it difficult for doctors to perform
proposed as a predictive mechanism for the simultaneous medical tasks or delay illness, which can lead to medical
classification of MFH status by considering more than four accidents. When pregnant women are in the obstetrics
possible outcomes. The results showed that the proposed system department, early warning function and intelligent real-time
for mobile monitoring between MFH is a practical solution based monitoring system are unable and they face other issues such
on the IoT. as high risk, high emergencies, and massive flow of other
pregnant women. In addition, serious consequences and life-
Keywords—Deep convolutional generative adversarial network; threatening risks have occurred, when pregnant women are
fetal health monitoring; high-risk pregnancies; internet of things;
unable to notify doctors in time. Finally, monitoring of human
smart healthcare system
health at home fails to recognize: at present, traditional health
I. INTRODUCTION systems cannot meet the needs of continuous monitoring of
pregnant women. Pregnant women, as expectant mothers, play
Remote monitoring systems in the healthcare domain are an indispensable role in the upbringing of their children.
increasing the daily reach of health for at-risk populations, Therefore, self-monitoring at home is an important content
especially pregnant women [1] and the elderly [2]. To identify during the period of perinatal health care.
the early disease symptoms and provide care, the patients are
monitored every second by using these promising techniques In recent years, communities and families are greatly
in healthcare. The major functionality of the system is to entering into the comprehensive application of information
diagnose and predict the health conditions of the user and platforms such as cloud computing technology, IoT
provide warnings and training for the same. Nowadays, recent healthcare, big data, communication technology, etc. It
advances in the technologies of IoT have presented a way to provides individuals with purposeful and personalized
enable such monitoring services 24/7. The IoT is a growing services, enabling them to advance from telemedicine to new
network of interconnected objects that include shared ideas and ways of preventing disease and addressing major
knowledge about decision-making and efficient and public health issues in the lives of women and children [11-
autonomous operation [3-6]. Various sources such as 13]. The IoT [14] means things are connected via the Internet
computer knowledge, communication link, and sensitivity are that, understands the communication between objects using
used by IoT in healthcare. As the content of public health, modern information technologies such as smart sensing,
MFH is highly regarded by governments. However, medical identification technology, and wireless communication. IoT-
care services, especially obstetric care, are limited, which based M-Health uses wearable clinical sensors [15-17] to
decreases the efficiency of the medical staff and increased the provide patients with real-time feedback on key symptoms and
pressure of high-quality service. medical information and provide them with "anytime,
anywhere" healthcare.
214 | P a g e
www.ijacsa.thesai.org
Vol. 13, No. 1, 2022
Healthcare as a Service platform architecture for cloud-

contractility database, this smartphone app has been developed
based medical decision support services is developed in [18].
and tested for verifying reliability and performance in terms of
In [19], a coherent framework for M-Health monitoring and
power consumption. The analysis showed that this application
IoT-based remote monitoring is proposed. In [20], the IoT-
serves the purposes of the framework in defining the work
based cloud service is optimized for the next generation of
system.
smart environments. In wireless heterogeneous networks,
architecture of hierarchical sensor-based healthcare is The significance of variants with similar features between
developed by the work [21]. Other work [22] focused on a the EPL models and the current pregnancy models is proposed
variety of wireless access networks and provided a framework by Liu, et al., [25]. After the collection of embryo samples, the
for remote patient monitoring services. In some other cases, correlation between the heart rate of the fetus is identified,
the software is developed by the IoT infrastructure for safe where a regression model is used to achieve the normal
and smart healthcare [23]. development of FHR. The remaining analysis reveals the
importance of the FHR in determining pregnancy outcomes.
An example of GAN model architecture is shown as below
To develop the computational models, this paper developed
in Fig. 1.
six different machine learning (ML) techniques are developed.
Sensitivity is used to compare the accuracy of both the
presence of FHR and conditions of absence for predicting the
performance. FHR is closely related to ETD for normal
development and attained a high-performance value. When
compared with all techniques, the random forest has 97% of
recall, F1-score, and accuracy with 0.97 of AUC; however,
deep learning techniques are required for effective prediction.
During pregnancy, the exposure of incarceration and food
insecurity is identified by Testa et al., [26]. From 2004 to
Fig. 1. Example of Generative Adversarial Network Model Architecture.
2015, the LR was used to determine the relationship between
An integrated solution is proposed in this work for father and mother of a fetus’ food insecurity using Pregnancy
collecting different data from devices and sensors of IoT, Risk Assessment System (PRAMS) results. Withdrawal of
linear and non-linear features are extracted, emergency alarms controls is associated, directly or indirectly, with a 165%
are used to analyze the data and finally, the MFH is increase in the risk of food instability. Attendance analysis
automatically predicted by the DCGAN model. The most indicates that this relationship is driven by various factors
significant contributions are presented here as: such as receiving WIC benefits, unemployment of maternal
and financial hardship.
1) A continuous monitoring of MFH is carried out by
Azimi et al., [27], established a flexible decision-making
integrating the medical devices and sensors of IoT.
mechanism to provide 24/7 health outcomes in the absence of
2) To improve the diagnostic accuracy, fog computing data, despite missing policies. Various data resources are
architecture is used to develop an automated emergency leveraged in IoT systems for providing the results and
subsystem with inference rules set. imputing the mission values. This approach was validated in
3) The extraction of linear and non-linear features are the Human Maternal Health Cycle Research, where 20
done by a smart health analytics system. pregnancies were observed for 7 months. The health status of
4) The status of MFH is classified by analyzing the the maternal is measured by using her heart rate in real-time
multiple metrics with the help of the DCGAN model. applications. While comparing with existing related works, the
accuracy is highly achieved by this developed method. But,
This research paper is structured as follows. The related the accuracy results are low, when there are large missing
works for monitoring the fetal and maternal status are given in window size data presents.
Section 2. A brief explanation of the system model with a
predictive model is presented in Section 3. The validation of The website is developed by Mourad M et al., [28], and the
existing techniques with the proposed algorithm is described signalling site is used to study uterine contractions, their
in Section 4. Finally, the scientific contribution of the research characteristics, and labour study. In this investigation,
work with its future development is depicted in Section 5. different nonlinear techniques are used to determine
pregnancy and labor signals and to examine pregnancy signals
II. RELATED WORK before labor with Hogworth frontiers, the multifaceted nature
A safe and reliable monitoring framework at less cost- of Lempel-Ziv, and the measurement of a fractal. In Lebanon
effective is developed by Allah et al., [24] to make the home and France, all data from 12 WBL to 1 WBL are recorded and
more comfortable and mitigate the effects of preterm labor in played back using a terminal network of size 4 × 4. The
pregnant women. Non-invasive technology is used by the engineered signals are used by these techniques for testing the
system to monitor EHG defects using wireless body sensors sensitivity of nonlinearity modifications, which are then
and smartphones. The smartphone will check for contractions applied to real signals. These results show that nonlinear
and alert you in case of early delivery. Using the cervical techniques are commonly used to detect pregnancy
fluctuations and to reduce symptoms.
215 | P a g e
Vol. 13, No. 1, 2022

Vol. 13, No. 1, 2022
III. PROPOSED SYSTEM pressure, temperature, heart rate of both Mother and fetal and
Fig. 3 shows an overview of the proposed structure. The oxygen saturation. Fetal and maternal monitoring are
flow of the methodology is depicted as follows: initially, the developed by using IoT modules, where diagnostic support is
IoT devices are used to generate the data and then transmitted also provided by non-structured data.
to the emergency subsystem for identifying any distress of
FHS. The medical staff gets informed if any emergency is To continuously monitor the fetus, the heart rate of his/her
obtained. After all this, data is transferred to the cloud, where is only considered, which is obtained by the sensor of Doppler
the calculation of features is processed and a prediction with a 4 Hz sampling rate. Then, a toco-dynamometer sensor
system based on one-dimensional DCGAN is used. At last, is used to monitor the uterine tonus activity of maternal with
medical diagnoses are supported by this classification model the same sampling rate. Fig. 4 shows the modelling of the IoT
and the results are provided to the clinical staff members for interface layer.
further analysis. At a 1 Hz sampling rate, important signals of maternal are
The medical staff only has access to patients' details and obtained, where a photoplethysmography sensor is used to
their diagnostic outcomes, where authentication, access derive the oximetry and heart rate of maternal; then digital
control layer, and data encryption levels are used to provide sensor integrated with medical devices is used to acquire the
communication protection for data privacy and confidentiality. blood pressure for systolic and diastolic with temperature.
Then, relevant events, audio, and photo notes of maternal that
There are four parts in the developed solution, which are are acquired by medical staff are shared with the specialists,
presented in Fig. 2. The integration of medical devices and who are added to this system.
sensors for the collection of data is presented in the first layer
called the IoT layer, where the emergency subsystem is
presented in the second layer (i.e. Fog computing layer) that is
according to the inference rules and fixed clinical thresholds.
The third and final part is considered as the Cloud computing
layer, where signal processing techniques are used to extract
the features in the third part, and classification of MFH is
carried out by one-dimensional DCGAN in the fourth layer.
A. IoT Layer
Sensor and Equipment Devices which are used to collect
medial parameters from mother and fetal.
The components that are presented in this layer are
described as: Four vital signs of maternal such as blood Fig. 2. The Flow of the Proposed Structure.
Fig. 3. Proposed Healthcare-IoT for Simultaneous Monitoring of a Mother and Fetus.
Fig. 4. Representation of Patient's Data with the Generation of non-external Data.
216 | P a g e
Vol. 13, No. 1, 2022
B. Fog Computing Layer: Subsystem for Emergency It should be noted that a total of 6 classes are considered and
With limited resources of technology in remote clinical included in Table III for maternal and fetal diagnostic
facilities and developing countries for providing ambulatory
support, management and adoption of a cloud computing
system for monitoring the real-time data is a challenging task.
Therefore, architecture on fog computing is developed for
supporting the requirements by creating a layer to collect the
data on clinical premises.
For the signals of UC and heart rate of fetal, this type of
external sensor is ideal for sound generation depending on the
situation or the mother's movements [29]. Essentially, a pre-
processor is included in the model before considering the
specific dimensions of noise filtering and zero detection. The
selected layer develops an automated analytical system for
clinically important signals, according to the set of defined
limits. The system is designed using three types of diagnostics
(i.e. Emergency Class as EC) given in Table I.
According to the International Guidelines for Obstetricians
and Gynaecologists (IGOG) [30], detailed descriptions of each
standard portal and related classifications are provided in
Table II for guidance on clinical group definitions and
parental criteria.
C. Cloud Computing Layer: Subsystem for Extraction of
Automatic Features
A data analytical module is created in this part for the
extraction of maternal and fetus' features. To determine the
parameters of UC and heart rate of fetus, signal processing
techniques [31] are used and then non-linear and statistical
metrics are calculated. The changes include long decelerations
and baseline adjustments that need time to confirm and long-
term analysis are required by interpretation of fetal's heart rate.
Therefore, once the signal acquisition is done, after 10
minutes only the measures are calculated at the initial step and
updated every 5 minutes for the entire examination.
There are two steps involved in this module, the initial
importance is given for monitoring the fetal and finally, the
vital signs of the mother has considered as second steps. For
continuous monitoring, maximum information is achieved by
analyzing the uterine contractions and heart rate of fetal by
using signal processing techniques. In this sub-system, a total
of 15 features are extracted for the analysis of the heart rate of
the fetus that is established by medical experts, where the
features include baseline value, baseline changes for instant
and numbers, minima number, FHR minima instants, peaks
for number and instants, decelerations of DIP-I and DIP-II,
UC occurrences for number and instants, sample entropy for 5
and 20 minutes window, long decelerations and variable
decelerations.
D. Predictive Subsystem using DC-GAN Model
GANs (Generative Adversarial Networks) are made up of
two models that are trained concurrently using an adversarial
approach. As shown in Fig. 5(a) and Fig. 5(b), a generator
learns to make realistic images, whereas a discriminator learns
to distinguish between actual and fraudulent images.

Vol. 13, No. 1, 2022
diagnoses based on medical group classification. In this
work, a DC-GAN is used for the prediction process.
In this paper, the conditional DC-GAN is used to
generate conditional deep changes according to DC-
GAN [32] and cGAN [33]. In the original DC-GAN
architecture, the bias was made up of step confusion
layers, modular correction layers, and LeakyReLU
activations.
The generator contains spasms, translucency,
patches, and ReLU activations. From part 3 of the cloud
computing layer, the input of the selected classifier
consists of 15 features of the system to predict the six
possible outputs, which are described in Table III. Fig.
5 shows the configuration of the DC-GAN state.
Instead of the original layer of convolutional-
transpose, an up-sample and convolutional layer are
used in a generator for avoiding the artifacts of
checkerboard [34].If standard de- convolution is used to
scale up from low to high precision, it uses all of the
small feature points to 'plot' a larger square. This is
where the "unequal overlap" problem comes in, i.e.
when these "squares" converge on the larger side. In
particular, D convolutions are random nests when the
size of the kernel is not divisible by a step. Overlapping
pixels create an unnecessary chessboard shape on the
generated images. So, to get the "de-Convolution"
function, we used the sample layer above instead. We
scaled the feature using the top sample layer using
billionaire (or adjacent interpolation) and then the
convolutional layer. To achieve better results, a
RelectionPad2d layer with size 1 is added before the
convolutional layer for avoiding the boundary artifacts.
TABLE I. EMERGENCY SUBSYSTEM OUTPUT’S CLASSES
Layer’s Outcome Explanation

EC1 as 1 Fetal Emergency (FE)
EC2 as 2 Maternal Emergency (ME)
EC3 as 3 Maternal and Fetal Emergency (FME)
TABLE II. LIST OF EMERGENCY LIMITS/THRESHOLDS

BASED ON THE ABOVE GUIDELINES
Vol. 13, No. 1, 2022
Clinical Output
Threshold Interpretation
Parameter Class
Heart Rate of Fetus > 160 Normal tachycardia 1
> 180 Severe tachycardia 1
< 100 Normal bradycardia 1
< 80 Severe bradycardia 1
Heart Rate of
> 100 Tachycardia 2
Mother
< 60 Bradycardia 2
Oximeter < 90 Mother’s hypoxemia 2
Temperature > 37.5 Fever for mother 2
Systolic blood
> 140 Mother blood pressure 2
pressure
Diastolic blood Blood pressure for
> 90 2
pressure mother

Vol. 13, No. 1, 2022
TABLE III. PREDICTED CLASSES FOR THE PROPOSED SUBSYSTEM

min𝐺 max𝐷 𝑉(𝐷, 𝐺) =
Output Description D𝑥~𝑝𝑑𝑎𝑡𝑎 (𝑥)[log 𝐷 (𝑥)] + D𝑥~𝑝𝑧(𝑧)[log(1 − 𝐷(𝐺(𝑥))� (1)
PC1 Normal for both Maternal and Fetal There are two losses such as 𝐿𝑜𝑠𝑠_𝐷 and𝐿𝑜𝑠𝑠_𝐺 used
PC2 Suspicious only on fetal since a generator and a discriminator are presented in the
PC3 Distress on fetal
GAN model. Here, the loss function is used as Binary Cross-
Entropy (BCE).
PC4 Suspicious only on maternal
PC5 Harmful for Maternal
A sum of 𝑒𝑟𝑟𝐷_𝑟𝑒𝑎𝑙 = −𝑙𝑜𝑔(𝐷(𝑥))and𝑒𝑟𝑟𝐷_𝑓𝑎𝑘𝑒 =
−𝑙𝑜𝑔(1 − 𝐷(𝐺(𝑧))) is used to calculate the first loss, where
PC6 Harmful for both the BCE is represented to the reality only when the fake inputs
and real inputs are received by D. The prediction of false
positive is carried out by calculating the BCE when the fake
inputs are received by D, i.e.𝐿𝑜𝑠𝑠_𝐺 = −𝑙𝑜𝑔(𝐷(𝐺(𝑧))).
Set the default value for Adam optimizer as learning rate =
0.0001, when the training and updating of the generator and
discriminator are carried out one by one. Finally, six possible
outcomes are derived and the next section will show the
(a).Generator. validation of the proposed model with existing systems.
IV. VALIDATION AND RESULTS
In this section, details of the datasets used in testing
evaluation for a particular system are provided. Presenting the
results obtained with the contingency subsystem, the
following section validates the predictive subsystem feature of
DCGAN with or without extrusion, using existing deep
learning techniques. The performance measures used in this
(b).Discriminator.
study are described in this section.
Fig. 5. Structure of Conditional DC-GAN.
A. Dataset Description
To control the output function, the input model gets a class Simulation experiments were performed on a standard
designation for the generator and the amplifier. The generator antenatal CTG database from the UCI ML Repository
receives a random beep (1 x 1 x Z) and a heat conditional sign (University of California, Irvine) [36]. CTG data were
(1 x 1 x C), where the dimensions Z and C represent the collected from 29 to 42 weeks gestation at SisPorto 2.0 in
number of categories. By default, we chose Z = 100 and C = Portugal [37]. The database contains 2126 cases with 21 traits
60. They were combined and sent to the curved layer using a 1 and cases classified according to FIGO guidelines by the
× 1 core. Output channel 8192 (= 4 × 4 × 512). Later, the consensus of three experts: 1655 general cases, 295
output data was converted to 4×4×512format. Finally, we sent suspicious, and 176 pathological data.
the data to several modules (except for Up-sample + Conv2D
+ Batch-Norm, the output layer) as high as the original DC- B. Performances Metrics
GAN. An equal-valued data is up-sampled, only when the data In this section, major parameter metrics are discussed to
size is 1×1, and therefore, input data i.e. concatenation of one- validate the system model's performance. The correct
hot label and random noise is not resized directly. Hence, the identification of data samples over a total number of instances
input noise size is kept at 1×1×Z. To make the resizing step is calculated by using accuracy. An identification of MFS is
work, an extra convolutional layer is added in this model, often accurate by using the parameter called precision or
where the C channel is encoded with a label in the positive predictive value. The possible outcomes are correctly
discriminator. More precisely, the function label n is the data classified by the proposed model is known as
of the H × W × C scale, each 1s and 0.s in the n channel. In recall/sensitivity. The proportion of actual negatives is
the input layer, the feature is associated with the label: each calculated by using the true negative rate/specificity. The
feature is associated with the hotel. Channel direction label. harmonic average of sensitivity and precision is provided by
Thus, the input channel size was 3 + C. Similar to the original F1-score or F-measure.
DC-GAN configuration, the Discriminator configuration has
multiple configuration layers and a default volume layer Accuracy is calculated as follows:
𝑇𝑃+𝑇𝑁
(except for the output layer). 𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 = (2)
𝑇𝑃+𝑇𝑁+𝐹𝑃+𝐹𝑁
E. Training Process and Loss Function Precision is working out as following
We used the standard loss function for GANs, which is 𝑇𝑃
defined in [35] as follows: 𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 = (3)
𝑇𝑃+𝐹𝑃
218 | P a g e
Vol. 13, No. 1, 2022
Sensitivity is deliberate as follows. TABLE VI. EMERGENCY SUBSYSTEM PERFORMANCE UNDER EXPERT
𝑇𝑃 SUPERVISION AND DEFAULT RULES SET WITH FIXED LIMITS
𝑅𝑒𝑐𝑎𝑙𝑙 =
𝑇𝑃+𝐹𝑁 (4) Considering the set of static thresholding
Outpu
Specificity and F-measure are defined as follows: t Sensitivity Specificity AUC MSE
𝑆𝑝𝑒𝑐𝑖𝑓𝑖𝑐𝑖𝑡𝑦 = 𝑇𝑁/(𝐹𝑃 + 𝑇𝑁) 𝑜𝑟 (1 − 𝐹𝑃𝑅) (5) ME
0.76(0.70,0.81 0.56(0.54,0.58 0.70(0.68,0.73 0.08(0.07,0.08
) ) ) )
𝐹1 − 𝑠𝑐𝑜𝑟𝑒 = 2𝑇𝑃/(2𝑇𝑁 + 𝐹𝑃 + 𝐹𝑁) (6) 0.71(0.68,0.73 0.82 0.87(0.86,0.88 0.18(0.17,0.19
FE
) (0.80,0.85) ) )
C. Evaluation of Proposed Emergency Subsystem 0.87(0.85,0.88 0.91 0.96(0.96,0.97 0.08(0.07,0.09
FME
All emergencies have been classified by the organization. ) (0.89,0.92) ) )
The results in Table IV show that the sensitivities (Caesarean
deliveries as CI) for all classifiers are very low and the The new set of proposed default rules has slightly improved the
associated features are high. This is expected because the performance of the contingency subsystem. By considering only
database is skewed in favor of genital records. Sensitivity and the maternal prognosis, the AUC (ME) is 70%. For fetal
95% adjusted specificity for AUC and MSE are determined emergency diagnosis, the system performance is AUC (FE) 87%.
using the recommended CI model. This can happen because there is only one parameter that is
directly related to the condition of the fetus, which is the FHR.
Disagreements during the modelling phase may result in Finally, in the worst-case scenario, when the mother and fetus
poor performance. The integrating parameters from Table II have an emergency, the specific regimen performs best, with an
are used to add the inference rule set to the system for AUC (FME) of 96%.
improving the accuracy levels. For instance, the emergency of
MFH is highly calculated by diagnosing the elevated blood D. Performance Analysis of DC-GAN Prediction Subsystem
pressure for systolic and diastolic, the temperature of In this section, five parameters are used to validate the
maternal, etc. After discussing with the medical team, a total proposed DC-GAN with existing techniques by considering
of twenty-six hypothetical rules are generated and here, five with and without feature extraction techniques. and linear
samples are provided in Table V. features. The existing technique called Convolutional Neural
Network (CNN) [38] is designed for a smart healthcare system
The performance of the emergency subsystem based on the for monitoring the MFH. Multiple features extraction
set of standard limits is shown in the Table VI. techniques are used to calculate both non-linear and non-linear
It is important to note that performance is unsatisfactory features. The CNN network consists of six CLs, max-pooling,
with FP and FN rates high and sensitivities below 80%, which single flatten layer and output layer for the prediction process.
is unacceptable given the critical interpretation of the The work [38] uses homogenous i.e. having the same neuron
contingency. The new set of proposed default rules has type in the entire network and based solely on the linear-
slightly improved the performance of the contingency. neuron model and didn't focus on non-linear features for better
prediction. The data collected from 45 patients before labor
TABLE IV. PERFORMANCE OF THE EMERGENCY SUBSYSTEM and 55 patients during labor and validated the performance of
CNN with existing ML techniques. But the results are not
Outpu Performance of Model before setting the static threshold satisfactory, while using one-dimensional CNN, which is
t Sensitivity Specificity AUC MSE advanced network called DC-GAN is incorporated with a
0.00(0.00,0.0 0.99(0.99,0.9 0.60(0.58,0.6 0.08(0.07,0.0 smart healthcare system for monitoring the MFH. In addition,
ME this proposed model uses the standard datasets for the
0) 9) 1) 8)
0.02(0.01,0.0 0.99(0.99,0.9 0.68(0.65, 0.08(0.07,0.0 prediction process and compared them with existing
FE techniques such as CNN [38], Long-Short term memory
3) 9) 0.69) 8)
0.02(0.00,0.0 0.99(0.99,0.9 0.71(0.68,0.7 0.08 (0.07, (LSTM), etc.
FME
4) 9) 3) 0.08)
1) Validation analysis of the proposed model without
feature extraction: Initially, the experimental results of DC- GAN
TABLE V. THE SUBCOMMITTEE ON CONCEPTUAL LAWS CONSIDERED TO are compared with CNN, LSTM, RNN, and DNN in terms of
DESCRIBE THE EMERGENCY FOR MOTHER OR FETUS
sensitivity, specificity, and precision, which are shown in Table
VII and Fig. 6.
Rule Output
[MHR > 90] and [blood pressure for systolic> 120] ME The proposed DCGAN model achieved 62.32% of precision
and 77% of sensitivity and specificity. But, the DNN and LSTM
[Temperature < 36] and [blood pressure for systolic< 100] and
[blood pressure for diastolic< 60]
ME model achieved nearly 46% to 50% of sensitivity, specificity, and
precision. The reason is that the LSTM model requires more
[MHR > 80] and [FHR > 140] FE
memory and takes a long time for training and it is easy to overfit.
[FHR > 150] and [MT > 37] FE The DNN is also extremely expensive to train due to complex data
[blood pressure for diastolic > 13] and [blood pressure for models and it requires expensive GPUs. The CNN and RNN
MFE
systolic> 13] and [MHR > 90] and [FHR > 120] models achieved nearly 51% to 52% of sensitivity, specificity, and
the precision.
ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI 219 | P a g e

Vol. 13, No. 1, 2022
Vol. 13, No. 1, 2022
TABLE VII. COMPARATIVE ANALYSIS OF VARIOUS DL ALGORITHMS

WITHOUT FEATURE EXTRACTION analysis of different DL techniques in terms of specificity,
precision, and sensitivity.
Parameter Metrics
DL Algorithms
Sensitivity Specificity Precision TABLE VIII. COMPARATIVE ANALYSIS OF VARIOUS DL ALGORITHMS
77.66 77.66 62.32 WITHOUT FEATURE EXTRACTION
DC-GAN
CNN 52.27 52.27 51.65 DL Algorithms Accuracy F1-Score
RNN 51.52 51.52 50.73 DC-GAN 89.03 65.92
LSTM 50.87 50.52 48.56 CNN 81.66 51.72
DNN 47.85 48.65 46.5 RNN 83.63 50.24
LSTM 75.95 49.85
90 DNN 73.54 46.21

80
100
Parameter Values (%)
70
90
60
80
Parametric Values (%)

50 70
40 60
30 50
20 40
30
10
20
0 10
DC-GAN CNN RNN LSTM DNN
0
DL Algorithms
Sensitivity
Specificity
Accuracy
Precision
Fig. 6. Graphical Representation of Proposed DCGAN without Feature DL Algorithms F1-Score
Extraction.
Fig. 7. Graphical Representation of Proposed DCGAN in terms of Accuracy
The CNN model requires more training data for accurate and F1-score by considering without Feature Extraction.
results, but now it has only three inputs of the emergency
subsystem and provides low performance. The complex TABLE IX. COMPARATIVE ANALYSIS OF VARIOUS DL ALGORITHMS WITH
training procedures are presented in the RNN model and FEATURE EXTRACTION
hence it achieved less than 60% of all parameters. Table VIII DL Algorithms Sensitivity Specificity Precision
and Fig. 7 show the performance analysis of DCGAN and
DC-GAN 98.27 96.70 97
existing DL techniques in terms of accuracy and F1-score by
implementing without feature extraction techniques. CNN 95.95 92.63 93
RNN 97.11 94.62 95
In the accuracy analysis, DNN and LSTM achieved less
performance (only 74%) than other DL techniques, and LSTM 91.62 84.57 85
proposed DCGAN achieved high performance (i.e. 89.03%) DNN 90.87 81.23 83
than CNN and RNN techniques. But, the same proposed
method achieved very low performance in terms of F1-score 100
(i.e. 65.92%), because the three inputs of the emergency-
Parameteric Values (%)
subsystem are directly given to the DCGAN model and it 80

provides low performance since it is a one-dimensional model.
Even though the proposed model achieved less performance, it 60
provides better performance than CNN, RNN, LSTM, and
DNN. The reason is that these existing techniques are unable 40
to handle the inputs of the emergency subsystem due to its
20
structures. DNN and LSTM model achieved nearly 46% to
49% of F1-score, whereas RNN and CNN achieved nearly
0
50% of F1-score.
2) Validation analysis of the proposed model with feature Sensitivity
extraction: In this experimental analysis, the importance of Specificity
DL Algorithms
feature extraction is revealed by implementing it with all the Precision
existing DL and proposed DCGAN models in terms of various Fig. 8. Graphical Representation of Proposed DCGAN with Feature
parameters. Table IX and Fig. 8 show the performance Extraction.
220 | P a g e
Vol. 13, No. 1, 2022
When all the DL techniques are implemented with feature

achieved 89%, the CNN and RNN achieved nearly 96%, and
extraction, its performance is highly improved in terms of
the proposed DCGAN network achieved 97.50% of accuracy
precision, specificity, and precision, while comparing it
while implementing feature extraction. Fig. 10 shows the
without feature extractions. This shows that feature extraction
comparative analysis of various DL algorithms in terms of
plays a major role in this study and the one-dimensional CNN,
accuracy by considering with and without feature extraction
DCGAN, RNN, and DNN are used here and it requires feature
techniques for better validation purposes.
extraction techniques for better performance. In the analysis of
sensitivity, every DL technique achieved more than 90% and
100
the proposed DCGAN achieved 98.27%. The specificity of
DCGAN is less (i.e. 96.70%) than the precision (i.e.97%) of
80
proposed DCGAN, but its performance is highly improved
Accuracy (%)
while compared with existing DL techniques such as CNN,
60
RNN, LSTM, and DNN. The CNN and RNN achieved nearly
92% to 95% of specificity and precision, whereas LSTM and
40
DNN achieved nearly 81% to 85% of specificity and
precision. This analysis shows that the proposed DCGAN
model achieved better performance than other existing 20
techniques. Table X and Fig. 9 show the experimental analysis
of various DL algorithms in terms of accuracy and F1-score 0
DC-GAN CNN RNN LSTM DNN
by considering feature extraction techniques.
TABLE X. COMPARATIVE ANALYSIS OF VARIOUS DL ALGORITHMS WITH

FEATURE EXTRACTION Accuracy with
Feature Extraction
DL Algorithms
DL Algorithms Accuracy F1-Score Accuracy without
Feature Extraction
DC-GAN 97.50 96
CNN 96.03 94 Fig. 10. Comparative Analysis of DL Techniques with and without Feature
RNN 96.78 95 Extraction Techniques in Terms of Accuracy.
LSTM 89.98 86
V. CONCLUSION
DNN 88.58 84
According to the diagnostic system's fog computing
framework, an integrated solution is provided for high-risk
100 monitoring of maternal patients, where this process relies on
IoT-network-based sensors. A large data-analysis module for
95 feature extraction techniques are used to extract features from
Parametric Values (%)
the observed signals, and finally, an in-depth DCGAN-based

90
classification system for predicting maternal-fetal health by
the possible outcomes as PC1 to PC6 for performance
analysis. The main contribution of this work in the Emergency
85 Diagnostics Branch is the design of a set of hypothetical rules
that can achieve more than 80% of the area under the curve for
80 fetal, maternal, and emergencies. A total of 6 possible
outcomes from the prediction model were considered.
75 Compared with existing DL techniques such as CNN, LSDM,
RNN, and DNN, the results show that DCGAN techniques
and homogeneous systemic extraction performed better in the
maternal and fetal and stage II. In the future, the efficiency of
DL Algorithms Accuracy the emergency diagnostic system can be improved by
F1-Score modifying the selected model using different hypothetical
rules.
Fig. 9. Graphical Representation of Proposed DCGAN in Terms of REFERENCES
Accuracy and F1-score by considering with Feature Extraction. [1] WHO. Maternal mortality, Retrieved on 2019. http://www.who.int/
mediacentre/factsheets/fs348/en/.
In the analysis of the F1-score, the LSTM and DNN [2] WHO. Aging and health, Retrieved on 2019. http://www.who.int/
achieved nearly 85%, whereas CNN and RNN achieved nearly mediacentre/factsheets/fs404/en/.
94% to 95%, but the proposed DCGAN achieved 96%. The [3] L. Atzori, et al., The internet of things: a survey, Computer Network. 54
reason for the better performance of the proposed model is to (15) (2010) 2787–2805.
introduce the conditional-based network in the DC-GAN, [4] J.A. Stankovic, et al., Research directions for the internet of things,
where the other techniques use only its basic architecture. In IEEE Internet Things J. 1 (1) (2014) 3–9.
the experiments of accuracy, the DNN and LSTM techniques
221 | P a g e
Vol. 13, No. 1, 2022
[5] J. Gubbi, et al., Internet of things (IoT): A vision, architectural elements,

[22] D. Niyato, E. Hossain, S. Camorlinga, Remote patient monitoring
and future directions, Future Generation Computer Sysem. 29 (7) (2013)
service using heterogeneous wireless access networks: architecture and
1645–1660.
optimization, IEEE Journal on Selected Areas in Communications. 27
[6] R. Mieronkoski, et al., The internet of things for basic nursing care—a (4) (2009) 412–423,
scoping review, International Journalof Nursing Studies. 69 (2017) 78–
[23] M.A. Salahuddin, A. Al-Fuqaha, M. Guizani, K. Shuaib, F. Sallabi,
90.
Softwarization of internet of things infrastructure for secure and smart
[7] W. Gyselaers, V. Storms, L. Grieten, New technologies to reduce healthcare, Computer 50 (7) (2017) 74–79,
medicalization of prenatal care: a contradiction with realistic
[24] Allahem, Hisham and Srinivas Sampalli, "Automated uterine
perspectives, Expert review of medical devices. 13 (8) (2016) 697–699,
contractions pattern detection framework to monitor pregnant women
[8] Y. Lu, X. Zhang, X. Fu, F. Chen, K.K.L. Wong, Ensemble machine with a high risk of premature labor", Informatics in Medicine Unlocked,
learning for estimating fetal weight at varying gestational age, in vol.20, pp.100404, 2020.
Proceedings of the Thirty-Third AAAI Conference on Artificial
[25] Liu L, Jiao Y, Li X, Ouyang Y, and Shi D, "Machine learning
Intelligence, AAAI 2019, 2019, pp. 9522–9527,
algorithms to predict early pregnancy loss after in vitro fertilization-
[9] J. Li, L. Huang, Z. Shen, Y. Zhang, M. Fang, B. Li, X. Fu, Q. Zhao, H. embryo transfer with fetal heart rate as a strong predictor”, Computer
Wang, Automatic classification of fetal heart rate based on Methods and Programs in Biomedicine, vol.196, no.105624, 2020.
convolutional neural network, IEEE Internet Things J. 6 (2) (2019)
[26] Testa, A. and Jackson, D.B., 2020. Incarceration exposure and maternal
1394–1401.
food insecurity during pregnancy: Findings from the Pregnancy Risk
[10] Y. Lu, X. Zhang, L. Jing, X. Li, X. Fu, Estimation of the fetal heart rate Assessment Monitoring System (PRAMS), 2004–2015. Maternal and
baseline based on singular spectrum analysis and empirical mode child health journal, 24(1), pp.54-61.
decomposition, Future Generation Computer System 112 (2020) 126–
[27] Azimi I, Pahikkala T, Rahmani A. M, Niela-Vilén H, Axelin A, and
135.
Liljeberg P, “Missing data resilient decisionmaking for healthcare IoT
[11] Y. Lu, Y. Gao, Y. Xie, S. He, Computerised interpretation systems for through personalization: A case study on maternal health”, Future
cardiotocography for both home and hospital use, in: Proceedings of the Generation Computer Systems, vol.96, pp.297-308, 2019.
31st IEEE International Symposium on Computer-Based Medical
[28] Mourad M, A. Diab, M. Khalil, and C. Marque, "Pregnancy/Labor
Systems, CBMS 2018, IEEE, 2018, pp. 422–427,
Discrimination and Monitoring: An Investigation Using Nonlinear
[12] Y. Lu, Y. Qi, X. Fu, A framework for intelligent analysis of digital Methods”, International Arab Conference on Information Technology
cardiotocographic signals from IoMT-based fetal monitoring, Future (ACIT), Werdanye, Lebanon, pp.1-4, 2018.
Gener. Comput. Syst. 101 (2019) 1130–1141,
[29] J. A. Lobo Marques, P. C. Cortez, J. P. D. V. Madeiro, S. J. Fong, F. S.
[13] Lu, Y., Fu, X., Chen, F., & Wong, K.K, “Prediction of fetal weight at Schlindwein, and V. H. C. D. Albuquerque, "Automatic
varying gestational age in the absence of ultrasound examination using Cardiotocography Diagnostic System Based on Hilbert Transform and
ensemble learning”, Artificial intelligence in medicine, 102, 101748 . Adaptive Threshold Technique," in IEEE Access, vol. 7, pp. 73085-
(2020). 73094, 2019.
[14] C.Perera, C.H. Liu, S. Jayawardena, The emerging internet of things [30] Ayres-de-Campos, D., Spong, C.Y., &Chandraharan, E. (2015). “FIGO
marketplace from an industrial perspective: A survey, IEEE Trans. consensus guidelines on intrapartum fetal monitoring:
Emerg. Top. Comput. 3 (4) (2015) 585–598, Cardiotocography”, International Journal of Gynecology& Obstetrics,
[15] H. Ghasemzadeh, E. Guenterberg, R. Jafari, Energy-efficient 131. 2015.
information-driven coverage for physical movement monitoring in body [31] Q. Zhang, L. T. Yang, Z. Chen, P. Li and F. Bu, "An Adaptive Dropout
sensor networks, IEEE Journal of. Selective. Areas Communication. 27 Deep Computation Model for Industrial IoT Big Data Learning With
(1) (2009) 58–69, Crowdsourcing to Cloud Computing," in IEEE Transactions on
[16] K. Wac, M.S. Bargh, B. jan F. Van Beijnum, R.G. Bults, P. Pawar, A. Industrial Informatics, vol. 15, no. 4, pp. 2330-2337, April 2019.
Peddemors, Power- and delay-awareness of health tele-monitoring [32] Radford, A.; Metz, L.; Chintala, S. Unsupervised representation learning
services: the mobi-health system case study, IEEE Journal on Selected with deep convolutional generative adversarial networks. arXiv 2016,
Areas in Communications. 27 (4) (2009) 525–536. arXiv:1511.06434.
[17] G. Chiarini, P. Ray, S. Akter, C. Masella, A. Ganz, “mHealth [33] Mirza, M.; Osindero, S. Conditional generative adversarial nets. arXiv
technologies for chronic diseases and elders: A systematic review”,IEEE 2014, arXiv:1411.1784.
Journal on Selected Areas in Communications. 31 (9) (2013) 6–18,
[34] Sugawara, Y., Shiota, S., & Kiya, H. “Convolutional Neural Networks
[18] Oh, J. Cha, M. Ji, H. Kang, S. Kim, E. Heo, J.S. Han, H. Kang, H. Chae, Without Any Checkerboard Artifacts”,. 2018 26th European Signal
H. Hwang, S. Yoo, Architecture design of healthcare software-as-a- Processing Conference (EUSIPCO), 1317-1321. 2018.
service platform for cloud-based clinical decision support service,
[35] Goodfellow, I.J.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley,
Healthcare Inf. Res. 21 (2) (2015) 102–110,
D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adversarial nets. In
[19] A.J. Jara, M.A. Zamora-Izquierdo, A.F.S. and, Interconnection Advances in Neural Information Processing Systems 27; Ghahramani,
framework for mhealth and remote monitoring based on the internet of Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q., Eds.;
things, IEEE Journal on Selected Areas in Communications. 31 (9) Morgan Kaufmann Publishers Inc.: Burlington, MA, USA, 2014.
(2013) 47–65,
[36] A. Asuncion and D. J. Newman. “UCI machine learning
[20] M. Barcelo, A. Correa, J. Llorca, A.M. Tulino, J.L. Vicario, A. Morell, repository,”[http://www.ics.uci.edu/~mlearn/MLReposit-ory.html]
IoT-Cloud service optimization in next-generation smart environments, University of California, School of Information and Computer Science,
IEEE Journal on Selected Areas in Communications. 34 (12) (2016) Irvine, CA, 2007.
4077–4090,
[37] Ayresde, C.D., Bernardes, J., Garrido, A., et al.: SisPorto 2.0: “A
[21] Y. Huang, M.Y. Hsieh, H.C. Chao, S.H. Hung, J.H. Park, “Pervasive, program for automated analysis of cardiotocograph”,The Journal of
secure access to a hierarchical sensor-based healthcare monitoring Maternal-Fetal& Neonatal Medicine. 9(5), 311–318 (2000).
architecture in wireless heterogeneous networks”, IEEE Journal on
[38] Marques, J.A.L., Han, T., Wu, W., do Vale Madeiro, J.P., Neto, A.V.L.,
Selected Areas in Communications. 27 (4) (2009) 400–411,
Gravina, R., Fortino, G. and de Albuquerque, V.H.C., 2020. IoT-based
Smart Health System for Ambulatory Maternal and Fetal Monitoring.
IEEE Internet of Things Journal.,2020.
ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI 222 | P a g e

© 2022. This work is licensed under

https://creativecommons.org/licenses/by/4.0/ (the “License”).
Notwithstanding the ProQuest Terms and Conditions, you may
use this content in accordance with the terms of the License.
167

UTS - Bu Dewi2)

Diunggah oleh

Informasi Dokumen

Judul Asli

Hak Cipta

Format Tersedia

Bagikan dokumen Ini

Bagikan atau Tanam Dokumen

Opsi Berbagi

Apakah menurut Anda dokumen ini bermanfaat?

Apakah konten ini tidak pantas?

Hak Cipta:

Format Tersedia

UTS - Bu Dewi2)

Diunggah oleh

Hak Cipta:

Format Tersedia

TUGAS UTS

MATA KULIAH EVIDENCE BASED

Dosen Pengampu : Dewi Nopiska Lilis, M.Keb

CANDRA WIDHI ANJANI

PROGRAM STUDI SARJANA TERAPAN KEBIDANAN POLTEKKES

CANDRA WIDHI ANJANI

ANC TERPADU UNTUK KESEJAHTERAAN IBU DAN JANIN

Article History: Abstract: Universitas Faletehan ikut andil dengan upaya

http://bajangjournal.com/index.php/J-ABDI ISSN: 2797-9210 (Print) | 2798-2912(Online)

upaya meningkatkan derajat kesehatan.

ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

http://bajangjournal.com/index.php/J-ABDI ISSN: 2797-9210 (Print) | 2798-2912(Online)

Ibu Hamil Berdasarkan Usia

Tabel 1. Usia Ibu Hamil

ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

Tabel 2. Hasil Pemeriksaan Hb Ibu Hamil

http://bajangjournal.com/index.php/J-ABDI ISSN: 2797-9210 (Print) | 2798-2912(Online)

Membangun Body Image Ibu Hamil Terintegrasi Hypnosis

Kata Kunci: Body Image, Ibu hamil, Kesejahteraan janin

Received: December 5, 2020

BAHAN DAN METODE

dilakukan yaitu tahap persiapan (Perizinan kegiatan pengabdian kepada masyarakat,

Gambar 1. Distribusi Usia Responden

Hasil kegiatan pengabdian kepada masyarakat didapatkan bahwa sebagian besar

Gambar 2. Distribusi Pendidikan Responden

Hasil kegiatan pengabdian kepada masyarakat didapatkan bahwa sebagian besar

Gambar 3. Distribusi Paritas Responden

Hasil kegiatan pengabdian kepada masyarakat didapatkan bahwa sebagian besar

4. Pengetahuan ibu hamil sebelum dilakukan pelatihan

Gambar 4. Pengetahuan Responden Sebelum Dilakukan Intervensi

5. Pengetahuan ibu hamil setelah dilakukan pelatihan

Gambar 5. Pengetahuan Responden Setelah Dilakukan Intervensi

Pemanfaatan self hypnosis pada kehamilan sangat berpengaruh kepada peningkatan

Gambar 6. Edukasi membangun body image terintegrasi hypnosis dan pemantauan

2. Praktek membangun body image terintegrasi hypnosis dan pemantauan kesejahteraan

Gambar 8. Praktek membangun body image terintegrasi hypnosis dan pemantauan

ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

PENYULUHAN PENTINGNYA ANTE NATAL CARE PADA IBU HAMIL

Kata Kunci: ante natal care; ibu hamil; penyuluhan.

Keywords: ante natal care; pregnant mother; counseling.

ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

C. HASIL DAN PEMBAHASAN

Gambar 1. Flyer pengabdian

Gambar 1 menampilkan flyer pengabdian, di mana semula kegiatan

meeting. Virtual background digunakan oleh seluruh peserta selama kegiatan

Gambar 2. Penyampaian materi “Penyuluhan Kehamilan” oleh

Langkah-langkah berikut merupakan penjabaran dari pelaksanaan kegiatan

ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

Gambar 3. Beberapa peserta rise hand mengajukan pertanyaan

Gambar 4. Peserta pengabdian menyimak materi

Gambar 3 dan Gambar 4 menunjukkan antusiasme peserta menyimak

ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

Gambar 5. Nilai Pretes dan Postes Peserta Pengabdian

Evaluasi kegiatan pengabdian seperti tampak pada Gambar 5 yang

Gambar 6. Kepuasan dan manfaat pelaksanaan pengabdian

Gambar 6 menunjukkan 100% peserta merasakan puas terhadap

ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

D. SIMPULAN DAN SARAN

UCAPAN TERIMA KASIH

fasilitas-kesehatan. Tanggal akses: 13 Februari 2022.

ISSN: 2797-9210 (Print) | 2798-2912(Online) http://bajangjournal.com/index.php/J-ABDI

and Chengyu Liu 2,*

Received: 31 May 2022