Bangladesh has made substantial progress in maternal healthcare over the past two decades by reducing maternal mortality from 523 to 136 per 100,000 live births in 2023 [1,2]. However, this progress falls short of SDG 3 targets, and a significant number of women still face difficulties during their pregnancy and childbirth. Community clinics and free treatment have increased access to maternal healthcare, but critical gaps in quality and accessibility remain, particularly among low-income and marginalized communities (LIMCs). Emerging technologies such as artificial intelligence (AI) and Machine Learning have the potential to bridge these current Gaps.
Executive Summary
- Current MMR 136/100,000 live births ; Target < 70 by 2030
- Current NMR 20/1000 live births ; Target < 12 by 2030
- Key Challenges : Delayed Emergency Healthcare, Failed to Risk Detection, Home Based Delivery, Gaps in ANC and PNC, Lack of Formal training
- Benefits of Ai : Real Time Accurate Data, Activity Tracing, Universal and Affordable services
- Key Priorities : Draft AI-driven Maternal Healthcare Strategy, AI-driven Risk Assessment Tools, AI-driven Chatbot, Specialized Training
Current Challenges of Maternal Healthcare in Bangladesh
The report of “Maternal and Perinatal Death Surveillance and Response (MPDSR) in Bangladesh-2023 [3]” highlights ongoing challenges in maternal healthcare. According to the report,
- Postpartum hemorrhage (41.8%) and eclampsia (16.7%) are the leading causes of maternal deaths, both of which are highly preventable.
- Risk detection is poor, with 40% of deaths occurring late in pregnancy (between 37 and 39 weeks of gestation), and 62.5% within 42 days after delivery.
- Gaps in care are evident [5.2% receive no antenatal care, 35% receive no postnatal care] and 38% of deliveries still occur at home, often assisted by untrained birth attendants.
- Many women die at home (21.4%) or en route to a hospital (22.4%) due to delays in emergency care.
Besides these issues, nutritional challenges, unsafe abortion, high infant mortality, social stigma, depression and psychological trauma of pregnant mothers are critical concerns for our maternal healthcare.
Overview of the Current Policy:
Besides a significant number of limitations and challenges, we have made remarkable progress in maternal healthcare over the last two decades. One of the major achievements has been bridging equity gaps by establishing Community Clinics in every Union.
Additionally, the implementation of MPDSR Toolkit, including logistics support, regular coordination at Union level, and consistent training of community health professionals, has strengthened our service delivery.
Death mapping, emergency support kits (e.g., PPH and eclampsia kits), and field level initiative like Mothers’ Assembly and Uthan Baithak, social and verbal autopsies conducted by doctors, midwives, and health inspectors, have significantly increased awareness among local communities.
Upgrade Union Sub Center (USC), Union Health & Family Welfare Centers (UH&FWCs) and Comprehensive Emergency Obstetric and Neonatal Care (CEmONC) to provide 24/7 healthcare support.
Global Innovations in AI for Maternal Health
- Pakistan improves early risk detection from 7% to 40% by AI voice assistant[8]
- Rwanda detects post-C-section infection via AI-driven image analysis with almost 90% accuracy [7]
- Kenya’s remote health tracking system is decreasing maternal death rates [6]
- Malawi has reduced stillbirths by 82% [4,5]
- Vietnam, AI supports parents by providing maternal health tips, nutrition and breastfeeding by real-time question and answer [9].
AI Opportunities in Maternal Healthcare
In Bangladesh, chatbots like Maya APA and ToguMogu are capable of providing information on contraception, family planning, and smart parenting.The inclusion of AI has made them more inclusive and effective by incorporating real-time updated information in marginalized areas despite infrastructural challenges [20,21].
- Recommends safe and suitable treatment based on patient data and preferences [11]
- Supports early diagnosis and proactive management of pre-eclampsia, gestational diabetes, and premature birth [12,22]
- Provides scalable, cost-effective reproductive healthcare, especially for underserved communities [18]. Also enhance maternal healthcare for women with disabilities by using wearable devices, telemedicine, and predictive healthcare tools.
- Identifies major healthcare issues by analyzing cause of death, VA/SA reports, deaths review and ANC & PNC follow-ups data efficiently.
- Guides healthcare professionals [ Doctors, Midwives, CHCPs, FWAs and HAs ] on symptom assessment, referral, and treatment to reduce medical errors.
- Provides antepartum and postpartum clinical guidance including maternal nutrition, breastfeeding and lactation support, postpartum recovery, newborn care, excreta.
Challenges to Implementing AI in Maternal Health
Infrastructural Readiness: Digital health systems powered by AI require considerable investment in both infrastructure and software development, as well as training for stakeholders and providing a reliable, cost-effective, uninterrupted internet connection poses a challenge, particularly in rural areas [23].
Privacy & Bias: Managing reproductive health data presents significant privacy issues [24]. Data security, algorithm bias, and a lack of uniformity are also important concerns [25].
Misinformation: AI-generated content may be false or misleading, particularly from large scale machine learning models [26]. AI has the risk of reinforcing racial, gender, or class gaps, particularly among low- or middle-income groups (LMIGs) [27].
Mitigation Strategies and Stockholders Engagement Plan
Call to Action :
- Phase 01 (within 3 months) :
- Formulate a Comprehensive AI-Driven Maternal Healthcare Strategy
- Pilot AI-driven Risk Assessment Tools in high MMR/NMR region
- Phase 02 (From 6 to 18 months) :
- Scale successful intervention to all districts at union level
- Integrate Ai system into MPDSR-Maternal & Perinatal Death Surveillance and Response System
- Design and Deploy an AI-Powered Maternal Healthcare Chatbot
- Phase 03 (From 18 to 36 months) :
- Integrate Ai systems into National Health Information Systems
- Conduct Specialized Training for Frontline Healthcare Professionals on AI Tools
Appendices
| A2I | Aspire to Innovate |
| AI | Artificial Intelligence |
| ANC | Antenatal Care |
| BIGD | BRAC Institute of Governance and Development |
| CEmONC | Comprehensive Emergency Obstetric and Newborn Care |
| CHCPs | Community Health Care Providers |
| CSOs | Civil Society Organizations |
| DGFP | Directorate General of Family Planning |
| DGHS | Directorate General of Health Services |
| DWA | Department of Women Affairs |
| FWAs | Family Welfare Assistants |
| HAs | Healthcare Assistants |
| INGOs | International Non-Goverment Organizations |
| LIMCs | Low Income Marginalized Communities |
| LMIGs | Lower & Middle Income Group |
| MMR | Maternal Mortality Rate |
| MoHFW | Ministry of Health and Family Welfare |
| MPDSR | Maternal and Perinatal Death Surveillance and Response |
| NGOs | Non-Government Organization |
| NMR | Neonatal Mortality Rate |
| PNC | Postnatal Care |
| PPH | Postpartum Hemorrhage |
| WHO | World Health Organization |
| SDGs | Sustainable Development Goals |
| SHRH | Sexual Health and Reproductive Health |
| SVRS | Sample Vital Statistics |
| TBAs | Traditional Birth Attendants |
| UH&FWCs | Union Health and Family Welfare Centers |
| UNFPA | United Nations Population Fund |
| UNO | Upazila Nirbahi Officer |
| USC | Union Sub Center |
Reference
- Bangladesh Maternal Mortality Rate 2000-2024. (2024). Macrotrends.net.
https://www.macrotrends.net/global-metrics/countries/BGD/bangladesh/maternal-mortality-rate
- Bangladesh Bureau of Statistics. (March 2024). Bangladesh Sample Vital Statistics: Key
Findings. Dhaka: SVRS,BBS
ISBN : 978-984-35-6329-3
- Alim, Md. A., Islam, Md. J., Halim, Md. A., Rahman, Md. M., Mahmud, M., Khan, M.,
Hasan, A. S. M., Zaman, S., UNFPA, UNICEF, WHO, CIPRB, Directorate General of Health Services, & Government of the People’s Republic of Bangladesh. (2024). Maternal and Perinatal Death Surveillance and Response (MPDSR) in Bangladesh. In Progress and Highlights in 2023 [Report]. https://bangladesh.unfpa.org/sites/default/files/pub-pdf/2025-04/Maternal%20and%20Perinatal%20Death%20Surveillance%20and%20Response%20%28MPDSR%29%20in%20Bangladesh%20Progress%20and%20Highlights%20in%202023_0.pdf
- Kimeu, C. (2024, December 9). How AI monitoring is cutting stillbirths and neonatal
deaths in a clinic in Malawi. The Guardian. https://www.theguardian.com/global-development/2024/dec/06/how-ai-monitoring-is-cutting-stillbirths-and-neonatal-deaths-in-a-clinic-in-malawi
- Johnson, D., & Johnson, D. (2021, June 25). Maternal and neonatal care in Malawi
revolutionised through AI – Health Tech World. Health Tech World.
https://www.htworld.co.uk/news/maternal-and-neonatal-care-in-malawi-revolutionised-through-ai/
- Majanga, J. (2024, September 18). AI enhances maternal health care in Kenya, experts
say Voice of America.
https://www.voanews.com/a/ai-enhances-maternal-health-care-in-kenya-experts-say/7789467.html
- Protecting maternal health in Rwanda. (2022, September 18). MIT News | Massachusetts
Institute of Technology.
https://news.mit.edu/2022/protecting-maternal-health-rwanda-0918
- The scientist using AI to improve maternal health. (2025, April 9).
https://www.gatesfoundation.org/ideas/articles/ai-maternal-health-pakistan
- How AI is transforming maternal health care in Vietnam | Think Global Health.
(2022, June 29).Think Global Health.
https://www.thinkglobalhealth.org/article/how-ai-transforming-maternal-health-care-vietnam
- Carlson C, Plonczynski DJ, Vitucci D. My Choice: Navigating Contraception Application
Development. Comput Inform Nurs. 2016 Oct;34(10):423-428.
doi: 10.1097/CIN.0000000000000297. PMID: 27749335.
https://pubmed.ncbi.nlm.nih.gov/27749335/
- Daniel San Martin; Pexxi: the AI-powered genetic test clarifying contraception; Artificial
Intelligence 2020; May 21, 2020; London, UK
ISSN : 2167-0919
https://www.hilarispublisher.com/open-access/the-aipowered-genetic-test-clarifying-contraception.pdf
- Jiang L, Tang K, Magee LA, von Dadelszen P, Ekeroma A, Li X, Zhang E, Bhutta ZA. A global
view of hypertensive disorders and diabetes mellitus during pregnancy. Nat Rev Endocrinol. 2022 Dec;18(12):760-775. doi: 10.1038/s41574-022-00734-y. Epub 2022 Sep 15.
PMID: 36109676; PMCID: PMC9483536.
https://pubmed.ncbi.nlm.nih.gov/36109676/
- Aderaldo JF, Rodrigues de Albuquerque BHD, Câmara de Oliveira MTF, de Medeiros Garcia
Torres M, Lanza DCF. Main topics in assisted reproductive market: A scoping review. PLoS One. 2023 Aug 1;18(8):e0284099. doi: 10.1371/journal.pone.0284099. PMID: 37527215; PMCID: PMC10393141.
https://pubmed.ncbi.nlm.nih.gov/37527215/
- Sinha C, Cejas C, Oseku E, Arnaout NE, Imram M. AI solutions improving sexual and
reproductive health across the Global South; IDRC.
- Ullah F, Iqbal A, Iqbal S, Kwak D, Anwar H, Khan A, Ullah R, Siddique H, Kwak KS. A
Framework for Maternal Physical Activities and Health Monitoring Using Wearable Sensors. Sensors (Basel). 2021 Jul 21;21(15):4949. doi: 10.3390/s21154949. PMID: 34372186;
PMCID: PMC8348787.
https://pubmed.ncbi.nlm.nih.gov/34372186/
- Chemisto M, Gutu TJ, Kalinaki K, Bosco DM, Egau P, Fred K, Oloya IT, Rashid K. Artificial
intelligence for improved maternal healthcare: a systematic literature review.
IEEE AFRICON. 2023;20:1–6.
doi:10.1109/AFRICON55910.2023.10293674
https://ieeexplore.ieee.org/document/10293674
- Shifa HA, Mojumdar MU, Rahman MM, Chakraborty NR, Gupta V. Machine learning models for
maternal health risk prediction based on clinical data. In: 2024 11th International Conference on Computing for Sustainable Global Development (INDIACom).
IEEE. 2024; 1312–1318.
doi:10.23919/INDIACom61295.2024.10498822
https://ieeexplore.ieee.org/document/10498822
- Mikhael S, Gaidis A, Gavrilova-Jordan L. Regional disparities in access to assisted reproductive
technology: assessment of patient satisfaction when employing modern technology to close the gap. J Assist Reprod Genet. 2021 Apr;38(4):889-894.
doi: 10.1007/s10815-020-02027-7. Epub 2021 Jan 14. PMID: 33447948;
PMCID: PMC7808701.
https://pubmed.ncbi.nlm.nih.gov/33447948/
- Huddleston A, Ray K, Bacani R, Staggs J, Anderson RM, Vassar M. Inequities in Medically
Assisted Reproduction: a Scoping Review. Reprod Sci. 2023 Aug;30(8):2373-2396. doi: 10.1007/s43032-023-01236-6. Epub 2023 Apr 26. PMID: 37099229;
PMCID: PMC10132432.
https://pubmed.ncbi.nlm.nih.gov/37099229/
https://www.ipas.org/our-work/digital-innovations-for-reproductive-health-access/
- Wahl B, Cossy-Gantner A, Germann S, Schwalbe NR. Artificial intelligence (AI) and global
health: how can AI contribute to health in resource-poor settings? BMJ Glob Health. 2018 Aug 29;3(4):e000798. doi: 10.1136/bmjgh-2018-000798. PMID: 30233828;
PMCID: PMC6135465.
https://pubmed.ncbi.nlm.nih.gov/30233828/
- Rahman A, Alam MG. Explainable AI based maternal health risk prediction using machine
learning and deep learning. In: 2023 IEEE World AI IoT Congress (AIIoT). IEEE. 2023;0013–8.
doi:10.1109/AIIoT58121.2023.10174540
https://ieeexplore.ieee.org/document/10174540
- Datta, P. B. D. (2023, August 30). SJ EMR | a software for 21st century doctors.
- Jeyaraman M, Balaji S, Jeyaraman N, Yadav S. Unraveling the Ethical Enigma: Artificial
Intelligence in Healthcare. Cureus. 2023 Aug 10;15(8):e43262. doi: 10.7759/cureus.43262. PMID: 37692617; PMCID: PMC10492220.
https://pubmed.ncbi.nlm.nih.gov/37692617/
- Chaurasia A, Curry G, Zhao Y, Dawoodbhoy F, Green J, Vaninetti M, Shah N, Greer O. Use of
artificial intelligence in obstetric and gynaecological diagnostics: a protocol for a systematic review and meta-analysis. BMJ Open. 2024 May 8;14(5):e082287.
doi: 10.1136/bmjopen-2023-082287. PMID: 38719332; PMCID: PMC11086378.
https://pubmed.ncbi.nlm.nih.gov/38719332/
- Mehta N, Gupta S, Kularathne Y. The Role and Impact of Artificial Intelligence in Addressing
Sexually Transmitted Infections, Nonvenereal Genital Diseases, Sexual Health, and Wellness. Indian Dermatol Online J. 2023 Oct 27;14(6):793-798.
doi: 10.4103/idoj.idoj_426_23. PMID: 38099049; PMCID: PMC10718125.
https://pubmed.ncbi.nlm.nih.gov/38099049/
- Mittermaier, M., Raza, M.M. & Kvedar, J.C. Bias in AI-based models for medical applications:
challenges and mitigation strategies. npj Digit. Med. 6, 113 (2023).
doi:10.1038/s41746-023-00858-z
https://doi.org/10.1038/s41746-023-00858-z
- World Health Organization. (2024). Ethics and governance of artificial intelligence for health:
Guidance on large multi-modal models.
ISBN 978-92-4-008475-9
https://iris.who.int/bitstream/handle/10665/375579/9789240084759-eng.pdf?sequence=1