Pregnancy-related complications such as gestational diabetes mellitus (GDM), hypertension, anaemia and postpartum depression (PPD) remain significant contributors to maternal morbidity and mortality, particularly in rural and resource-limited settings. This paper surveys recent literature on the application of Artificial Intelligence (AI), Machine Learning (ML), Explainable AI (XAI) and Natural Language Processing (NLP) to maternal healthcare, covering twenty studies published between 2021 and 2026. The reviewed work is organised into four themes: general maternal-risk classification, GDM prediction, PPD detection, and maternal-health dataset creation. Across these themes, a consistent pattern emerges β most systems solve one problem in isolation, provide little transparency behind their predictions, stop at prediction without offering actionable follow-up, and are validated on data that does not represent rural or low-resource populations. Based on these findings, the paper argues for an integrated, explainable and recommendation-driven maternal-health platform, motivating the design of the proposed system, MaaSuraksha.
This survey reviewed twenty recent studies on AI-driven maternal healthcare, spanning maternal-risk prediction, GDM detection, PPD screening and dataset development. While individual techniques β particularly XGBoost-based classification and SHAP-based explainability β have matured considerably, the literature as a whole remains fragmented: most systems address a single complication, offer limited transparency, stop short of actionable guidance, and are validated on data that under-represents rural populations. These findings support the case for an integrated, explainable and recommendation-driven platform such as MaaSuraksha, which brings these capabilities together with a specific focus on underserved healthcare settings.
References
S. K. Dey, A. Rahman, U. R. Siddiqi, and A. Howlader, "Maternal health risk prediction with machine learning methods," PLoS ONE, vol. 19, no. 1, p. e0296307, Jan. 2024. [2] R. Al-Azazi, H. Al-Rashidi, and M. Al-Enezi, "Predicting maternal risk level using machine learning models," Scientific Reports, vol. 14, no. 1, p. 3892, Feb. 2024. [3] A. M. Al-Zahrani and M. A. Alharthi, "Ensemble machine learning framework for predicting maternal health risk (QEML MHRC)," IEEE Access, vol. 12, pp. 14207β14219, Feb. 2024. [4] M. R. Hossain, M. Islam, and T. Ahmed, "Explainable AI based maternal health risk prediction using gradient boosting with LIME and SHAP," Computers in Biology and Medicine, vol. 163, p. 107238, Sep. 2023. [5] A. Moreira, R. Santos, and L. Silva, "Machine learning for pregnancy and childbirth risk management," Journal of Biomedical Informatics, vol. 143, p. 104407, Jul. 2023. [6] N. Mahmud, J. Islam, K. Setu, and M. Islam, "Deep hybrid model for maternal health risk classification," Healthcare Analytics, vol. 3, p. 100142, Jul. 2023. [7] M. A. Islam, S. Akter, M. S. Hossen, S. A. Keya, S. A. Tisha, and S. Hossain, "Early prediction of maternal health risk factors using machine learning," in Proc. 2nd Int. Conf. on Intelligent Technologies (CONIT), Hubli, India, 2023. [8] D. Osei, K. Agyemang, and N. Mensah, "Machine learning models to predict maternal morbidity from electronic medical records: A scoping review," JAMIA Open, vol. 8, no. 2, p. ooab032, Jun. 2025. [9] Z. Huang, Y. Wei, X. Yang, et al., "Prediction of gestational diabetes mellitus at first trimester using machine learning," Frontiers in Endocrinology, vol. 15, p. 1348236, Apr. 2024. [10] R. Kumari, R. Kumar, and M. Nishad, "Explainable AI-driven gestational diabetes prediction using clinical markers," Diagnostics, vol. 14, no. 6, p. 621, Mar. 2024. [11] T. Xiao, R. Jiang, Y. Liu, et al., "Prediction of gestational diabetes mellitus in Asian women using machine learning," BMC Pregnancy and Childbirth, vol. 23, no. 1, p. 432, Jun. 2023. [12] K. Chen, H. Xiong, Y. Zhang, et al., "Prediction model for gestational diabetes mellitus using XGBoost algorithm," Frontiers in Endocrinology, vol. 14, p. 1105538, Mar. 2023. [13] L. Ye, Y. Cao, X. Li, et al., "Machine learning prediction models for gestational diabetes mellitus: A meta-analysis," Diabetes Research and Clinical Practice, vol. 190, p. 109990, Aug. 2022. [14] F. Akter, S. Hossain, M. N. Islam, et al., "AI for detecting and predicting postpartum depression: A scoping review," npj Digital Medicine, vol. 9, no. 1, p. 12, Jan. 2026. [15] S. Park, H. Cho, and J. Yoon, "Detecting and explaining postpartum depression in real-time with generative AI," IEEE Journal of Biomedical and Health Informatics, vol. 29, no. 4, pp. 1023β1034, Apr. 2025. [16] C. Anand, R. Kumar, and P. Sharma, "Predictive analysis of postpartum depression using machine learning," Applied Sciences, vol. 15, no. 3, p. 1284, Feb. 2025. [17] W. Zhang, L. Chen, X. Wang, et al., "Interpretable machine learning model for predicting postpartum depression," Journal of Psychiatric Research, vol. 181, pp. 45β54, Jan. 2025. [18] J. Kim, H. Park, and S. Lee, "Prediction of postpartum depression: Development and validation of machine learning models," Journal of Affective Disorders, vol. 368, pp. 123β132, Jan. 2025. [19] S. Aziz, S. Ahmed, and M. Asif, "Machine learning methods for predicting postpartum depression: A scoping review," JMIR Mental Health, vol. 8, no. 6, p. e29838, Jun. 2021. [20] M. Rahman, T. Islam, and A. Roy, "Comprehensive maternal health risk dataset from IoT systems," Data in Brief, vol. 52, p. 110987, Feb. 2026.
π How to Cite This Paper
Suruchi Pandey, Vinutha H K, Siri P, Suhani S Rao (2026). AI-Driven Approaches for Maternal Health Risk Prediction, Gestational Diabetes Detection, and Postpartum Depression Screening: A Literature Survey. International Journal of Engineering and Techniques, 12(6), 447β450. ISSN: 2395-1303. DOI: https://doi.org/10.5281/zenodo.24184751
