TY  - JOUR
AU  - Shirodkar, Shubham
AU  - Hasan, Raza
AU  - Mahmood, Salman
PY  - 2026
DA  - 2026/06/30
TI  - Maternal Health Risk Prediction in Bangladesh Using Machine Learning
JO  - Journal of Artificial Intelligence in Bioinformatics
T2  - Journal of Artificial Intelligence in Bioinformatics
JF  - Journal of Artificial Intelligence in Bioinformatics
VL  - 2
IS  - 1
SP  - 1
EP  - 21
DO  - 10.62762/JAIB.2026.495804
UR  - https://www.icck.org/article/abs/JAIB.2026.495804
KW  - maternal health risk prediction
KW  - machine learning
KW  - IoT healthcare data
KW  - class imbalance
KW  - clinical decision support
AB  - Maternal mortality risk in Bangladesh remains a critical public health challenge, compounded by rural access gaps and the absence of scalable, data-driven early-warning systems. This study presents a reproducible, interpretable machine learning framework for maternal health risk classification using an IoT-collected dataset of 1,014 patient records and six physiological indicators; a deduplication audit identified 562 repeated sensor readings, a finding which is documented in the exploratory analysis. A rigorous pipeline was implemented encompassing five clinically grounded engineered features - Mean Arterial Pressure, Shock Index, Pulse Pressure, BP Ratio, and Composite Risk Score - alongside SMOTE-based class imbalance correction applied strictly post-split to prevent data leakage. Seven classifiers were systematically evaluated across two experimental tracks: the raw six-feature dataset and the eleven-feature engineered dataset. On the raw six-feature dataset with SMOTE (training: 811 $\rightarrow$ 1{,}218 samples; test: 203 samples), Random Forest achieved the best overall performance (Accuracy: 88.2%; Macro Recall: 0.889; F1: 0.888; AUC: 0.966), confirming its suitability as the champion model. XGBoost achieved the highest AUC (0.967) with marginally lower Macro Recall (0.868). Feature importance analysis revealed Blood Sugar (28.4% MDI) and the engineered Composite Risk Score (12.2% MDI) as the two dominant predictors, validating the clinical feature engineering approach. Feature engineering benefited weaker models most (Logistic Regression $+$3.3 percentage points in Macro Recall) while the strongest tree ensembles marginally preferred the SMOTE-balanced raw feature space. An interactive Tableau dashboard translates predictive outputs into accessible visual analytics for clinical and policy decision support.
SN  - 3068-7535
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Shirodkar2026Maternal,
  author = {Shubham Shirodkar and Raza Hasan and Salman Mahmood},
  title = {Maternal Health Risk Prediction in Bangladesh Using Machine Learning},
  journal = {Journal of Artificial Intelligence in Bioinformatics},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {1-21},
  doi = {10.62762/JAIB.2026.495804},
  url = {https://www.icck.org/article/abs/JAIB.2026.495804},
  abstract = {Maternal mortality risk in Bangladesh remains a critical public health challenge, compounded by rural access gaps and the absence of scalable, data-driven early-warning systems. This study presents a reproducible, interpretable machine learning framework for maternal health risk classification using an IoT-collected dataset of 1,014 patient records and six physiological indicators; a deduplication audit identified 562 repeated sensor readings, a finding which is documented in the exploratory analysis. A rigorous pipeline was implemented encompassing five clinically grounded engineered features - Mean Arterial Pressure, Shock Index, Pulse Pressure, BP Ratio, and Composite Risk Score - alongside SMOTE-based class imbalance correction applied strictly post-split to prevent data leakage. Seven classifiers were systematically evaluated across two experimental tracks: the raw six-feature dataset and the eleven-feature engineered dataset. On the raw six-feature dataset with SMOTE (training: 811 \$\rightarrow\$ 1{,}218 samples; test: 203 samples), Random Forest achieved the best overall performance (Accuracy: 88.2\%; Macro Recall: 0.889; F1: 0.888; AUC: 0.966), confirming its suitability as the champion model. XGBoost achieved the highest AUC (0.967) with marginally lower Macro Recall (0.868). Feature importance analysis revealed Blood Sugar (28.4\% MDI) and the engineered Composite Risk Score (12.2\% MDI) as the two dominant predictors, validating the clinical feature engineering approach. Feature engineering benefited weaker models most (Logistic Regression \$+\$3.3 percentage points in Macro Recall) while the strongest tree ensembles marginally preferred the SMOTE-balanced raw feature space. An interactive Tableau dashboard translates predictive outputs into accessible visual analytics for clinical and policy decision support.},
  keywords = {maternal health risk prediction, machine learning, IoT healthcare data, class imbalance, clinical decision support},
  issn = {3068-7535},
  publisher = {Institute of Central Computation and Knowledge}
}