Predicting High-Risk Pregnancies Using Machine Learning Algorithms and Explainable AI

Sari  Puspita; Gusrino  Yanto

doi:10.29207/resti.v10i4.7071

Authors

Sari Puspita Universitas Metamedia
Gusrino Yanto Universitas Metamedia

DOI:

https://doi.org/10.29207/resti.v10i4.7071

Keywords:

explainable artificial intelligence, high-risk pregnancy, machine learning, random forest, SHAP

Abstract

Pregnancies classified as high-risk play a significant role in increasing health complications and deaths among mothers and newborns, making early risk identification essential for timely clinical intervention. Although machine learning has shown promising performance in predicting pregnancy risk, most existing studies rely on binary classification and provide limited model interpretability. This study proposes an interpretable multiclass machine learning framework that predicts pregnancy risk using maternal health records from primary healthcare facilities. A total of 2,553 maternal medical records collected from five community health centers in Koto Tangah District, Padang City, Indonesia, were analyzed. The proposed framework integrates data preprocessing, StandardScaler, Synthetic Minority Over-sampling Technique (SMOTE), GridSearchCV-based hyperparameter optimization, and Shapley Additive exPlanations (SHAP). Four machine learning algorithms, which are Logistic Regression, Decision Tree, Support Vector Machine, and Random Forest, were systematically assessed with the application of Accuracy, Precision, Recall, F1-score, and ROC-AUC. Of the machine learning models considered, Random Forest performed best, achieving 97.26% accuracy, 90.44% precision, 98.06% recall, 93.65% F1-score, and 99.79% ROC-AUC. SHAP analysis identified Heart Rate, Blood Glucose, Diastolic Blood Pressure, and Systolic Blood Pressure as the most influential predictors, while also improving model transparency through feature contribution and interaction analysis. The results indicate that the suggested framework delivers precise and interpretable multiclass pregnancy risk prediction, demonstrating how it can assist with the early detection of pregnancy risks within primary care environments.

Downloads

Download data is not yet available.

References

[1] S. Bhandari, Y. Dwa, M. Maharjan, and M. Bajracharya, “High Risk Pregnancy and its Outcome in a Tertiary Care Hospital: A Descriptive Cross-sectional Study,” Journal of the Nepal Medical Association, vol. 62, no. 273, pp. 306–310, May 2024, doi: 10.31729/jnma.8561.

[2] R. Sirisomboon et al., “Enhancing the competencies of obstetrical nurses and midwives in high-risk pregnancy management through simulation-based training in Lao people’s democratic republic: A pilot study,” Midwifery, vol. 137, Oct. 2024, doi: 10.1016/j.midw.2024.104132.

[3] R. Arjariya and P. Tiwari, “Prevalence of High Risk Pregnancy: in A Tertiary Care Centre of Sagar Division of M.P,” Int. J. Physiol., vol. 9, no. 1, pp. 36–42, Feb. 2021, doi: https://doi.org/10.37506/ijop.v9i1.2609.

[4] D. A. Galgalo, P. N. Nyakundi, Á. Várnagy, and V. Prémusz, “Evaluating the effectiveness of the global position system beaded bracelets to improve the uptake of antenatal care, health facility delivery, and post-natal care services among pastoralist women in Kenya,” Jul. 01, 2025, Elsevier Ltd. doi: 10.1016/j.healthplace.2025.103484.

[5] M. Mathieu et al., “Incidence, causes, and risk factors of stillbirth in an Amazonian context: Saint Laurent du Maroni maternity ward 2016–2021,” Eur. J. Obstet. Gynecol. Reprod. Biol. X, vol. 18, Jun. 2023, doi: 10.1016/j.eurox.2023.100190.

[6] S. Dahiya, S. Anand, V. Rani, S. Gautam, and S. Nanda, “A Study of High-Risk Factors in Ante-natal Women At A Tertiary Care Centre,” Int. J. Reprod. Contracept. Obstet. Gynecol., vol. 9, no. 7, p. 2959, Jun. 2020, doi: 10.18203/2320-1770.ijrcog20202740.

[7] O. Kelly et al., “The impact of diabetes mellitus on the development of psychiatric and neurological disorders,” Jun. 01, 2024, Elsevier B.V. doi: 10.1016/j.dscb.2024.100135.

[8] K. W. Southern et al., “Standards for the care of people with cystic fibrosis; establishing and maintaining health,” Journal of Cystic Fibrosis, vol. 23, no. 1, pp. 12–28, Jan. 2024, doi: 10.1016/j.jcf.2023.12.002.

[9] S. E. Cuda et al., “Metabolic, behavioral health, and disordered eating comorbidities associated with obesity in pediatric patients: An Obesity Medical Association (OMA) Clinical Practice Statement 2022,” Obesity Pillars, vol. 3, Sep. 2022, doi: 10.1016/j.obpill.2022.100031.

[10] O. Szewczuk, W. Szewczuk, M. Walędziak, and A. Różańska-Walędziak, “Spontaneous regression of fetal pleural effusion in pregnancy complicated with Herpes simplex infection: Clinical presentation and literature review,” Aug. 01, 2024, Elsevier Ireland Ltd. doi: 10.1016/j.ejogrb.2024.06.024.

[11] J. A. Joglar et al., “2023 HRS expert consensus statement on the management of arrhythmias during pregnancy,” Heart Rhythm, vol. 20, no. 10, pp. e175–e264, Oct. 2023, doi: 10.1016/j.hrthm.2023.05.017.

[12] T. Manca, “‘Vaccines protect both you and your newborn:’ A discourse analysis of risk and uncertainty in information about vaccination in pregnancy,” Soc. Sci. Med., vol. 364, Jan. 2025, doi: 10.1016/j.socscimed.2024.117526.

[13] U. Mahadevan et al., “Global Consensus Statement on the Management of Pregnancy in Inflammatory Bowel Disease,” Clinical Gastroenterology and Hepatology, vol. 23, no. 11, pp. S1–S60, Oct. 2025, doi: 10.1016/j.cgh.2025.04.005.

[14] M. Engelhardt et al., “Exclusion and Othering in maternity care for forced migrant women: a qualitative study with forced migrant mothers and health care professionals in Germany,” SSM - Qualitative Research in Health, vol. 8, Dec. 2025, doi: 10.1016/j.ssmqr.2025.100614.

[15] K. Pavagada and J. Vemuri, “Prediction of Maternal Health Risk Factors Using Machine Learning Algorithms,” in Procedia Computer Science, Elsevier B.V., 2025, pp. 2713–2722. doi: 10.1016/j.procs.2025.04.532.

[16] A. O. Khadidos, F. Saleem, S. Selvarajan, Z. Ullah, and A. O. Khadidos, “Ensemble machine learning framework for predicting maternal health risk during pregnancy,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-71934-x.

[17] K. Mahmud Sujon, R. Binti Hassan, Z. Tusnia Towshi, M. A. Othman, M. Abdus Samad, and K. Choi, “When to Use Standardization and Normalization: Empirical Evidence from Machine Learning Models and XAI,” IEEE Access, vol. 12, pp. 135300–135314, 2024, doi: 10.1109/ACCESS.2024.3462434.

[18] R. Shetty, S. Gupta, V. Mediratta, S. Rai, and M. Geetha, “Optimizing Machine Learning-Based Ovarian Cancer Prediction Through Normalization Strategies,” IEEE Access, vol. 13, pp. 128974–128995, 2025, doi: 10.1109/ACCESS.2025.3590871.

[19] I. Aruleba and Y. Sun, “Enhanced credit risk prediction using deep learning and SMOTE-ENN resampling,” Machine Learning with Applications, vol. 21, p. 100692, Sep. 2025, doi: 10.1016/j.mlwa.2025.100692.

[20] M. Yusoff, Y. Mahmud, P. A. R. Azmi, and M. T. M. Sallehud-din, “The improvement of SMOTE-ENN-XGBoost through Yeo Johnson strategy on Dissolved Gas Analysis dataset,” Energy Reports, vol. 13, pp. 6281–6290, Jun. 2025, doi: 10.1016/j.egyr.2025.05.013.

[21] R. K. R. Sarker, S. Hafij, M. A. Yasir, M. Assaduzzaman, M. M. H. Shimul, and M. K. Hossain, “Predicting maternal health risk using PCA-enhanced XGBoost and SMOTE-ENN for improved healthcare outcomes,” Intell. Based. Med., vol. 12, Jan. 2025, doi: 10.1016/j.ibmed.2025.100300.

[22] S. Matharaarachchi, M. Domaratzki, and S. Muthukumarana, “Enhancing SMOTE for imbalanced data with abnormal minority instances,” Machine Learning with Applications, vol. 18, p. 100597, Dec. 2024, doi: 10.1016/j.mlwa.2024.100597

[23] D. Dash, M. Kumar, S. Patra, A. Kumar, and A. Ganguly, “Healthcare Fraud Detection Using an Integrated ML Approach with SMOTE,” in Procedia Computer Science, Elsevier B.V., 2025, pp. 800–810. doi: 10.1016/j.procs.2025.04.312.

[24] Y. Belsti, L. Moran, A. Mousa, H. Teede, and J. Enticott, “Evaluation of machine learning and logistic regression-based gestational diabetes prognostic models,” J. Clin. Epidemiol., vol. 187, Nov. 2025, doi: 10.1016/j.jclinepi.2025.111957.

[25] T. Wahyuningsih, D. Manongga, I. Sembiring, and S. Wijono, “Comparison of Effectiveness of Logistic Regression, Naive Bayes, and Random Forest Algorithms in Predicting Student Arguments,” in Procedia Computer Science, Elsevier B.V., 2024, pp. 349–356. doi: 10.1016/j.procs.2024.03.014.

[26] Y. Gao, Y. Wang, L. Tian, X. Hong, C. Xue, and D. Li, “Evolving adaptive and interpretable decision trees for cooperative submarine search,” Defence Technology, Feb. 2025, doi: 10.1016/j.dt.2025.02.007.

[27] R. Zhao et al., “Decision tree-based parameter identification and state estimation: Application to Reactor Operation Digital Twin,” Nuclear Engineering and Technology, vol. 57, Jul. 2025, doi: 10.1016/j.net.2025.103527.

[28] M. Piazza, A. Spinelli, F. Maggioni, M. Bedoni, and E. Messina, “A robust support vector machine approach for Raman data classification,” Decision Analytics Journal, vol. 16, Sep. 2025, doi: 10.1016/j.dajour.2025.100595.

[29] M. P. Raghunath et al., “PCA and PSO based optimized support vector machine for efficient intrusion detection in internet of things,” Measurement: Sensors, vol. 37, Feb. 2025, doi: 10.1016/j.measen.2024.101806.

[30] W. Li, S. Chen, L. Lin, and L. Chen, “Random-forest-based task pricing model and task-accomplished model for crowdsourced emergency information acquisition,” Systems and Soft Computing, vol. 7, Dec. 2025, doi: 10.1016/j.sasc.2025.200235.

[31] M. García-Torres, F. Saucedo, F. Divina, and S. Gómez-Guerrero, “RFMSU: A multivariate symmetrical uncertainty-based random forest,” Pattern Recognit., vol. 169, Jan. 2026, doi: 10.1016/j.patcog.2025.111939.

[32] D. C. E. Saputra, K. Sunat, T. Ratnaningsih, A. Ma’arif, and I. Suwarno, “SmartForest: Optimizing anemia diagnosis with enhanced random forest and XGBoost integration,” Results in Engineering, vol. 27, Sep. 2025, doi: 10.1016/j.rineng.2025.106442.

[33] E.-B. Rachid, S. Abderrahim, A. Hafid, and R. Souad, “Predicting water potability using a machine learning approach,” Environmental Challenges, vol. 19, p. 101131, Jun. 2025, doi: 10.1016/j.envc.2025.101131.

[34] F. L. P. de Souza, M. A. Dias, T. D. Setiyono, S. Campos, L. S. Shiratsuchi, and H. Tao, “Identification of soybean planting gaps using machine learning,” Smart Agricultural Technology, vol. 10, Mar. 2025, doi: 10.1016/j.atech.2025.100779.

[35] T. Pamutha, W. Promthong, and S. Pahlawan, “Diabetes Disease Prediction Using Machine Learning Classification Algorithms,” vol. 15, no. 4, 2025, doi: https://doi.org/10.18517/ijaseit.15.4.20457.

[36] H. Elbatanouny, H. Tawfik, T. Khater, and A. Gorbenko, “An interpretable machine learning model to predict hospitalizations,” Clinical eHealth, vol. 8, pp. 53–65, Dec. 2025, doi: 10.1016/j.ceh.2025.03.004.

[37] M. Ali, “Classification of imbalanced travel mode choice dataset with SMOTE and prediction using interpretable machine learning,” Sustainable Futures, vol. 10, Dec. 2025, doi: 10.1016/j.sftr.2025.101119.

[38] M. Shamshuzzoha, T. T. B. Audry, M. J. Alam, Z. A. Bhuiyan, M. Motaharul Islam, and M. M. Hassan, “A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTE,” Acta Psychol. (Amst)., vol. 256, Jun. 2025, doi: 10.1016/j.actpsy.2025.105005.

[39] P. Supakar, M. Sarkar, and B. Sarkar, “Forecasting grocery item sales using gradient boosting models: A study of GridSearchCV, RandomizedSearchCV, and optuna optimization approaches,” Ain Shams Engineering Journal, vol. 17, no. 3, Mar. 2026, doi: 10.1016/j.asej.2026.104012.

[40] S. Sadaghiyanfam, H. Kamberaj, and Y. Isler, “Enhanced prediction of ionic liquid toxicity using a meta-ensemble learning framework with data augmentation,” Artificial Intelligence Chemistry, vol. 3, no. 1, Jun. 2025, doi: 10.1016/j.aichem.2025.100087.

[41] O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-56706-x.

[42] J. Opitz, “A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice”, doi: 10.1162/tacl.

[43] K. Gajowniczek and T. Ząbkowski, “ImbTreeAUC: An R package for building classification trees using the area under the ROC curve (AUC) on imbalanced datasets,” SoftwareX, vol. 15, Jul. 2021, doi: 10.1016/j.softx.2021.100755.

[44] G. Niveditha, B. U. Maheswari, and R. P. De Prado, “Elevating Maternal Healthcare: Synergy of Cardiotocography, Machine Learning Models and Interpretive Analysis,” in Procedia Computer Science, Elsevier B.V., 2025, pp. 2787–2797. doi: 10.1016/j.procs.2025.04.539.

[45] A. M. Salih et al., “A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME,” Advanced Intelligent Systems, vol. 7, no. 1, Jan. 2025, doi: 10.1002/aisy.202400304.

[46] Z. Sadeghi et al., “A review of Explainable Artificial Intelligence in healthcare,” Computers and Electrical Engineering, vol. 118, Aug. 2024, doi: 10.1016/j.compeleceng.2024.109370.

[47] V. Vimbi, N. Shaffi, and M. Mahmud, “Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer’s disease detection,” Dec. 01, 2024, Springer Science and Business Media Deutschland GmbH. doi: 10.1186/s40708-024-00222-1.

[48] O. O. Oladimeji, H. Ayaz, I. McLoughlin, and S. Unnikrishnan, “Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis,” Results in Engineering, vol. 24, Dec. 2024, doi: 10.1016/j.rineng.2024.103071.

[49] M. Herrero-Tudela, R. Romero-Oraá, R. Hornero, G. C. Gutiérrez Tobal, M. I. López, and M. García, “An explainable deep-learning model reveals clinical clues in diabetic retinopathy through SHAP,” Biomed. Signal Process. Control, vol. 102, Apr. 2025, doi: 10.1016/j.bspc.2024.107328.