Vol.15, No.3, August 2026.                                                                                                                                                                          ISSN: 2217-8309

                                                                                                                                                                                                                        eISSN: 2217-8333

TEM Journal

TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS

Association for Information Communication Technology Education and Science

Hybrid Multi-Method Explainable AI and Machine Learning for Early Prediction of High-Risk Pregnancies

Gusrino Yanto, Sari Puspita

© 2026 Mana Saleh Al Reshan, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)

Citation Information: TEM Journal. Volume 15, Issue 3, Pages 2218-2229, ISSN 2217-8309, DOI: 10.18421/TEM153-16, August 2026.

Received: 29 April 2025.
Revised: 02 March 2026.
Accepted: 10 March 2026.
Published: 27 August 2026.

Abstract:

High-risk pregnancies are the main reason for high maternal and infant mortality and morbidity rates. Efforts to detect these pregnancies early are essential to ensure timely and targeted medical interventions. The objective of this study is to develop a pregnancy risk prediction model that combines machine learning algorithms with a multi-method explainable artificial intelligence approach. Data was collected from five community health center in Koto Tangah District and then pre-processed with steps including cleaning, normalizing, and balancing the classes using the Synthetic Minority Over-sampling Technique method. Four algorithms were tested: Logistic Regression, Decision Tree, Support Vector Machine, and Random Forest. The experimental results showed that the Random Forest and Decision Tree algorithms achieved the highest accuracy, at 88% and 72%, respectively, while the Logistic Regression algorithm had the lowest accuracy, at 63%. Shapley Additive exPlanations, Local Interpretable Model-agnostic Explanations, and Permutation Feature Importance analyses confirmed systolic blood pressure, blood sugar, and diastolic blood pressure as the most influential features. Integrating Multi-Method Explainable Artificial Intelligence produced an accurate, transparent, and relevant model for supporting the early detection and prevention of maternal complication.

Keywords – High risk pregnancies, machine learning, multi-method XAI, maternal, Padang City.

-----------------------------------------------------------------------------------------------------------

Full text PDF >  

-----------------------------------------------------------------------------------------------------------