INTERPRETABLE ENSEMBLE FRAMEWORK FOR PCOS RISK PREDICTION WITH SHAP AND LIME-BASED EXPLAINABILITY
Open Access
- 12 August 2026
- journal article
- Published by University of Nigeria in Nigerian Journal of Technology
- Vol. 45 (3)
Abstract
Polycystic Ovary Syndrome (PCOS) affects an estimated one in ten women of reproductive age and presents with a heterogeneous range of metabolic, endocrine, and reproductive symptoms, complicating consistent clinical diagnosis. Methodology: Two related PCOS datasets (2,000 and 541 samples) were cleaned and combined for model training and external validation. Recursive Feature Elimination with Cross-Validation was used for feature selection, and class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE), applied within each cross-validation fold to avoid data leakage. Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), and a soft-voting ensemble of the three were trained and evaluated using accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC, with statistical significance assessed via McNemar's test. Results: On the external test set, SVM, RF, and the ensemble achieved comparable accuracy (96.7-97.2%), all significantly outperforming LR (90.5%; p < 0.0001), with no significant difference among the three (p > 0.05). SHAP and LIME were applied for global and local interpretability, identifying follicle count, weight gain, skin darkening, and hormonal markers (AMH, cycle regularity) as leading predictors, though follicle count's dominance also raises a diagnostic-circularity concern given its role as a clinical diagnostic criterion. Conclusion: This framework demonstrates that ensemble and tree-based models substantially outperform linear baselines for PCOS risk prediction, with the ensemble offering comparable predictive performance alongside interpretable, dual-level explanations. These findings contribute toward more transparent and clinically trustworthy machine learning tools for PCOS diagnosis support.Keywords
This publication has 32 references indexed in Scilit:
- Improving diagnostic accuracy for PCOS: A hybrid machine learning architecture with feature selection, data balancing, and explainable AI techniquesResults in Control and Optimization, 2025
- Explainable AI for Generalizable PCOS Diagnosis: A Geographically Validated Ensemble Learning Approach With Feature SelectionEngineering Reports, 2025
- The last update on polycystic ovary syndrome(PCOS), diagnosis criteria, and novel treatmentEndocrine and Metabolic Science, 2025
- Opening the black box: challenges and opportunities regarding interpretability of artificial intelligence in emergency medicineCanadian Journal of Emergency Medicine, 2025
- Machine Learning Applications in the Prediction of Polycystic Ovarian Syndrome2025
- Empowering early detection: A web-based machine learning approach for PCOS predictionInformatics in Medicine Unlocked, 2024
- Early identification of PCOS with commonly known diseases: Obesity, diabetes, high blood pressure and heart disease using machine learning techniquesExpert Systems with Applications, 2023
- Lifestyle interventions in women with polycystic ovary syndrome: A scoping systematic review of randomised evidenceMedicina de Familia. SEMERGEN, 2022
- Diagnosis of Polycystic Ovary SyndromeEndocrinology and Metabolism Clinics of North America, 2021
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020