An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data

Aruna Pavate; Tanvi Sawant; Sangeeta Vhatkar

doi:10.31127/tuje.1846874

An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data

Abstract

Polycystic Ovary Syndrome (PCOS) is the most prevalent endocrine disorder affecting women of reproductive age, and there is a need for early and accurate diagnosis to prevent long-term reproductive and metabolic consequences. This work introduces a transparent ensemble model to predict PCOS at the individual level using everyday clinical, hormonal, metabolic, and lifestyle parameters. This work allows patient-based prediction, as this includes biologically plausible predictors such as serum testosterone, the luteinizing hormone to follicle-stimulating hormone ratio (LH/FSH), insulin, and menstrual irregularities. A scheme for data preprocessing, feature selection, model training, and testing is proposed. The performance of four classical classifiers, i.e., Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting (GB), is evaluated. Then, a voting-based ensemble method is proposed to enhance robustness and generalization. Results of experiments confirm good predictive performance, even for a significantly challenging task, with 96% accuracy and an ROC–AUC of 0.99, while decreasing false-negative rates is highly important for early screening. To add a layer of transparency and clinical trustworthiness, SHAP-based explainable artificial intelligence was adopted to evaluate global and patient-level feature importance. In addition to binary prediction, the proposed model reduces risk stratification to a probabilistic scale (low, moderate, high), making it more practical for clinical decision support. In conclusion, our proposed explainable ensemble framework presents a scalable, accurate, and interpretable decision support system for PCOS that is feasible to adopt in practical healthcare environments, especially in rural areas where medical resources are limited and more medical aids for the detection of such diseases are desperately needed. It has strong potential for integration into AI-enabled clinical screening systems.

Keywords

Supporting Institution

This research was supported by Thkur college of engineering and technology. The authors gratefully acknowledge the infrastructure, resources, and academic support provided during the completion of this study.

Ethical Statement

This study was based on a dataset that is publicly available from Kaggle. The dataset had been anonymized and contained no personal patient identifiers. As this study is a large-scale secondary data analysis and does not involve human subjects, it is exempt from seeking ethics approval and informed consent. All the methods were performed in accordance with the relevant guidelines and regulations.

References

Hosain, A. K. M. S., Mehedi, M. H. K., & Kabir, I. E. (2022). PCONet: A convolutional neural network architecture to detect polycystic ovary syndrome (PCOS) from ovarian ultrasound images. In Proceedings of the 8th International Conference on Engineering and Emerging Technologies (ICEET). Kuala Lumpur, Malaysia. doi: 10.1109/ICEET56468.2022.10007353.
Suha, S. A., & Islam, M. N. (2022). An extended machine learning technique for polycystic ovary syndrome detection using ovary ultrasound image. Scientific Reports, 12, 17123. https://doi.org/10.1038/s41598-022-21724-0.
Elmannai, H., El-Rashidy, N., Mashal, I., Alohali, M. A., Farag, S., El-Sappagh, S., & Saleh, H. (2023). Polycystic Ovary Syndrome Detection Machine Learning Model Based on Optimized Feature Selection and Explainable Artificial Intelligence. Diagnostics, 13(8), 1506. https://doi.org/10.3390/diagnostics13081506
Zad, Z., Jiang, V. S., Wolf, A. T., Wang, T., Cheng, J. J., Paschalidis, I. C., & Mahalingaiah, S. (2024). Predicting polycystic ovary syndrome with machine learning algorithms from electronic health records. Frontiers in Endocrinology, 15, 1298628. https://doi.org/10.3389/fendo.2024.1298628
Panjwani, B., Yadav, J., Mohan, V., Agarwal, N., & Agarwal, S. (2025). Optimized Machine Learning for the Early Detection of Polycystic Ovary Syndrome in Women. Sensors, 25(4), 1166. https://doi.org/10.3390/s25041166.
Reka, S., Praba, T. S., Prasanna, M., Reddy, V. N. N., & Amirtharajan, R. (2025). Automated high precision PCOS detection through a segment anything model on super resolution ultrasound ovary images. Scientific Reports, 15, 16832. https://doi.org/10.1038/s41598-025-01744-2
Li, M., He, Z., Shi, L., Lin, M., Li, M., Cheng, Y., Liu, H., Xue, L., Said, K. S., Yusuf, M., Galadanci, H. S., & Nie, L. (2025). Intelligent detection for polycystic ovary syndrome (PCOS): Taxonomy, datasets and detection tools. Computational and Structural Biotechnology Journal, 27, 1578–1599. https://doi.org/10.1016/j.csbj.2025.04.011
Shanmugavadivel, K., Dhar, M. S., Mahesh, T. R., Al-Shehari, T., Alsadhan, N. A., & Yimer, T. E. (2024). Optimized polycystic ovarian disease prognosis and classification using AI-based computational approaches on multi-modality data. BMC Medical Informatics and Decision Making, 24, 281. https://doi.org/10.1186/s12911-024-02688-9.

Wang, C.-Y., Pei, D., Wang, C.-K., Ke, J.-C., Lee, S.-T., Chu, T.-W., & Liang, Y.-J. (2025). Using machine learning to predict patients with polycystic ovary disease in Chinese women. Taiwanese Journal of Obstetrics and Gynecology, 64(1), 68–75. https://doi.org/10.1016/j.tjog.2024.09.019.
Zhu, Y., Luo, D., Shen, X., et al. (2025). Application of ChatGPT-based artificial intelligence in the diagnosis and management of polycystic ovary syndrome. BMC Medical Informatics and Decision Making, 25, 271. https://doi.org/10.1186/s12911-025-03114-4
Faris, N., Sahi, A., Diykh, M., Abdulla, S., & Siuly, S. (2025). Enhanced Polycystic Ovary Syndrome diagnosis model leveraging a K-means based genetic algorithm and ensemble approach. Intelligence-Based Medicine, 11, 100253. https://doi.org/10.1016/j.ibmed.2025.100253
Pulluparambil, S. J., & Bhat, S. (2021). Medical image processing: Detection and prediction of PCOS – A systematic literature review. International Journal of Health Sciences and Pharmacy, 5(2), 80–98. https://doi.org/10.47992/IJHSP.2581.6411.0075
Emara, H. M., El-Shafai, W., Soliman, N. F., Algarni, A. D., Alkanhel, R., & Abd El-Samie, F. E. (2025). A stacked learning framework for accurate classification of polycystic ovary syndrome with advanced data balancing and feature selection techniques. Frontiers in Physiology, 16, Article 1435036. https://doi.org/10.3389/fphys.2025.1435036
Uddin, K. M. M., Bhuiyan, M. T. A., Rahman, M. M., Islam, M. M., & Uddin, M. A. (2025). Early PCOS detection: A comparative analysis of traditional and ensemble machine learning models with advanced feature selection. Engineering Reports, 7(2). https://doi.org/10.1002/eng2.70008.
Thakre, V. S., Vedpathak, S., Thakre, K., & Sonawani, S. (2020). PCOcare: PCOS detection and prediction using machine learning algorithms. Bioscience Biotechnology Research Communications, 13(14), 240–244. https://doi.org/10.21786/bbrc/13.14/56.
Koçak, S. (2021). PCOS animal models: An approach induced by dehydroepiandrosterone. Gaziantep Islam Science and Technology University, 2(1), 136–145. https://doi.org/10.46871/eams.2021.17.
Başpınar, O., Şimşek, Y., Koçer, D., Dizdar, O. S., & Kayış Topaloğlu, H. (2022). Does serum R-Spondin-1 play a role in PCOS pathophysiology? Genel Tıp Dergisi, 32(5), 490–493. https://doi.org/10.54005/geneltip.1111079.
Dokuzeylül Güngör, N., Çelik, S., Güçlü, M., Çelik, S., & Cengiz, F. (2021). Evaluation of metabolic and hormonal parameters in women with PCOS living in Black Sea Region. Journal of Experimental and Clinical Medicine, 38(3), 235–240. https://doi.org/10.52142/omujecm.38.3.5.
Yaşar, Ş. (2025). Machine learning-driven metabolomic biomarker discovery for PCOS: An interpretable approach using Random Forest and SHAP. Medical Records-International Medical Journal, 7(3), 763–767. https://doi.org/10.37990/medr.1718952.
Pavate, A., & Ansari, N. (2015). Risk prediction of disease complications in type 2 diabetes patients using soft computing techniques. In Proceedings of the Fifth International Conference on Advances in Computing and Communications (ICACC) (pp. 371–375).
Pavate, A., et al. (2020). Diabetic retinopathy detection-MobileNet binary classifier. Acta Scientific Medical Sciences, 4(12), 86–91.
Dirik, M. (2023). Machine learning-based lung cancer diagnosis. Turkish Journal of Engineering, 7(4), 322-330. https://doi.org/10.31127/tuje.1180931
Maza, D., Ojo, J. O., & Akinlade, G. O. (2024). A predictive machine learning framework for diabetes. Turkish Journal of Engineering, 8(3), 583-592. https://doi.org/10.31127/tuje.1434305
Başarslan, M. S., & Kayaalp, F. (2024). Sentiment analysis of coronavirus data with ensemble and machine learning methods. Turkish Journal of Engineering, 8(2), 175-185. https://doi.org/10.31127/tuje.1352481
Sade, J. (2025). Predicting fetal health using ANFIS: A comparative study with machine learning models. Turkish Journal of Engineering, 10(1), 187-196. https://doi.org/10.31127/tuje.1711661
Polater, S. N., & Sevli, O. (2024). Deep learning based classification for alzheimer’s disease detection using MRI images. Turkish Journal of Engineering, 8(4), 729-740. https://doi.org/10.31127/tuje.1434866
Koca, Y. B., & Aktepe, E. (2024). Effect of dimension reduction with PCA and machine learning algorithms on diabetes diagnosis performance. Turkish Journal of Engineering, 8(3), 447-456. https://doi.org/10.31127/tuje.1413087

Details

Primary Language

English

Subjects

Information Systems (Other)

Journal Section

Research Article

Authors

Aruna Pavate ^*
0000-0002-3387-0905
India

Tanvi Sawant
0009-0001-4500-0472
India

Sangeeta Vhatkar
0000-0002-3956-4597
India

Publication Date

July 6, 2026

Submission Date

December 24, 2025

Acceptance Date

March 4, 2026

Published in Issue

Year 2026 Volume: 10 Number: 3

DOI

https://doi.org/10.31127/tuje.1846874

IZ

https://izlik.org/JA67CT47ZX

Cite

RIS / Bibtex

APA

Pavate, A., Sawant, T., & Vhatkar, S. (2026). An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data. Turkish Journal of Engineering, 10(3), 864-874. https://doi.org/10.31127/tuje.1846874

AMA

1.Pavate A, Sawant T, Vhatkar S. An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data. TUJE. 2026;10(3):864-874. doi:10.31127/tuje.1846874

Chicago

Pavate, Aruna, Tanvi Sawant, and Sangeeta Vhatkar. 2026. “An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data”. Turkish Journal of Engineering 10 (3): 864-74. https://doi.org/10.31127/tuje.1846874.

EndNote

Pavate A, Sawant T, Vhatkar S (July 1, 2026) An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data. Turkish Journal of Engineering 10 3 864–874.

IEEE

[1]A. Pavate, T. Sawant, and S. Vhatkar, “An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data”, TUJE, vol. 10, no. 3, pp. 864–874, July 2026, doi: 10.31127/tuje.1846874.

ISNAD

Pavate, Aruna - Sawant, Tanvi - Vhatkar, Sangeeta. “An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data”. Turkish Journal of Engineering 10/3 (July 1, 2026): 864-874. https://doi.org/10.31127/tuje.1846874.

JAMA

1.Pavate A, Sawant T, Vhatkar S. An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data. TUJE. 2026;10:864–874.

MLA

Pavate, Aruna, et al. “An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data”. Turkish Journal of Engineering, vol. 10, no. 3, July 2026, pp. 864-7, doi:10.31127/tuje.1846874.

Vancouver

1.Aruna Pavate, Tanvi Sawant, Sangeeta Vhatkar. An Explainable Ensemble Machine Learning Framework for PCOS Risk Prediction Using Clinical and Hormonal Data. TUJE. 2026 Jul. 1;10(3):864-7. doi:10.31127/tuje.1846874