Enhanced Diagnosis of Polycystic Ovarian Syndrome Using ‎Stacking Classifier with Random Forest As a Meta Learner

  • Authors

    • Pragati Patil Research Scholar, Drs. Kiran and Pallavi Patel Global University, Vadodara, INDIA
    • Nandini Chaudhari Director, Krishna School of Emerging Technology and Applied Research, Drs. Kiran and Pallavi Patel Global University, Vadodara, INDIA
    https://doi.org/10.14419/36w9s378

    Received date: October 28, 2025

    Accepted date: November 27, 2025

    Published date: December 4, 2025

  • Polycystic Ovary Syndrome (PCOS); Machine Learning; Ensemble Methods; Feature Selection; Diagnostic Accuracy.

  • Abstract

    Polycystic Ovary Syndrome (PCOS) is considered a very serious health problem among the women of childbirth age. Early and accurate ‎detection is essential for effective management but remains challenging due to symptom variability and subjective traditional diagnostics. ‎Machine learning (ML) algorithms have recently emerged as promising tools for PCOS diagnosis by analyzing multidimensional clinical, ‎hormonal, and imaging data. This study evaluates and compares multiple supervised ML methods—including Gradient Boosting (XGBoost, ‎LightGBM, and CatBoost), AdaBoost, Logistic Regression, Naive Bayes, Random Forest, Decision Tree, Support Vector Machine (SVM), ‎and Stacking classifiers—on a publicly available dataset of 541 patients. Various evaluation measures like Receiver Operating Characteristic ‎curve (AUC-ROC), recall, accuracy, F1-score, and precision are used for the evaluation. Stacking classifier outperforms all single models ‎used in this research. The Stacking classifier with Random Forest as meta-learner achieved 98% accuracy with AUC of 98%. These find‎ings demonstrate that advanced ensemble ML models can robustly detect PCOS, with potential for integration into clinical workflows for ‎early, objective diagnosis. Future work should focus on multi-center validation and explainable AI to enhance clinical trust and deployment‎.

  • References

    1. Lizneva, D., Suturina, L., Walker, W., et al. (2016). Criteria, prevalence, and phenotypes of polycystic ovary syndrome. Fertility and Sterility, 106(1), 6-15. https://doi.org/10.1016/j.fertnstert.2016.05.003.
    2. Azziz, R., Carmina, E., Dewailly, D., et al. (2016). The Androgen Excess and PCOS Society criteria for PCOS diagnosis: The complete task force report. Fertility and Sterility, 91(2), 456-488. https://doi.org/10.1016/j.fertnstert.2008.06.035.
    3. Rotterdam ESHRE/ASRM-Sponsored PCOS Consensus Workshop Group. (2004). Revised 2003 consensus on diagnostic criteria and long-term health risks related to PCOS. Human Reproduction, 19(1), 41-47. https://doi.org/10.1093/humrep/deh098.
    4. Das, S., Ganapathy, S., & Aruna, S. (2023). Machine learning approaches for early diagnosis of PCOS using clinical and hormonal data. Computers in Biology and Medicine, 150, 106234.
    5. Sharma, N., & Verma, P. (2024). Comparative study of supervised learning algorithms for detecting PCOS. Frontiers in Endocrinology, 15, 1017850.
    6. Patil, V., & Koli, H. (2025). Application of XGBoost and Random Forest classifiers for PCOS prediction: A feature selection approach. Biomedical Signal Processing and Control, 79, 103934.
    7. Choudhary, S., & Singh, M. (2024). Stacking ensemble methods for enhanced PCOS detection using multi-modal datasets. Journal of Medical Systems, 48(1), 25.
    8. V. V. Khanna, K. Chadaga, N. Sampathila, S. Prabhu, V. Bhandage, and G. K. Hegde, “A Distinctive Explainable Machine Learning Framework for Detection of Polycystic Ovary Syndrome,” Applied System Innovation, vol. 6, no. 2, p. 32, 2023. https://doi.org/10.3390/asi6020032.
    9. H. Elmannai, A. Ahmad, M. M. A. Khan, R. N. Awad, and A. B. Alshahrani, “Polycystic Ovary Syndrome Detection Machine Learning Model Based on Optimized Feature Selection and Explainable Artificial Intelligence,” Diagnostics, vol. 13, no. 8, p. 1506, Apr. 2023. https://doi.org/10.3390/diagnostics13081506.
    10. Panjwani, J. Yadav, V. Mohan, N. Agarwal, and S. Agarwal, “Optimized Machine Learning for the Early Detection of Polycystic Ovary Syndrome in Women,” Sensors, vol. 25, no. 4, p. 1166, Feb. 2025. https://doi.org/10.3390/s25041166.
    11. K. M. S. Hosain, M. Rahman, and T. D. Nguyen, “PCONet: A deep learning model for detection of polycystic ovary syndrome using ultrasound images,” arXiv preprint, arXiv:2210.00407, Oct. 2022.
    12. W. Lv, X. Sun, C. Wang, et al., “Deep Learning Algorithm for Automated Detection of Polycystic Ovary Syndrome Using Scleral Images,” Frontiers in Endocrinology, vol. 13, p. 789878, 2022. https://doi.org/10.3389/fendo.2021.789878.
    13. M. Mohi Uddin, M. Hussain, and K. Islam, “Polycystic Ovary Syndrome Diagnosis Using an Enhanced Machine Learning Framework with Mutual Information and Optimized Feature Selection,” Engineering Reports, 2025. https://doi.org/10.1002/eng2.70008.
    14. M. Rahman, A. Parvin, and R. Akter, “A Machine Learning-Based Clinical Decision Support System for Early Diagnosis of PCOS,” Engineering Reports, 2024.
    15. P. Bharati, D. Bhoi, and D. Nayak, “Hybrid Machine Learning Approaches for Early Detection of PCOS Using Logistic Regression and Feature Selection,” Engineering Reports, 2024.
    16. F. Zigarelli, L. Costa, and A. Della Corte, “Clinical Screening of PCOS Using CatBoost and Feature Engineering,” Engineering Reports, 2023.
    17. M. Danaei Mehr and H. Polat, “Improved PCOS Detection Using Ensemble of Random Forest, Extra Trees, and AdaBoost,” Engineering Reports, 2024.
    18. M. Zad, A. Radin, and F. Miller, “Predicting PCOS Diagnoses in a Large Healthcare System Using Machine Learning on Electronic Health Records,” Engineering Reports, 2024.
    19. H. Elmannai, A. Ahmad, and M. A. Khan, “Explainable AI and Web-Based Interface for PCOS Diagnosis,” Diagnostics, vol. 14, no. 4, p. 2225, 2024. https://doi.org/10.3390/diagnostics14192225.
    20. Divekar and S. Sonawane, “AUTO-PCOS: Transfer Learning and Explainable AI for Automated Detection of Polycystic Ovary Syndrome from Ultrasound Images,” arXiv preprint, arXiv:2501.01984, 2024.
    21. J. Morris, C. Lee, and F. Gomez, “Federated Learning for Secure PCOS Detection Using Distributed Medical Data,” arXiv preprint, arXiv:2308.11220, 2023.
    22. S. Silva, C. Reis, and R. Barros, “PCOS Classification Using BorutaShap and Random Forests on Small-Sample Datasets,” Engineering Reports, 2023.
    23. Prasher, S., Nelson, L., Sharma, A. (2023). Evaluation of Machine Learning Techniques to Diagnose Polycystic Ovary Syndrome Using Kaggle Dataset. In: Rathore, V.S., Piuri, V., Babo, R., Ferreira, M.C. (eds) Emerging Trends in Expert Applications and Security. ICETEAS 2023. Lecture Notes in Networks and Systems, vol 682. Springer, Singapore. https://doi.org/10.1007/978-981-99-1946-8_25.
    24. Z. Zahra, J.S. Victoria, W.T. Amber, W. Taiyao , C. J. Jojo, P. Ioannis, M. Shruthi, "Predicting polycystic ovary syndrome with machine learning algorithms from electronic health records," Frontiers in Endocrinology, vol. 15, 2024, https://doi.org/10.3389/fendo.2024.1298628.
    25. Kaur, N., Gupta, G., Hafiz, A., Sharma, M., Singh, J. (2023). Machine Learning Algorithms for Polycystic Ovary Syndrome/Polycystic Ovarian Syndrome Detection: A Comparison. In: Shukla, P.K., Mittal, H., Engelbrecht, A. (eds) Computer Vision and Robotics. CVR 2023. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-99-4577-1_37.
    26. N. Yadav, R. K. A, and S. D. Pande, “Comparative Analysis of Polycystic Ovary Syndrome Detection Using Machine Learning Algorithms”, EAI Endorsed Trans Perv Health Tech, vol. 10, Mar. 2024. https://doi.org/10.4108/eetpht.10.5552.
    27. Elmannai, H., El-Rashidy, N., Mashal, I., Alohali, M. A., Farag, S., El-Sappagh, S., & Saleh, H. ,"Polycystic Ovary Syndrome Detection Machine Learning Model Based on Optimized Feature Selection and Explainable Artificial Intelligence," Diagnostics, vol 13, no 2, 2023 1506. https://doi.org/10.3390/diagnostics13081506.
    28. S. A. Suha and M. N. Islam, “Exploring the dominant features and data driven detection of Polycystic Ovary Syndrome through modified stacking ensemble machine learning technique,” Heliyon, vol. 9, no. 3, 2023. https://doi.org/10.1016/j.heliyon.2023.e14518.
    29. Emara HM, El-Shafai W, Soliman NF, Algarni AD, Alkanhel R and Abd El-Samie FE (2025) A stacked learning framework for accurate classification of polycystic ovary syndrome with advanced data balancing and feature selection techniques. Front. Physiol. 16:1435036. https://doi.org/10.3389/fphys.2025.1435036.
    30. Mohi Uddin, K.M., Bhuiyan, M.T.A., Rahman, M.M., Islam, M.M. and Uddin, M.A. (2025), Early PCOS Detection: A Comparative Analysis of Traditional and Ensemble Machine Learning Models with Advanced Feature Selection. Engineering Reports, 7: e70008. https://doi.org/10.1002/eng2.70008.
    31. S. Alshakrani, S. Hilal and A. M. Zeki, "Hybrid Machine Learning Algorithms for Polycystic Ovary Syndrome Detection," 2022 International Conference on Data Analytics for Business and Industry (ICDABI), Sakhir, Bahrain, 2022, pp. 160-164, https://doi.org/10.1109/ICDABI56818.2022.10041525.
    32. Z. Vairachilai et al., “SMOTE logistic blending hybrid machine learning model for chronic polycystic ovary syndrome prediction with correlated feature selection,” Inform Health Soc Care, Oct. 2024. https://doi.org/10.1080/17538157.2024.2405868.
    33. G, Umaa Mahesswari et al.," SmartScanPCOS: A feature-driven approach to cutting-edge prediction of Polycystic Ovary Syndrome using Machine Learning and Explainable Artificial Intelligence," Heliyon, Volume 10, Issue 20, Oct. 2024. https://doi.org/10.1016/j.heliyon.2024.e39205

  • Downloads

  • How to Cite

    Patil, P., & Chaudhari, N. (2025). Enhanced Diagnosis of Polycystic Ovarian Syndrome Using ‎Stacking Classifier with Random Forest As a Meta Learner. International Journal of Basic and Applied Sciences, 14(8), 97-105. https://doi.org/10.14419/36w9s378