IRO Journals
Journal of Ubiquitous Computing and Communication Technologies

XGBoost-Driven PCOS Prediction Using Multidimensional Clinical, Hormonal, and Lifestyle Features

Open Access
Published: 14 October, 2026
Pages: 326-338
  • Gourika J Sreenivas , Gourika J Sreenivas
    Student, Department of Computing Technologies, SRM Institute of Science and Technology, Chennai, India
    Student, Department of Computing Technologies, SRM Institute of Science and Technology, Chennai, India
  • Riya K P. , Riya K P.
    Student, Department of Computing Technologies, SRM Institute of Science and Technology, Chennai, India
    Student, Department of Computing Technologies, SRM Institute of Science and Technology, Chennai, India
  • Yamini R. Yamini R.
    Associate Professor, Department of Computing Technologies, SRM Institute of Science and Technology, Chennai, India
    Associate Professor, Department of Computing Technologies, SRM Institute of Science and Technology, Chennai, India
view PDF
view PDF

How to Cite

Sreenivas, Gourika J, Riya K P., and Yamini R. 2026. “XGBoost-Driven PCOS Prediction Using Multidimensional Clinical, Hormonal, and Lifestyle Features”. Journal of Ubiquitous Computing and Communication Technologies 8 (4): 326-38. https://doi.org/10.36548/jucct.2026.4.002.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Polycystic Ovary Syndrome (PCOS)
Hormonal Feature Analysis
Lifestyle-Based Prediction
Extreme Gradient Boosting
Stratified Cross-Validation
Explainable Prediction
Probability-Based Risk Assessment

Abstract

Polycystic Ovary Syndrome (PCOS) is an endocrine-metabolic disease caused by various hormonal, clinical and lifestyle aspects, thus making its early prediction difficult. This research proposes an efficient predictive framework to classify PCOS by employing Machine Learning (ML) models that are trained with a dataset of 541 patient records with clinical, hormonal, physical, reproductive, lifestyle and other associated health characteristics. Four different supervised learning approaches such as Logistic Regression, Support Vector Machine, Random Forest, and Extreme Gradient Boosting (XGBoost) are compared based on the stratified five-fold cross validation process. The performance of the proposed model is evaluated in terms of accuracy, precision, recall, F1-score, and ROC-AUC. The highest performance is exhibited by the XGBoost model with an accuracy of 89.81%, precision of 93.10%, recall of 75.00%, and F1-Score of 83.08%, whereas the Random Forest attains highest ROC-AUC of 96.62%.

References

  1. Tiwari, Shamik, Lalit Kane, Deepika Koundal, Anurag Jain, Adi Alhudhaif, Kemal Polat, Atef Zaguia, Fayadh Alenezi, and Sara A. Althubiti. "SPOSDS: A Smart PCOSdiagnostic System using Machine Learning." Expert Systems with Applications, 2022, vol. 203: 117592.
  2. Zigarelli, Angela, Ziyang Jia, and Hyunsun Lee. "Machine-Aided Self-Diagnostic Prediction Models for Polycystic Ovary Syndrome: Observational Study." JMIR Formative Research, 2022, vol. 6, no. 3: e29967.
  3. Elmannai, Hela, Nora El-Rashidy, Ibrahim Mashal, Manal Abdullah Alohali, Sara Farag, Shaker El-Sappagh, and Hager Saleh. "PCOSdetection Machine Learning Model based on Optimized Feature Selection and Explainable Artificial Intelligence." Diagnostics, 2023, vol. 13, no. 8: 1506.
  4. Suha, Sayma Alam, and Muhammad Nazrul Islam. "Exploring the Dominant Features and Data-Driven Detection of PCOSthrough Modified Stacking Ensemble Machine Learning Technique." Heliyon, 2023, vol. 9, no. 3: e14518.
  5. Zad, Zahra, Victoria S. Jiang, Amber T. Wolf, Taiyao Wang, J. Jojo Cheng, Ioannis Ch Paschalidis, and Shruthi Mahalingaiah. "Predicting PCOSwith Machine Learning Algorithms from Electronic Health Records." Frontiers in Endocrinology, 2024, vol. 15: 1298628.
  6. Rahman, Md Mahbubur, Ashikul Islam, Forhadul Islam, Mashruba Zaman, Md Rafiul Islam, Md Shahriar Alam Sakib, and Hafiz Md Hasan Babu. "Empowering Early Detection: A Web-based Machine Learning Approach for PCOS Prediction." Informatics in Medicine Unlocked, 2024, vol. 47: 101500.
  7. Ahmad, Rumman, Lamees A. Maghrabi, Ishfaq Ahmad Khaja, Louai A. Maghrabi, and Musheer Ahmad. "SMOTE-based Automated PCOS Prediction using Lightweight Deep Learning Models." Diagnostics, 2024, vol. 14, no. 19: 2225.
  8. Tong, Cheng, Yue Wu, Zhenchao Zhuang, and Ying Yu. "A Diagnostic Model for PCOSbased on Machine Learning." Scientific Reports, 2025, vol. 15, no. 1: 9821.
  9. Agirsoy, Mehtap, and Matthew A. Oehlschlaeger. "A Machine Learning Approach for Non-Invasive PCOS Diagnosis from Ultrasound and Clinical Features." Scientific Reports, 2025, vol. 15, no. 1: 33638.
  10. Acharya, Sachin, Satyanarayana Poojari, and Asha Kamath. "Prediction of PCOSusing Machine Learning Models: Addressing Class Imbalance and High Dimensionality." Journal of Education and Health Promotion, 2026, vol. 15: 174.
  11. Kottarathil, Prasoon. PCOS(PCOS). Kaggle Dataset, 2020. Available: https://www.kaggle.com/datasets/prasoonkottarathil/polycystic-ovary-syndrome-pcos