Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207248,
        author = {Aradhya Mishra and Kanishka Gupta and Pawan Tiwari and Deepali Mishra},
        title = {Predicting PCOS Severity Based on Lifestyle Factors Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {130-135},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207248},
        abstract = {Polycystic Ovary Syndrome (PCOS) is the most common endocrine disorder among reproductive-age women, affecting 8–13% globally, yet nearly 70% remain undiagnosed. Existing machine learning (ML) models mainly use clinical and hormonal biomarkers while overlooking lifestyle factors such as diet, physical activity, sleep, and stress that influence disease severity. This study proposes a lifestyle-integrated ensemble ML framework for continuous PCOS risk prediction and severity stratification. Using the Kaggle PCOS dataset of 541 patients from 10 hospitals in Kerala, India, lifestyle survey features were added. Seven classifiers, including Logistic Regression, SVM, Random Forest, Gradient Boosting, XGBoost, CatBoost, and a Voting Ensemble, were evaluated using stratified five-fold cross-validation, SMOTE balancing, and GridSearchCV tuning. The Voting Ensemble achieved the highest AUC of 0.941, while XGBoost attained 89.9% accuracy. SHAP analysis identified fast food consumption as a major predictor, highlighting the importance of lifestyle-aware, interpretable PCOS risk assessment.},
        keywords = {CatBoost, clinical decision support, machine learning, PCOS, risk stratification, severity prediction, SHAP, SMOTE, Voting Ensemble, XGBoost},
        month = {July},
        }