Phenotype-Specific Lifestyle Prediction for PCOS Using Machine Learning Multi-Class Classification and SHAP Explainability

May 2026 in “ International Journal of Drug Delivery Technology ”

Sudhir Kumar Sharma, Aung Nyein Chan Paing

Studysummary This study reports that using machine learning models, particularly XGBoost and Random Forest, can accurately predict PCOS phenotypes based on non-invasive data, with cycle length as the most significant predictor.

Automatically generated from the study's abstract, not written by a person, and not a review of the full paper. Not medical advice or a treatment recommendation. Read the original study, and consult a qualified healthcare professional before changing treatment. Full disclaimer ·

View this study on doi.org →

Discuss this study in the Community →

Similar Research

5 / 1000+ results

research A Data-Driven Approach to Polycystic Ovary Syndrome Diagnosis: Evaluating Machine Learning Models

July 2025

This study found that using machine learning models, particularly Random Forest with 93% accuracy and 86% sensitivity, can effectively predict PCOS by analyzing features like antral follicle count, hair growth, and skin pigmentation, offering a promising alternative to traditional diagnostic methods.

Optimized Polycystic Ovarian Disease Prognosis and Classification Using AI-Based Computational Approaches on Multi-Modality Data

research Optimized polycystic ovarian disease prognosis and classification using AI based computational approaches on multi-modality data

19 citations , October 2024 in “BMC Medical Informatics and Decision Making”

This study used machine learning models to analyze PCOS symptoms for early diagnosis, finding Support Vector Machine and VGG16 algorithms achieved high accuracy rates of 94.44% and 98.29% respectively.

research Machine learning-based steroid metabolome analysis reveals three distinct subtypes of polycystic ovary syndrome and implicates 11-oxygenated androgens as major drivers of metabolic risk

3 citations , May 2023 in “Endocrine Abstracts”

This study identified three subgroups of women with PCOS with distinct androgen profiles, finding that the subgroup with adrenal-derived androgen excess had the highest insulin resistance and rates of hirsutism and hair loss.

Predicting Polycystic Ovary Syndrome Among Reproductive-Aged Women in Bangladesh Using Machine Learning Algorithms: Development of a Hospital-Based Predictive Model

research Predicting Polycystic Ovary Syndrome among Reproductive-Aged Women in Bangladesh Using Machine Learning Algorithms: Development of a Hospital-Based Predictive Model

November 2025

This study evaluated machine-learning models to predict PCOS among reproductive-aged women in Bangladesh, finding that the XGBoost model achieved high accuracy (99.63%) and effectiveness, particularly when prioritizing clinical features over psychological ones in the predictive process.

research A machine learning approach for non-invasive PCOS diagnosis from ultrasound and clinical features

6 citations , September 2025 in “Scientific Reports”

This study found that using XGBoost with clinical and ultrasound features may provide a highly accurate, non-invasive method for diagnosing polycystic ovary syndrome, although further validation is needed to ensure robustness.