Machine Learning Approaches on Diagnosis of Polycystic Ovary Syndrome

• Author(s): Akash Dongare ; Mahesh Karande ; Sanket Ghondge ; Prajkta Vishe
• Paper ID: 1707870
• Page: 501-509
• Published Date: 14-04-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 8 Issue 10 April-2025

Abstract

PCOS is a complex hormonal condition that affects women who are of reproductive age. It is characterized by ovarian dysfunction and irregular menstrual cycles. For effective intervention and care to address possible hazards such infertility, metabolic syndrome, and cardiovascular consequences, timely detection and accurate diagnosis of PCOS are essential. Machine learning methods have emerged as useful instruments for evaluating intricate medical data and supporting the diagnosis and prognosis of illnesses in recent years. With an emphasis on predictive modeling and diagnostic accuracy, this paper examines the use of machine learning techniques in PCOS research. Data pertaining to PCOS, including clinical, hormonal, and imaging features, has been analyzed using a variety of machine learning techniques, such as logistic regression, SVM, random forests, neural networks, and ensemble approaches. To improve model performance and interpretability, feature selection strategies and data preprocessing approaches have also been applied. Potential remedies are explored for issues such class imbalance, data heterogeneity, and model interpretability. Additionally, there is potential for better PCOS diagnosis, risk assessment, and individualized treatment plans through the integration of multimodal data sources and the creation of interpretable machine learning models. Additionally mentioned are potential avenues for translational application of ML-based methods in clinical practice as well as future research directions.

Keywords

Machine Learning, SVM, RF, Decision Tree, Naive Bayes, CNN, Polycystic Ovary Syndrome (PCOS).

Citations

IRE Journals:
Akash Dongare , Mahesh Karande , Sanket Ghondge , Prajkta Vishe "Machine Learning Approaches on Diagnosis of Polycystic Ovary Syndrome" Iconic Research And Engineering Journals Volume 8 Issue 10 2025 Page 501-509

IEEE:
Akash Dongare , Mahesh Karande , Sanket Ghondge , Prajkta Vishe "Machine Learning Approaches on Diagnosis of Polycystic Ovary Syndrome" Iconic Research And Engineering Journals, 8(10)