Leveraging Machine Learning to Detect and Predict Diabetes in Polycystic Ovary Syndrome Patients: A Review

Abstract

Polycystic ovary syndrome (PCOS) is a prevailing hormonal disorder affecting women in their childbearing years, often associated with hormonal imbalances and metabolic disturbances. PCOS is closely linked to various health complications, including Type 2 Diabetes Mellitus (T2DM). Early detection and prediction of T2DM among PCDS patients are essential steps in providing comprehensive care to mitigate the potential adverse effects that PCOS has on its sufferers, such as infertility. Extensive research has been conducted to leverage advanced tools, particularly Machine Learning (ML) algorithms, for detecting and predicting PCOS and diabetes. This review explores the efforts to address the intersection of PCOS and diabetes, specifically focusing on ML-based approaches. Through a thorough examination of recent literature, this paper reveals all ML algorithms, methodologies and datasets that apply to detecting and predicting T2DM among PCOS patients. This paper further aims to discover and discuss possible challenges and limitations in leveraging ML in addressing the intersection of PCOS and T2DM and the future directions of ML as far as personalised healthcare interventions targeting PCOS patients at risk of T2DM are concerned.