Polycystic Ovary Syndrome (PCOS) is a common endocrine disorder affecting reproductive-age women, characterized by a constellation of symptoms including irregular menstruation, hyperandrogenism, and ovarian cysts. Early and accurate detection of PCOS is crucial for effective management and prevention of associated health complications. Over the past few years, machine learning (ML) has gained prominence as a promising tool for diagnosing and predicting PCOS. Machine Learning methods such as Logistic Regression, Support Vector Machine, Naive Bayes, and Random Forest have notable benefits. This comprehensive review paper examines the current state of research on ML-based PCOS detection. Many machine learning techniques have been surveyed, including traditional supervised learning algorithms and deep learning model (CNN) that have been applied to PCOS detection using diverse datasets and features. Additionally, it delves into the challenges and limitations of these approaches, offering insights into future directions for improving PCOS detection through ML. By critically analyzing the current literature it aims to provide a comprehensive overview of PCOS detection using different machine learning algorithms.