<![CDATA[Polycystic Ovary Syndrome (PCOS) is a common hormonal disorder among women of reproductive age, often leading to menstrual irregularities, infertility, and metabolic issues. Diagnosing PCOS remains challenging due to the wide range of symptoms and varying patient responses to treatment. Therefore, this study aims to apply artificial intelligence (AI) to identify key symptoms contributing to PCOS based on patients' clinical data.This study employs a machine learning approach, with the Support Vector Machine (SVM) algorithm as the primary method for classifying patients with and without PCOS. The data used was sourced from patient medical records, which included clinical data parameters obtained from the Kaggle website, with a total of 541 patient data samples. The research stages include data collection and preprocessing, selection of main features using feature selection technique, model training with SVM algorithm. The AI model developed produces 10 main features that affect the diagnosis with an accuracy value of 90.74% which shows that the model has the ability to classify PCOS and non-PCOS sufferers. In addition, the matrix shows a balance between the matrix values for precision 87.5%, recall 82.35% and F1 score 84.85%. The results of this study are expected to contribute to the medical field, especially in supporting faster and more accurate early diagnosis and personalization of PCOS treatment.]]>
Copyrights © 2025
