Diagnosis of Polycystic Ovary Syndrome (PCOS) using Deep Learning and Classification Technique’s

TLDR

A novel approach for diagnosis of PCOS using deep learning & classification techniques and analysis of various machine learning algorithms like svm, naïve Bayes, random forest and decision tree & deep neural network architecture for identification of PCOS based on clinical and biochemical features is proposed.

Abstract

Polycystic Ovary Syndrome (PCOS) is a disorder which affects women worldwide. One can know whether she is affected by PCOS that is it is characterized by irregular menstrual cycles, high blood pressure, obesity, fatigueness, etc. Timely Diagnosis of PCOS is very crucial for effectively managing and preventing associated complications. The advancements in artificial intelligence shows promise in diagnosis of medical tasks. In this paper we propose a novel approach for diagnosis of PCOS using deep learning & classification techniques. We provide analysis of various machine learning algorithms like svm, naïve Bayes, random forest and decision tree & deep neural network architecture for identification of PCOS based on clinical and biochemical features. Our results are mostly useful for the medical experts which helps them by reducing the diagnostic delays caused thereby providing an improved patient care and management. Keywords: Polycystic ovary syndrome, deep learning, classification techniques, healthcare, PCOS diagnosis.