Open AccessA MACHINE LEARNING APPROACH FOR SELECTION OF POLYCYSTIC OVARIAN SYNDROME (PCOS) ATTRIBUTES AND COMPARING DIFFERENT CLASSIFIER PERFORMANCE WITH THE HELP OF WEKAAND PYCARET
Author(s) -
Ashok Munjal,
Rekha Khandia,
Brijraj Gautam
Publication year - 2020
Publication title -
international journal of scientific research
Language(s) - English
DOI - 10.36106/ijsr/5416514
Subject(s) - machine learning , confusion matrix , artificial intelligence , classifier (uml) , confusion , disease , polycystic ovary , computer science , polycystic ovarian disease , medical history , medicine , pathology , psychology , insulin resistance , psychoanalysis , obesity
For any medical treatment there is a requirement of identification of features those are affecting the clinical condition the most. These are the parameters which decide the line of treatment and decide prognostic values. Process of diagnosis includes various aspects like physical examination through symptoms exhibited for a disease, person’s previous medical history, and various type of medical tests. Diagnosis of a disease is often challenging since there are many nonspecific signs and symptoms and often are common with other ailments too. In present study we applied Advance Machine Learning approach to identify the major attributes those are involved in polycystic ovary syndrome (PCOS) disease progression as well as help medical professional to predict the disease with accuracy and minimal time.Present work encompasses the use of genetic algorithm a Machine learning approach for selection of major attributes (the sign and symptoms ) for PCOS patients data which affect the disease condition most ,in present study various classifiers have been applied in our dataset and different accuracy parameters also have been used including Confusion matrix , Precision , F1 score and AUC (area under the curve) to select the best classifier which classify the diseased and non diseased patients with high accuracy.