A Comparative Analysis of Machine Learning Techniques for Efficient Diabetes Prediction

Abstract

In the healthcare sector, predictive analytics plays a vital role, presenting a challenging task but offering potential benefits in making informed decisions about patient health and treatment based on big data. This research paper delves into the realm of predictive analytics in healthcare, employing four distinct machine learning algorithms. The experiment involves the utilization of a dataset comprising patients’ medical records, upon which the four algorithms are applied. A comprehensive analysis is conducted using a diverse range of algorithms, including logistic regression, decision trees, random forests and support vector machines. These algorithms’ effectiveness is assessed using important measures like precision, recall, precision, accuracy and F1-score. By comparing the different machine learning techniques employed in the present study, the analysis aims to determine the most suitable algorithm for predicting diabetes.