A Comprehensive Approach For Symptoms-Driven Multiple Disease Detection using Machine Learning Algorithms

Abstract

Computer-Assisted; In medical analysis, diagnosis is a rapidly developing, multifaceted topic of research. The development of computer-aided diagnostic applications has garnered significant attention in recent years due to the potential for seriously misleading medical therapies resulting from errors in medical diagnosis systems. It is essential to use machine learning (ML) to computer-aided diagnostic testing. An item, like bodily organs, cannot be correctly identified by a simple equation. For this reason, pattern recognition essentially requires learning from examples. Pattern recognition and machine learning (ML) have the potential to increase the accuracy of disease approach and diagnosis in the field of biomedicine. They also honour the impartiality of the decision-making process. Creating an excellent, automated system for the analysis of high-dimensional, multi-modal biomedical data may be accomplished with the help of machine learning (ML). This survey research examines the similarities and differences of many machine learning algorithms for the diagnosis of different illnesses, including diabetes and heart disease. It focuses on a collection of machine learning methods and algorithms used in disease detection and decision-making, such as Random-Forest, Naive Bayes Classifier, Decision Tree, and Voting Classifier.