A Critical Analysis of Machine Learning Techniques for Human Disease Prediction Model

Main Article Content

Dr. Hemamalini G E, Dr. J Prakash

Abstract

Various diseases affect people today because of environmental factors and their lifestyles. Therefore, predicting disease at an early stage becomes crucial. It is difficult for doctors to make an accurate diagnosis based on symptoms alone. It is very challenging to accurately predict disease. Data mining plays a critical role in disease prediction in order to solve this challenge. Each year, there is a tremendous amount of data expansion in the world of medicine. A growing amount of medical and healthcare data has resulted in the ability to analyze medical data in a way that benefits early patient care. A data mining technique uses disease data to find hidden patterns in vast amounts of medical information. The purpose of our proposal was to provide general disease predictions based on symptoms of the patient. In order to predict disease accurately, (DECISION TREE AND NAIVE BAYES) machine learning algorithm is used. It is necessary to collect data on disease symptoms for disease prediction. For the reliability of the general illness diagnosis, a person's lifestyle and check-up facts are taken into account. It is possible to forecast general disease with an accuracy of 84.5% using Naive Bayes and Decision Trees.

Article Details

Section
Articles