A Comparative Study of Building Disease Classification Model through Supervised Machine Learning Algorithms for HealthCare Data

Abstract

With the emerging new disease patterns, new technologies like machine learning and data analytics are
proving to provide promising solutions in early detection of symptoms, decoding various patterns, predicting various
responses to drugs, etc. These are proving to be very helpful to biomedical professionals, the healthcare industry, and
patients. Machine learning can be used to develop models for the prediction of chronic diseases.
In this paper, machine learning techniques will be compared using the benchmark datasets. The different types of data
classification methods and techniques are available such as Decision Tree, k-Nearest Neighbor, Support Vector
Machine, Naive Bayes, Logistic Regression, and Linear Discriminant algorithms. The objective of the thesis work is to
do the comparative study and evaluation of supervised machine learning methods with the help of reduced healthcare
datasets collected. It is shown that the accuracy of the SVM classifier is better than the others.