Disease Prediction and Performance Analysis using Data Analytics

Abstract

Big Data means the large and the voluminous data collected from various resources. The data helps us in understanding lot many aspects of the particular field. Healthcare is one such field or area which produces huge number of data such as patient's profiles, disease, symptoms and so on. Data Analytics comes into the picture when we have to review, analyze and predict the data. The main objective of the Data Mining Techniques is to make smart decisions, consume less time and being more accurate. In this paper, we have used two different datasets: Pregnancy Diabetes Dataset and Breast Cancer Dataset. The Classification Algorithms like SVM and Random Forest for the top-level classification and Clustering Algorithms like Agglomerative, Gaussian Mixture Model, and Spectral Clustering for further processing. The efficient algorithm is identified by comparing the accuracy results of the different implemented clustering algorithms.