Development of Big Data Predictive Analytics Model for Disease Prediction using Machine learning Technique

Abstract

Now days, health prediction in modern life becomesvery much essential. Big data analysis plays a crucial role to predict future status of healthand offerspreeminenthealth outcome to people. Heart disease is a prevalent disease cause's death around the world. A lotof research is going onpredictive analytics using machine learning techniques to reveal better decision making. Big data analysis fosters great opportunities to predict future health status from health parameters and provide best outcomes. WeusedBig Data Predictive Analytics Model for Disease Prediction using Naive Bayes Technique (BPA-NB). It providesprobabilistic classification based on Bayes' theorem with independence assumptions between the features. Naive Bayes approach suitable for huge data sets especially for bigdata. The Naive Bayes approachtrain the heart disease data taken from UCI machine learning repository. Then, it was making predictions on the test data to predict the classification. The results reveal that the proposed BPA-NB scheme providesbetter accuracy about 97.12% to predict the disease rate. The proposed BPA-NB scheme used Hadoop-spark as big data computing tool to obtain significant insight on healthcare data. The experiments are done to predict different patients' future health condition. It takes the training dataset to estimate the health parameters necessary for classification. The results show the early disease detection to figure out future health of patients.

Keywords: Big data; Machine learning; Naive Bayes; Prediction; SparkFramework.