An Integrated Architecture for Prediction of Heart Disease from the Medical Database

Abstract

A database is a collection of data organized for storage, access and retrieval. With increasing growth in big data, especially in healthcare and biomedical communities, the techniques to analyze the medical data tends to benefit the patients by detecting the disease early. However, with the advent of incomplete data in such medical datasets, the quality tends to reduce. In addition to this, each region has its own unique disease characteristics, which further reduces the prediction quality. To overcome the difficulty in processing the medical datasets with incomplete data, the proposed method initially reconstructs the missing or incomplete data. To improve the processing capability of automated disease prediction in an uncertain environment, an integrated architecture is proposed. It controls the processing capability of medical datasets in an uncertain environment. This integrated diagnostic model generates the hesitant fuzzy based decision tree algorithm using genetic classification. The architecture is designed to process both the structure and unstructured data sets. The new and innovative prediction methods are projected in this research to predict heart disease from the medical database in a faster manner.