Heart Diseases Prediction Using Block-chain and Machine Learning

TL;DR

This paper proposes a secure healthcare data system using blockchain combined with a novel machine learning algorithm, SCA-WKNN, to improve early prediction accuracy of heart disease.

Contribution

It introduces an integrated blockchain and SCA-WKNN approach for secure and accurate heart disease prediction, enhancing data security and prediction performance.

Findings

Blockchain secures patient data effectively.

SCA-WKNN achieves higher accuracy than existing methods.

Improved dataset enhances prediction reliability.

Abstract

Most people around the globe are dying due to heart disease. The main reason behind the rapid increase in the death rate due to heart disease is that there is no infrastructure developed for the healthcare department that can provide a secure way of data storage and transmission. Due to redundancy in the patient data, it is difficult for cardiac Professionals to predict the disease early on. This rapid increase in the death rate due to heart disease can be controlled by monitoring and eliminating some of the key attributes in the early stages such as blood pressure, cholesterol level, body weight, and addiction to smoking. Patient data can be monitored by cardiac Professionals (Cp) by using the advanced framework in the healthcare departments. Blockchain is the world's most reliable provider. The use of advanced systems in the healthcare departments providing new ways of dealing with diseases has been developed as well. In this article Machine Learning (ML) algorithm known as a sine-cosine weighted k-nearest neighbor (SCA-WKNN) is used for predicting the Hearth disease with the maximum accuracy among the existing approaches. Blockchain technology has been used in the research to secure the data throughout the session and can give more accurate results using this technology. The performance of the system can be improved by using this algorithm and the dataset proposed has been improved by using different resources as well.