Heart disease diagnosis is the most considerable issue in the medical research which needs to be diagnosed earlier to avoid the unwanted human loss. Early detection of heart disease would lead to proper and on time treatment to the patients. This is performed in our previous work by introducing the method namely Hybrid Differential Evolution based Fuzzy Neural Network (HDEFNN) that ensures the proper and on time heart disease diagnosis. However this research work doesn’t focus on the risk factors involved with the heart disease which might reduce the accuracy of the diagnosis outcome. And also HDEFNN method is tends to have more computational overhead which needs to be resolved to avoid the health related issues. This is focused and resolved in this research work by introducing the method namely Risk Factor aware Heart Disease Diagnosis using Fuzzy Extreme Learning Machine (RFHDD-FELM). In this work initially risk factor selection is performed by introducing the optimization method namely Particle Swarm Optimization algorithm. These selected risk factors will learnt for the accurate heart disease diagnosis outcome. The overall evaluation of the research work is conducted in the matlab simulation environment. The performance assessment is carried out on Alizadeh Sani dataset which is gathered from the UCI repository. The numerical assessment outcome proves that the proposed method RFHDD-FELM tends to better heart disease diagnosis outcome than the existing methodologies.
Volume 12 | 03-Special Issue
Pages: 36-44
DOI: 10.5373/JARDCS/V12SP3/20201236