Adittia Fathah
Informatika, Sekolah Tinggi Teknologi Cipasung

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Development of a Heart Disease Risk Classification Model Using Various Kernels with the Support Vector Machine Algorithm (SVM) Algorithm Adittia Fathah
Techno Xplore: Journal of Computer Science and Information Technology Vol. 11 No. 2 (2026): Techno Xplore: Jurnal Ilmu Komputer dan Teknologi Informasi
Publisher : Informatics Engineering, Faculty of Engineering and Computer Science, Universitas Buana Perjuangan Karawang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36805/hk3h4m23

Abstract

Advances in information technology have had a significant impact on the healthcare sector, particularly in accelerating the early detection of diseases to reduce mortality rates. Heart attacks remain a crucial health issue in Indonesia, necessitating rapid and accurate preventative management. With the increasing availability of medical data, the utilisation of data-driven analytical techniques and machine learning has emerged as a highly relevant computational solution. This study aims to develop and evaluate a heart disease risk prediction model using the Support Vector Machine (SVM) algorithm. Model development was conducted by applying the structured SEMMA (Sample, Explore, Modify, Model, Assess) methodology. To identify the most optimal modelling architecture, a comparative evaluation was performed on four SVM kernel functions: Linear, Radial Basis Function (RBF), Polynomial, and Sigmoid. Empirical testing results demonstrated that the RBF kernel-based SVM algorithm yielded the most superior classification performance, achieving an accuracy rate of 98.12%. Furthermore, feature ranking analysis revealed that the manifestation of acute clinical symptoms physically experienced by patients served as the primary predictor influencing the risk classification outcomes. The findings of this study conclude that the integration of the RBF kernel within the SVM model and clinical symptom attributes can provide a precise and reliable early detection system for heart disease risk.