Classification of Heart Disease Risk using the Support Vector Machine

Suci Wulan Dari, Hendrawaty Hendrawaty, Azhar Azhar

Abstract


Heart disease is one of the leading causes of death globally, affecting millions of people every year. The development of information technology has facilitated significant advances in health data analysis through machine learning and data mining. One of the techniques used, the Support Vector Machine (SVM), allows for accurate classification of heart disease risk based on clinical data such as age, gender, blood pressure, and other factors. The study aimed to optimize the SVM model for heart disease risk classification, with results showing a success rate of 90% from 50 trials. The SVM method works by finding the best hyperplane that maximizes the margin between data classes, even in higher dimensional spaces through the use of the kernel. The results show that the SVM model with optimal parameters (C=10, γ=1) and SMOTE technique produces 92% accuracy, 89% precision, 95% recall, and 92% f1-score. The conclusions of this study confirm that SVM is effective in grouping clinical data for heart disease risk classification, although challenges remain in recognizing some of the more complex risk cases. This research can provide a foundation for the development of a better classification system.

References


A. Javeed, S. S. Rizvi, S. Zhou, R. Riaz, S. U. Khan, and S. J. Kwon, “Heart risk failure prediction using a novel feature selection method for feature refinement and neural network for classification,†Mob. Inf. Syst., vol. 2020, 2020.

R. Katarya and P. Srinivas, “Predicting Heart Disease at Early Stages using Machine Learning: A Survey,†Proc. Int. Conf. Electron. Sustain. Commun. Syst. ICESC 2020, no. Icesc, pp. 302–305, 2020.

V. harsha vardhan:Uppala rajesh kumar;Yanumu vardhini;Sabbi leela varalakshmi;A. sura. Kumar, “Heart Disease Prediction Using Machine Learning,†vol. 14, no. 04, 2023.

A. Yazdani, K. D. Varathan, Y. K. Chiam, A. W. Malik, and W. A. Wan Ahmad, “A novel approach for heart disease prediction using strength scores with significant predictors,†BMC Med. Inform. Decis. Mak., vol. 21, no. 1, pp. 1–16, 2021.

A. A. Permana et al., Machine Learning, vol. 45, no. 13. 2023. [Online].

I. Ibrahim and A. Abdulazeez, “The Role of Machine Learning Algorithms for Diagnosing Diseases,†J. Appl. Sci. Technol. Trends, vol. 2, no. 01, pp. 10–19, 2021.

I. Rashad, Sistem Prediksi Untuk Risiko Penyakit Jantung Menggunakan Algoritma Klasifikasi Linear Discriminant Analysis. 2023.

N. Fitriyani, D. R. Amalia, H. H. Handayani, A. Fitri, and N. Masruriyah, “Aplikasi Berbasis Web Berdasarkan Model Klasifikasi Algoritma SVM dan Logistic Regression Terhadap Data Diabetes,†vol. 7, pp. 1762–1771, 2023.

B. Akalin, Ü. Veranyurt, and O. Veranyurt, “Classification of Individuals at Risk of Heart Disease Using Machine Learning,†Cumhur. Med. J., no. September, pp. 283–289, 2020.

S. T. P. Prasanna and T. Veeramani, “Supervised study of Novel Random Forest Algorithm for prediction of heart disease in Comparison With The Decision Tree Algorithm,†Cardiometry, no. 25, pp. 1483–1490, 2023.


Refbacks

  • There are currently no refbacks.


Indexing :

Creative Commons License
Journal of Informatics Engineering and Software Applications (JIEngS) licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.