Optimasi Support Vector Machine Menggunakan Pendekatan Hybrid Kernel Linear-RBF Untuk Klasifikasi Penyakit Jantung
-
Mulyadi Mulyadi
*
Universitas Nurdin Hamzah, Jambi,
Indonesia
- Dian Kasoni STMIK Antar Bangsa, Tangerang, Indonesia
- Nurdiana Handayani Universitas Muhammadiyah Tangerang, Tangerang, Indonesia
- Liesnaningsih Liesnaningsih Universitas Muhammadiyah Tangerang, Tangerang, Indonesia (*) Corresponding Author
Abstract
Heart disease remains one of the leading causes of mortality worldwide, making early detection crucial to prevent severe complications. The limitations of conventional diagnostic approaches have encouraged the adoption of machine learning techniques to enable faster and more accurate predictions. Support Vector Machine (SVM) is widely recognized as an effective method for medical classification tasks; however, its performance is highly dependent on the choice of kernel function. This study evaluates three single-kernel SVM models (Linear, RBF, and Polynomial) and two hybrid kernel configurations, namely Linear–RBF and Linear–Polynomial, using the UCI Heart Disease Statlog dataset, which consists of 270 samples and 13 predictive features. In the hybrid approach, the probabilistic outputs of the individual base kernels are combined through an aggregation strategy to construct a decision function capable of capturing both linear and nonlinear patterns simultaneously. To ensure performance stability on the relatively small dataset, model evaluation was conducted using Stratified K-Fold Cross Validation, ensuring that the reported results do not rely on a single data split. Experimental results indicate that the SVM-Polynomial model achieved the highest ROC-AUC value of 0.9420; however, it did not outperform other models in terms of accuracy, precision, or F1-score. The hybrid approach demonstrated more consistent overall performance, with the Linear–RBF combination emerging as the best-performing model, achieving an accuracy of 0.8889, macro precision of 0.8896, and macro F1-score of 0.8886. These findings suggest that integrating linear and nonlinear kernel characteristics produces a more balanced decision function compared to single-kernel models. In contrast, the Linear–Polynomial combination did not yield significant performance improvements. The main contribution of this study lies in presenting a structured comparative analysis of kernel combination strategies in SVM for heart disease classification, which may support the development of more adaptive and stable clinical prediction systems.
Downloads
References
W. Handayani, “Faktor-Faktor Risiko Penyakit Kordiovaskular: Artikel Review,” J. Pengemb. Ilmu dan Prakt. Kesehat., vol. 4, no. 3, pp. 139–158, 2025, doi: https://doi.org/10.56586/pipk.v4i3.465.
D. Saraswati, “Inovasi Pelayanan Kesehatan: Deteksi Dini Penyakit Jantung Koroner melalui Posbindu PTM,” J. Kesehat. dan Kebidanan Nusant., vol. 2, no. 1, pp. 10–16, 2024, doi: https://doi.org/10.69688/jkn.v2i1.81.
T. Septiana, M. A. Muda, D. Budiyanto, M. Pratama, and W. P. Jaya, “Analisis Penggunaan Support Vector Machine pada Deteksi Dini Penyakit Diabetes Melitus,” J. Penelit. Inov., vol. 4, no. 3, pp. 1631–1640, 2024, doi: https://doi.org/10.54082/jupin.643.
S. Arifin, R. Satria, and T. Tarwoto, “Pengembangan Algoritma Support Vector Machine (SVM) untuk Mengklasifikasi Penyakit Diabetes,” J. Informatics Interact. Technol., vol. 1, no. 2, pp. 140–147, 2024, doi: https://doi.org/10.63547/jiite.v1i2.39.
A. Pratama, A. H. Siregar, and M. R. D. Cahyo, “Analisis Penyakit Rabies Menggunakan Algoritma Support Vector Machine (SVM),” JITET (Jurnal Inform. dan Tek. Elektro Ter., vol. 13, no. 2, pp. 422–429, 2025, doi: https://doi.org/10.23960/jitet.v13i2.6229.
T. F. Ramadhan, A. Asrianda, and R. Risawandi, “Penerapan Metode Algoritma SVM (Support Vector Machine) Untuk Klasifikasi Penderita Penyakit Gastroesophageal Reflux Disease,” RABIT J. Teknol. dan Sist. Inf. Univrab, vol. 10, no. 2, pp. 1212–1219, 2025, doi: https://doi.org/10.36341/rabit.v10i2.6466.
L. N. Farida and S. Bahri, “Klasifikasi Gagal Jantung Menggunakan Metode SVM (Support Vector Machine),” Komputika J. Sist. Komput., vol. 13, no. 2, pp. 149–156, 2025, doi: https://doi.org/10.34010/komputika.v13i2.11330.
M. R. Pradana, W. Witanti, and A. Komarudin, “Prediksi Tingkat Keparahan Diabetes Melitus Menggunakan Support Vector Machine (SVM) dengan Kernel Polinomial dan RBF,” J. LOCUS Penelit. Pengabdi., vol. 4, no. 8, pp. 7521–7533, 2025, doi: https://doi.org/10.58344/locus.v4i8.4357.
A. Alexsander, A. Nazri, R. A. Panbudi, and J. Junadhi, “Implementasi Algoritma SVM dalam Memprediksi Penyakit Stroke,” J. Zetroem, vol. 06, no. 02, pp. 1–5, 2024, doi: https://doi.org/10.36526/ztr.v6i2.3676.
Z. Arifin, D. F. Rahman, B. S. Rintyarna, and D. Daryanto, “Penerapan Algoritma Support Vector Machine Berbasis Kernel Radial Basis Function dalam Klasifikasi Sel Kanker,” BIOS J. Teknol. Inf. dan Rekayasa Komput., vol. 4, no. 2, pp. 100–106, 2023, doi: https://doi.org/10.37148/bios.v4i2.165.
R. Mukarramah, D. Atmajaya, and L. Budi, “Performance comparison of support vector machine (SVM) with linear kernel and polynomial kernel for multiclass sentiment analysis on twitter,” Ilk. J. Ilm., vol. 13, no. 2, pp. 168–174, 2021, doi: https://doi.org/10.33096/ilkom.v13i2.851.168-174.
M. Rafidianto, D. A. Fatah, and Y. D. P. Negara, “Analisis Sentimen Aplikasi Mpstore Menggunakan Metode Support Vector Machine Multi Kernel,” Innov. J. Soc. Sci. Res., vol. 5, no. 1, pp. 6253–6263, 2025, doi: https://doi.org/10.31004/innovative.v5i1.17930.
A. G. Sooai, P. A. Nani, N. M. R. Mamulak, C. O. Sianturi, S. C. Sianturi, and A. H. Mondolang, “Klasifikasi Citra Daun Anggur Menggunakan SVM Kernel Linear,” JOINTECS (Journal Inf. Technol. Comput. Sci., vol. 7, no. 1, pp. 19–26, 2022, doi: https://doi.org/10.31328/jointecs.v8i1.4496.
I. Putri, F. Fadlisyah, and A. Razi, “Implementasi Metode SVM RBF (Radial Basis Function) Kernel Untuk Klasifikasi Status Gizi Pada Balita,” J. Teknol. Terap. Sains 4.0, vol. 5, no. 2, pp. 43–56, 2024, doi: https://doi.org/10.29103/tts.v5i2.19156.
R. Ritwik, “Heart Disease Statlog,” Kaggle. Accessed: Sep. 08, 2025. [Online]. Available: https://www.kaggle.com/datasets/ritwikb3/heart-disease-statlog
D. E. Yanti, L. Framesti, and A. Desiani, “Perbandingan Algoritma C4.5 dan SVM dalam Klasifikasi Penyakit Anemia,” JIP (Jurnal Inform. Polinema), vol. 9, no. 4, pp. 449–456, 2023, doi: https://doi.org/10.33795/jip.v9i4.1381.
A. W. Anggraeni, A. S. Fitrani, and A. Eviyanti, “Penerapan Algoritma Support Vector Machine untuk Memprediksi Tingkat Partisipasi Pemilu terhadap Kualitas Pendidikan,” Edumatic J. Pendidik. Inform., vol. 8, no. 1, pp. 21–27, 2024, doi: https://doi.org/10.21070/ups.9670.
M. M. Lasiyono, N. Nurhayati, T. G. Soares, and M. Mulyadi, “Enhancing Support Vector Machine Performance for Heart Attack Prediction using RobustScaler-Based Outlier Handling,” vol. 4, no. 1, pp. 1–9, 2025, doi: http://dx.doi.org/10.61944/bids.v4i1.94.
S. Adi and A. Wintarti, “Komparasi Metode Support Vector Machine (SVM), K-Nearest Neighbors (KNN), dan Random Forest (RF) Untuk Prediksi Penyakit Gagal Jantung,” MATHunesa J. Ilm. Mat., vol. 10, no. 02, pp. 258–268, 2022, doi: https://doi.org/10.26740/mathunesa.v10n2.p258-268.
A. F. Rochim, K. Widyaningrum, and D. Eridani, “Performance Comparison of Support Vector Machine Kernel Functions in Classifying COVID-19 Sentiment,” in 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), IEEE, 2021, pp. 224–228. doi: 10.1109/ISRITI54043.2021.9702845.
E. R. M. Sholihah, I. G. S. M. Diyasa, and E. Y. Puspaningrum, “Perbandingan Kinerja Kernel Linear dan RBF Support Vector Machine Untuk Analisis Sentimen Ulasan Pengguna KAI Access Pada Google Play Store,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 1, pp. 728–733, 2024, doi: https://doi.org/10.36040/jati.v8i1.8800.
C. V. Angkoso, K. Asror, A. Kusumaningsih, and A. K. Nugroho, “Optimasi Algoritma Support Vector Machine Berbasis Kernel Radial Basis Function (RBF) Menggunakan Metode Particle Swarm Optimization Untuk Analisis Sentimen,” J. Teknol. Inf. dan Ilmu Komput., vol. 12, no. 3, pp. 705–718, 2025, doi: https://doi.org/10.25126/jtiik.2025129317.
A. Faradisia and M. A. I. Pakereng, “Analisis Komparatif Kernel Linear, Polynomial, RBF, dan Sigmoid pada Support Vector Machine untuk Klasifikasi Penyakit Jantung,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 4, pp. 1531–1537, 2025, doi: https://doi.org/10.57152/malcom.v5i4.2321.
K. Paranjothi, F. Ghouse, and R. Vaithiyanathan, “Detection of Parkinson’s Disease on DaTSCAN Image Using Multi-kernel Support Vector Machine,” Int. J. Intell. Eng. Syst., vol. 17, no. 5, pp. 45–55, 2024, doi: 10.22266/ijies2024.1031.05.
A. K. Jhapate and H. Shrivastava, “GAIT based human Parkinson’s disease detection using fused features with multi-kernel support vector machine,” Int. J. Inf. Technol., vol. 17, no. 3, pp. 1387–1395, 2025, doi: 10.1007/s41870-024-02099-z.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Optimasi Support Vector Machine Menggunakan Pendekatan Hybrid Kernel Linear-RBF Untuk Klasifikasi Penyakit Jantung
Pages: 567-576
Copyright (c) 2026 Mulyadi Mulyadi, Dian Kasoni, Nurdiana Handayani, Liesnaningsih Liesnaningsih
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
