Optimasi Support Vector Machine Menggunakan Grid Search Untuk Prediksi Jenis Penyakit Stroke

I Gusti Agung Harkit Brahmantya; I Nyoman Sukajaya; Raphita Yanisari Silalahi

doi:10.35960/ikomti.v7i2.2493

Authors

I Gusti Agung Harkit Brahmantya Universitas Pendidikan Ganesha
I. N. Sukajaya Universitas Pendidikan Ganesha
Raphita Yanisari Silalahi Universitas Pendidikan Ganesha

DOI:

https://doi.org/10.35960/ikomti.v7i2.2493

Keywords:

stroke type classification, support vector machine, grid search

Abstract

This study aims to improve the classification performance of stroke types by optimizing the Support Vector Machine (SVM) algorithm using the Grid Search method. The dataset used consists of medical records of stroke patients in 2024 from RSUD Buleleng, comprising 610 patient records with 13 clinical attributes as input variables and stroke type as the target variable. The research stages include data preprocessing (data cleaning and label encoding), data splitting with an 80:20 ratio, building an SVM model without optimization, and parameter optimization using Grid Search. Model performance was evaluated using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results show that the SVM model without optimization achieved an accuracy of 0.92, precision of 0.92, recall of 0.93, and F1-score of 0.92. After applying Grid Search optimization, the best parameters obtained were a polynomial kernel with , , , and , which improved the model performance to an accuracy of 0.95, precision of 0.94, recall of 0.95, and F1-score of 0.94. These results indicate that parameter optimization using Grid Search can effectively enhance the performance of the SVM model in classifying stroke types more accurately.

References

[1] Y. A. Utama and S. S. Nainggolan, “Faktor resiko yang mempengaruhi kejadian stroke: sebuah tinjauan sistematis,” Jurnal Ilmiah Universitas Batanghari Jambi, vol. 22, no. 1, pp. 549–553, Feb. 2022, doi: 10.33087/jiubj.v22i1.1950.

[2] V. L. Feigin et al., “World Stroke Organization (WSO): global stroke fact sheet 2022,” International Journal of Stroke, vol. 17, no. 1, pp. 18–29, Jan. 2022, doi: 10.1177/17474930211065917.

[3] N. K. Hayati, D. L. Badriah, and R. Suparman, “Faktor-faktor yang berhubungan dengan penyakit stroke pada pasien rawat inap di ruang penyakit dalam rumah sakit umum daerah 45 kuningan,” Journal of Health Research Science, vol. 4, no. 1, pp. 69–84, Jun. 2024, doi: 10.34305/jhrs.v4i1.1144.

[4] K. Khairuman et al., “Analisis faktor risiko dan pencegahan jantung koroner dan stroke: tinjauan literatur,” Jurnal Dremi (Demi Pengabdi Masyarakat), vol. 1, no. 1, pp. 23–30, Feb. 2025, [Online]. Available: https://ejournalrisetsadewa.com/index.php/dremi/article/view/7/6

[5] P. A. Setiawan, “Diagnosis dan tatalaksana stroke hemoragik,” Jurnal Medika Hutama, vol. 3, no. 1, pp. 1660–1665, Oct. 2021, [Online]. Available: https://www.jurnalmedikahutama.com/index.php/JMH/article/view/336

[6] A. Familah, A. F. Arifin, A. H. Muchsin, M. E. Rachman, and D. Dahliah, “Karakteristik penderita stroke iskemik dan stroke hemoragik,” Fakumi Medical Journal, vol. 4, pp. 457–464, 2024, doi: 10.33096/fmj.v4i6.468.

[7] I. O. Herlistiono and S. Violina, “Model prediksi risiko stroke menggunakan machine learning,” Journal of Information Technology and Computer Science (INTECOMS), vol. 7, no. 4, pp. 1230–1238, 2024, doi: 10.31539/intecoms.v7i4.10942.

[8] M. Putri and E. Erlin, “Prediksi penyakit stroke menggunakan machine learning dengan algoritma random forest,” Jurnal Infomedia: Teknik Informatika, Multimedia & Jaringan, vol. 9, no. 2, pp. 16–21, Mar. 2024, doi: 10.30811/jim.v9i1.5199.

[9] A. Setiawan, R. F. Waleska, M. A. Purnama, R. Rahmaddeni, and L. Efrizoni, “Komparasi algoritma k-nearest neighbor (K-NN), support vector machine (SVM), dan decision tree dalam klasifikasi penyakit stroke,” Jurnal Informatika & Rekayasa Elektronika, vol. 7, no. 1, pp. 107–114, Apr. 2024, doi: 10.36595/jire.v7i1.1161.

[10] R. Anggreini, “Analisis Prediksi Risiko Stroke Menggunakan Algoritma Random Forest Classifier (RFC) Dan Support Vector Machine (SVM),” EJECTS: Journal Computer, Technology and Informations System, vol. 4, no. 2, pp. 64–70, Mar. 2025.

[11] M. Sheykhmousa, M. Mahdianpari, H. Ghanbari, F. Mohammadimanesh, P. Ghamisi, and S. Homayouni, “Support vector machine versus random forest for remote sensing image classification: a meta-analysis and systematic review,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 13, pp. 6308–6325, 2020, doi: 10.1109/JSTARS.2020.3026724.

[12] I. A. Muis and M. Affandes, “Penerapan metode support vector machine (SVM) menggunakan kernel radial basis function (RBF) pada klasifikasi tweet,” Jurnal Sains, Teknologi dan Industri, vol. 12, no. 2, pp. 189–197, Jun. 2015, doi: 10.24014/sitekin.v12i2.1010.

[13] I. Ispandi and R. S. Wahono, “Penerapan algoritma genetika untuk optimasi parameter pada support vector machine untuk meningkatkan prediksi pemasaran langsung,” Journal of Intelligent Systems, vol. 1, no. 2, 2015, [Online]. Available: https://www.neliti.com/publications/243563/penerapan-algoritma-genetika-untuk-optimasi-parameter-pada-support-vector-machin

[14] A. C. Müller and S. Guido, Introduction to machine learning with python a guide for data scientists introduction to machine learning with python. O’Reilly Media, 2016. [Online]. Available: https://www.oreilly.com/library/view/introduction-to-machine/9781449369880/

[15] F. O. Awalullaili, D. Ispriyanti, and T. Widiharih, “Klasifikasi penyakit hipertensi menggunakan metode SVM grid search dan SVM Genetic Algorithm (GA),” Jurnal Gaussian, vol. 11, no. 4, pp. 488–498, Feb. 2022, doi: 10.14710/j.gauss.11.4.488-498.

[16] A. C. Nisa, B. Rahmat, and A. Junaidi, “SVM Optimization for Autism Spectrum Disorder Classification: A Comparison of PCA, PSO, and Grid Search,” Journal of Artificial Intelligence and Engineering Applications, vol. 4, no. 3, pp. 1900–1906, Jun. 2025, doi: 10.59934/jaiea.v4i3.1044.

[17] M. Masriana, M. Muammar, and M. Yahya, “Faktor-faktor yang mempengaruhi terjadinya stroke pada pasien,” Darussalam Indonesian Journal of Nursing and Midwifery, vol. 3, no. 3, pp. 55–66, 2021, [Online]. Available: https://www.jurnal.sdl.ac.id/index.php/dij/article/view/47

[18] D. Hisni, M. Evelianti Saputri, and Sujarni, “Faktor - Faktor Yang Berhubungan dengan Kejadian Stroke Iskemik di Instalasi Fisioterapi Rumah Sakit Pluit Jakarta Utara Periode Tahun 2021,” Jurnal Penelitian Keperawatan Kontemporer, vol. 2, pp. 140–149, Jan. 2022, doi: doi.org/10.59894/jpkk.v2i1.333.

[19] J. W. Horn et al., “Body mass index measured repeatedly over 42 years as a risk factor for ischemic stroke: the hunt study,” Nutrients, vol. 15, pp. 1–13, Feb. 2023, doi: 10.3390/nu15051232.

[20] R. I. K. Dewi, “Faktor Risiko Kejadian Stroke pada Pasien Diabetes Melitus di Indonesia: Narrative Review,” Jurnal Kesehatan Bakti Tunas Husada : Jurnal Ilmu Ilmu Keperawatan, Analis Kesehatan dan Farmasi, vol. 24, pp. 161–171, Aug. 2024, doi: doi.org/10.36465/jkbth.v24i2.1322.

[21] Z. M. Razdiq and Y. Imran, “Hubungan antara tekanan darah dengan keparahan stroke menggunakan National Institute Health Stroke Scale,” Jurnal Biomedika dan Kesehatan, vol. 3, no. 1, pp. 15–20, 2020, doi: 10.18051/JBiomedKes.2020.v3.15-20.

[22] A. Fauzi, P. Putri, and A. T. Afandi, “Hubungan Tanda-Tanda Vital dengan GCS Pasien Stroke,” Jurnal Keperawatan Malang, vol. 7, no. 1, pp. 89–103, 2022, doi: 10.36916/jkm.v7i1.164.

[23] A. A. Daniswara and I. K. D. Nuryana, “Data preprocessing pola pada penilaian mahasiswa program profesi guru,” Journal of Informatics and Computer Science, vol. 05, pp. 97–100, 2023, doi: 10.26740/jinacs.v5n01.p97-100.

[24] K. Maharana, S. Mondal, and B. Nemade, “A review: Data pre-processing and data augmentation techniques,” Global Transitions Proceedings, vol. 3, no. 1, pp. 91–99, Jun. 2022, doi: 10.1016/j.gltp.2022.04.020.

[25] C. Herdian, A. Kamila, and I. G. A. M. Budidarma, “Studi kasus feature engineering untuk data teks: perbandingan label encoding dan one-hot encoding pada metode linear regresi,” Technologia : Jurnal Ilmiah, vol. 15, p. 93, Jan. 2024, doi: 10.31602/tji.v15i1.13457.

[26] D. E. Sondakh, “Comparative study of classification algorithms: holdouts as accuracy estimation,” Cogito Smart Journal, vol. 1, no. 1, pp. 13–23, Dec. 2015, doi: 10.31154/cogito.v1i1.2.13-23.

[27] M. Bansal, A. Goyal, and A. Choudhary, “A comparative analysis of K-Nearest Neighbor, Genetic, Support Vector Machine, Decision Tree, and Long Short Term Memory algorithms in machine learning,” Decision Analytics Journal, vol. 3, p. 100071, Jun. 2022, doi: 10.1016/j.dajour.2022.100071.

[28] A. Kurani, P. Doshi, A. Vakharia, and M. Shah, “A Comprehensive Comparative Study of Artificial Neural Network (ANN) and Support Vector Machines (SVM) on Stock Forecasting,” Annals of Data Science, vol. 10, no. 1, pp. 183–208, Feb. 2023, doi: 10.1007/s40745-021-00344-x.

[29] P. Chhajer, M. Shah, and A. Kshirsagar, “The applications of artificial neural networks, support vector machines, and long–short term memory for stock market prediction,” Decision Analytics Journal, vol. 2, Mar. 2022, doi: 10.1016/j.dajour.2021.100015.

[30] L. Yao, Z. Fang, Y. Xiao, J. Hou, and Z. Fu, “An intelligent fault diagnosis method for lithium battery systems based on grid search support vector machine,” Energy, vol. 214, pp. 1–32, Jan. 2021, doi: 10.1016/j.energy.2020.118866.

[31] R. Nurhidayat and K. E. Dewi, “Penerapan algoritma k-nearest neighbor dan fitur ekstraksi n-gram dalam analisis sentimen berbasis aspek,” KOMPUTA: Jurnal Ilmiah Komputer dan Informatika, vol. 12, no. 1, Apr. 2023, doi: 10.34010/komputa.v12i1.9458.

[32] J. Han, M. Kamber, and J. Pei, Data mining: concepts and techniques thrd edition. Morgan Kaufmann, 2012. [Online]. Available: https://www.sciencedirect.com/book/9780123814791/data-mining-concepts-and-techniques#book-info