IMPLEMENTASI SUPPORT VECTOR MACHINE (SVM) DALAM KLASIFIKASI PENYAKIT ASMA BERDASARKAN DATA REKAM MEDIS
DOI:
https://doi.org/10.70248/jdaics.v3i3.4435Abstract
Penyakit asma memiliki pola gejala, faktor risiko, dan fungsi paru yang heterogen sehingga identifikasi berbasis rekam medis memerlukan pendekatan yang objektif dan terukur. Penelitian ini mengimplementasikan Support Vector Machine (SVM) kernel Radial Basis Function (RBF) untuk mengklasifikasikan pasien tidak asma/normal dan asma berdasarkan 1.087 rekam medis RSUD Tidore periode 1 Januari 2021–31 Desember 2025 dengan 13 fitur klinis. Data dibagi secara stratified menjadi 80% data latih dan 20% data uji; MinMaxScaler ditempatkan dalam pipeline untuk mencegah information leakage. Hyperparameter C dan gamma dioptimasi menggunakan Grid Search dengan stratified 5-fold cross-validation pada data latih, dan kestabilan model dievaluasi menggunakan nested stratified 5-fold cross-validation. Parameter terbaik pada data latih adalah C=30 dan gamma=0,01. Pada holdout test set, model menghasilkan TN=89, FP=1, FN=6, dan TP=122 dengan akurasi 96,79%, presisi 99,19%, sensitivitas 95,31%, spesifisitas 98,89%, F1-score 97,21%, Matthews Correlation Coefficient (MCC) 0,935, dan ROC-AUC 0,9949. Nested cross-validation menghasilkan ROC-AUC 0,9898±0,0049 dan akurasi 95,21±1,56%, yang menunjukkan performa relatif stabil pada pembagian data yang berbeda. Permutation importance menempatkan FEV1, dada terasa berat, riwayat keluarga asma, dan sesak napas sebagai fitur dengan kontribusi prediktif terbesar. Enam false negative terutama menunjukkan ketiadaan sesak napas dan gejala malam hari, sehingga penekanan false negative tetap penting dari perspektif patient safety. Keterbatasan penelitian meliputi data satu pusat, distribusi kelas yang tidak sepenuhnya seimbang, ketidaktersediaan provenance rinci label diagnosis, dan metadata unit spirometri. Model diposisikan sebagai Clinical Decision Support System dan tidak menggantikan diagnosis profesional dokter.
References
M. A. Tosca, I. Schiavetti, G. Ciprandi, et al., “The challenge of asthma control grading in clinical practice,” Respiratory Investigation, vol. 59, no. 5, pp. 683–685, 2021, doi: 10.1016/j.resinv.2021.06.001.
G. Guarnieri et al., “Asthma severity: the patient’s point of view,” European Clinical Respiratory Journal, vol. 11, no. 1, Art. no. 2381307, 2024, doi: 10.1080/20018525.2024.2381307.
Y. Y. Sio and F. T. Chew, “Risk factors of asthma in the Asian population: a systematic review and meta-analysis,” Journal of Physiological Anthropology, vol. 40, Art. no. 22, 2021, doi: 10.1186/s40101-021-00273-x.
T. Sarwar, S. Seifollahi, J. Chan, X. Zhang, V. Aksakalli, I. Hudson, K. Verspoor, and L. Cavedon, “The secondary use of electronic health records for data mining: data characteristics and challenges,” ACM Computing Surveys, vol. 55, no. 2, Art. no. 33, pp. 1–40, 2022, doi: 10.1145/3490234.
U. M. Butt, S. Letchmunan, M. Ali, F. H. Hassan, A. Baqir, and H. H. R. Sherazi, “Machine learning based diabetes classification and prediction for healthcare applications,” Journal of Healthcare Engineering, vol. 2021, Art. no. 9930985, 2021, doi: 10.1155/2021/9930985.
R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An overview on the advancements of Support Vector Machine models in healthcare applications: a review,” Information, vol. 15, no. 4, Art. no. 235, 2024, doi: 10.3390/info15040235.
X. Zhou et al., “Support vector machine deep mining of electronic medical records to predict the prognosis of severe acute myocardial infarction,” Frontiers in Physiology, vol. 13, Art. no. 991990, 2022, doi: 10.3389/fphys.2022.991990.
H. Joo, D. Lee, S. H. Lee, Y. K. Kim, and C. K. Rhee, “Increasing the accuracy of the asthma diagnosis using an operational definition for asthma and a machine learning method,” BMC Pulmonary Medicine, vol. 23, Art. no. 196, 2023, doi: 10.1186/s12890-023-02479-4.
M. Moloney et al., “Validation of adult asthma case definitions for primary care sentinel surveillance,” Allergy, Asthma & Clinical Immunology, vol. 19, Art. no. 95, 2023, doi: 10.1186/s13223-023-00854-8.
M. M. Ahsan, M. A. P. Mahmud, P. K. Saha, K. D. Gupta, and Z. Siddique, “Effect of data scaling methods on machine learning algorithms and model performance,” Technologies, vol. 9, no. 3, Art. no. 52, 2021, doi: 10.3390/technologies9030052.
I. Izonin, R. Tkachenko, N. Shakhovska, B. Ilchyshyn, and K. K. Singh, “A two-step data normalization approach for improving classification accuracy in the medical diagnosis domain,” Mathematics, vol. 10, no. 11, Art. no. 1942, 2022, doi: 10.3390/math10111942.
A. Razaque et al., “Improved Support Vector Machine enabled Radial Basis Function and linear variants for remote sensing image classification,” Sensors, vol. 21, no. 13, Art. no. 4431, 2021, doi: 10.3390/s21134431.
D. Chicco, N. Tötsch, and G. Jurman, “The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation,” BioData Mining, vol. 14, Art. no. 13, 2021, doi: 10.1186/s13040-021-00244-z.
N. Budhathoki, R. Bhandari, S. Bashyal, and C. Lee, “Predicting asthma using imbalanced data modeling techniques: evidence from 2019 Michigan BRFSS data,” PLOS ONE, vol. 18, no. 12, Art. no. e0295427, 2023, doi: 10.1371/journal.pone.0295427.
O. K. Gargari et al., “Assessing the diagnostic accuracy of machine learning algorithms for identification of asthma in United States adults based on NHANES dataset,” Scientific Reports, vol. 15, Art. no. 4537, 2025, doi: 10.1038/s41598-025-88345-1.
H. Tang, G. Yang, X. Gu, H. Mao, and H. Cao, “A support vector machine-based tool for rapid pediatric asthma exacerbation risk assessment: development and nursing application,” Frontiers in Pediatrics, vol. 13, Art. no. 1660895, 2025, doi: 10.3389/fped.2025.1660895.
Global Initiative for Asthma (GINA), Global Strategy for Asthma Management and Prevention, 2026. [Online]. Available: https://ginasthma.org/2026-gina-strategy-report/.
J. Landeo-Gutierrez et al., “Leveraging Electronic Health Records for Guideline-Based Asthma Documentation,” Journal of Allergy and Clinical Immunology: In Practice, vol. 11, no. 3, pp. 855–862.e4, 2023, doi: 10.1016/j.jaip.2022.11.032.
S. Sohn, C.-I. Wi, Y. J. Juhn, and H. Liu, “Analysis of clinical variations in asthma care documented in electronic health records between staff and resident physicians,” Studies in Health Technology and Informatics, vol. 245, pp. 1170–1174, 2017, doi: 10.3233/978-1-61499-830-3-1170.
