Penerapan Metode Naïve Bayes dengan SMOTE pada Sistem Pendukung Keputusan untuk Prediksi Risiko Stroke
Keywords:
stroke, Naïve Bayes, SMOTE, sistem pendukung keputusan, klasifikasiAbstract
Stroke merupakan salah satu penyebab kematian dan kecacatan terbesar di dunia, sehingga prediksi dini menjadi kritis untuk mencegah komplikasi serius. Penelitian ini mengembangkan sistem pendukung keputusan untuk memprediksi risiko stroke menggunakan algoritma Naïve Bayes yang dikombinasikan dengan Synthetic Minority Oversampling Technique (SMOTE) guna mengatasi ketidakseimbangan data pada Stroke Prediction Dataset (5110 sampel, 4,87% kasus stroke). Metode penelitian mencakup preprocessing data, penghapusan fitur non-informatif, encoding variabel kategorikal, oversampling menggunakan SMOTE, serta evaluasi performa model menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa SMOTE meningkatkan sensitivitas model secara signifikan, dengan nilai recall 93% dan F1-score 81%, meskipun precision mengalami penurunan akibat bertambahnya prediksi positif palsu. Temuan ini menegaskan pentingnya pemilihan metrik evaluasi yang tepat pada data tidak seimbang. Studi ini memberikan kontribusi dalam pengembangan pipeline prediksi medis berbasis Naïve Bayes dan menawarkan dasar bagi pengembangan model yang lebih akurat melalui optimasi parameter dan algoritma alternatif.
References
Azeraf, E., Monfrini, E., & Pieczynski, W. (2021). Using the Naïve Bayes as a discriminative model. 2021 13th International Conference on Machine Learning and Computing, 106–110. https://doi.org/10.1145/3457682.3457697
Bathla, P., & Kumar, R. (2022). Artificial Intelligence based Model for Brain Stroke Prediction. 2022 IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), 1–6. https://doi.org/10.1109/IATMSI56455.2022.10119373
Carvalho, M., Pinho, A. J., & Brás, S. (2025). Resampling approaches to handle class imbalance: a review from a data perspective. Journal of Big Data, 12(1), 71. https://doi.org/10.1186/s40537-025-01119-4
D, A., & V, U. (2024). Integrating SMOTE and LIME Techniques for Enhanced Stroke Prediction using Machine Learning Approaches. 2024 International Conference on Emerging Technologies in Computer Science for Interdisciplinary Applications (ICETCS), 1–6. https://doi.org/10.1109/ICETCS61022.2024.10544182
Damari, A., Taghfirul Azhima Yoga Siswa, & Wawan Joko Pranoto. (2025). Implementation of the PSO-SMOTE Method on the Naïve Bayes Algorithm to Address Class Imbalance in Landslide Disaster Data. INOVTEK Polbeng - Seri Informatika, 10(1), 332–343. https://doi.org/10.35314/7wcvrb72
Das, D. K., & Chowdhury, S. (2024). Brain Stroke Prediction by Machine Learning Algorithm Along with Boosting Classifier. 2024 4th International Conference on Sustainable Expert Systems (ICSES), 1576–1581. https://doi.org/10.1109/ICSES63445.2024.10763085
Khansa, G. A. F., & Gunawan, P. H. (2024). Predicting Stunting in Toddlers Using KNN and Naïve Bayes Methods. 2024 International Conference on Data Science and Its Applications (ICoDSA), 17–21. https://doi.org/10.1109/ICoDSA62899.2024.10651676
Masood, A., Naseem, U., Rashid, J., Kim, J., & Razzak, I. (2024). Review on enhancing clinical decision support system using machine learning. CAAI Transactions on Intelligence Technology. https://doi.org/10.1049/cit2.12286
Prameswara, A., & Gunawan, P. H. (2024). Predicting Toddler Stunting at Bandarharjo Health Center: Applications of K-Nearest Neighbors and Naïve Bayes Algorithms. 2024 8th International Conference on Electrical, Telecommunication and Computer Engineering (ELTICOM), 30–34. https://doi.org/10.1109/ELTICOM64085.2024.10864390
Rivaldo, V. J., Siswa, T. A. Y., & Pranoto, W. J. (2024). Perbaikan Akurasi Naïve Bayes dengan Chi-Square dan SMOTE Dalam Mengatasi High Dimensional dan Imbalanced Data Banjir. JURNAL MEDIA INFORMATIKA BUDIDARMA, 8(3), 1656. https://doi.org/10.30865/mib.v8i3.7886
Sakho, A., Malherbe, E., & Scornet, E. (2025). Do we need rebalancing strategies? A theoretical and empirical study around SMOTE and its variants. http://arxiv.org/abs/2402.03819
Tompra, K.-V., Papageorgiou, G., & Tjortjis, C. (2024). Strategic Machine Learning Optimization for Cardiovascular Disease Prediction and High-Risk Patient Identification. Algorithms, 17(5), 178. https://doi.org/10.3390/a17050178
Wongvorachan, T., He, S., & Bulut, O. (2023). A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining. Information, 14(1), 54. https://doi.org/10.3390/info14010054
