Stroke adalah gangguan neurologis akibat terganggunya aliran darah ke otak, dan merupakan salah satu penyebab utama kematian serta disabilitas di dunia. Prediksi dini berbasis pembelajaran mesin dapat membantu pencegahan dan penanganan stroke. Penelitian ini membandingkan kinerja algoritma Random Forest dan Decision Tree dalam memprediksi stroke menggunakan dataset Brain Stroke Prediction (4.981 data pasien) yang sangat tidak seimbang, dengan dan tanpa teknik penyeimbangan Random Undersampling (RUS). Kinerja model dievaluasi menggunakan 5-fold stratified cross-validation dengan 5 kali pengulangan dan metrik accuracy, sensitivity, specificity, precision, F1-score, ROC-AUC, dan PR-AUC. Tanpa penyeimbangan, kedua model mencapai akurasi tinggi (sekitar 95%) tetapi gagal mendeteksi kelas minoritas, dengan sensitivity mendekati 0%. Setelah menerapkan RUS, sensitivity meningkat tajam menjadi sekitar 77% untuk Decision Tree dan 81% untuk Random Forest, dengan Random Forest sebagai model terbaik (ROC-AUC 0,82). Hasil ini menunjukkan bahwa teknik penyeimbangan data berperan penting dalam meningkatkan kemampuan model mendeteksi kasus stroke pada dataset yang sangat tidak seimbang.
References
[1] D. Kuriakose and Z. Xiao, “Pathophysiology and treatment of stroke: Present status and future perspectives,” International Journal of Molecular Sciences, vol. 21, no. 20. 2020. doi: 10.3390/ijms21207609.
[2] V. L. Feigin et al., “World Stroke Organization (WSO): Global Stroke Fact Sheet 2022,” International Journal of Stroke, vol. 17, no. 1. 2022. doi: 10.1177/17474930211065917.
[3] M. Yousufuddin and N. Young, “Aging and ischemic stroke,” Aging, vol. 11, no. 9. 2019. doi: 10.18632/aging.101931.
[4] K. M. Rexrode, T. E. Madsen, A. Y. X. Yu, C. Carcel, J. H. Lichtman, and E. C. Miller, “The Impact of Sex and Gender on Stroke,” Circ Res, vol. 130, no. 4, 2022, doi: 10.1161/CIRCRESAHA.121.319915.
[5] M. M. Martin-Saez and N. James, “The experience of occupational identity disruption post stroke: a systematic review and meta-ethnography,” Disabil Rehabil, vol. 43, no. 8, 2021, doi: 10.1080/09638288.2019.1645889.
[6] Y. Ge, M. Zadeh, C. Yang, E. Candelario-Jalil, and M. Mohamadzadeh, “Ischemic Stroke Impacts the Gut Microbiome, Ileal Epithelial and Immune Homeostasis,” iScience, vol. 25, no. 11, 2022, doi: 10.1016/j.isci.2022.105437.
[7] E. C. Chiu, F. C. Chi, and P. T. Chen, “Investigation of the home-reablement program on rehabilitation outcomes for people with stroke: A pilot study,” Medicine (United States), vol. 100, no. 26, 2021, doi: 10.1097/MD.0000000000026515.
[8] P. B. Gorelick, “The global burden of stroke: persistent and disabling,” The Lancet Neurology, vol. 18, no. 5. 2019. doi: 10.1016/S1474-4422(19)30030-4.
[9] F. T. Kurdi, “Random Forest Machine Learning Technique for Automatic Vegetation Detection and Modelling in LiDAR Data,” International Journal of Environmental Sciences & Natural Resources, vol. 28, no. 2, 2021, doi: 10.19080/ijesnr.2021.28.556234.
[10] C. M. YEŞİLKANAT, “Spatio-temporal estimation of the daily cases of COVID-19 in worldwide using Random Forest machine learning algorithm,” Chaos Solitons Fractals, vol. 140, 2020, doi: 10.1016/j.chaos.2020.110210.
[11] N. Widjiyati, “Implementasi Algoritme Random Forest Pada Klasifikasi Dataset Credit Approval,” Jurnal Janitra Informatika dan Sistem Informasi, vol. 1, no. 1, 2021, doi: 10.25008/janitra.v1i1.118.
[12] T. Lu, Y. Huang, W. Zhao, and J. Zhang, “The Metering Automation System based IntRUSion Detection Using Random Forest Classifier with SMOTE+ENN,” in Proceedings of IEEE 7th International Conference on Computer Science and Network Technology, ICCSNT 2019, 2019. doi: 10.1109/ICCSNT47585.2019.8962430.
[13] B. Charbuty and A. Abdulazeez, “Classification Based on Decision Tree Algorithm for Machine Learning,” Journal of Applied Science and Technology Trends, vol. 2, no. 01, pp. 20–28, Mar. 2021, doi: 10.38094/jastt20165.
[14] I. D. Mienye, Y. Sun, and Z. Wang, “Prediction performance of improved decision tree-based algorithms: A review,” in Procedia Manufacturing, 2019. doi: 10.1016/j.promfg.2019.06.011.
[15] E. Dritsas and M. Trigka, "Stroke Risk Prediction with Machine Learning Techniques," Sensors, vol. 22, no. 13, p. 4670, 2022, doi: 10.3390/s22134670.
[16] N. Biswas, K. M. M. Uddin, S. T. Rikta, and S. K. Dey, "A comparative analysis of machine learning classifiers for stroke prediction: A predictive analytics approach," Healthcare Analytics, vol. 2, p. 100116, 2022, doi: 10.1016/j.health.2022.100116.
[17] T. Tazin, M. N. Alam, N. N. Dola, M. S. Bari, S. Bourouis, and M. M. Khan, "Stroke Disease Detection and Prediction Using Robust Learning Approaches," Journal of Healthcare Engineering, vol. 2021, art. 7633381, 2021, doi: 10.1155/2021/7633381.
[18] T. Liu, W. Fan, and C. Wu, "A hybrid machine learning approach to cerebral stroke prediction based on imbalanced medical dataset," Artificial Intelligence in Medicine, vol. 101, art. 101723, 2019, doi: 10.1016/j.artmed.2019.101723.
[19] M. Carvalho, A. J. Pinho, and S. Brás, "Resampling approaches to handle class imbalance: a review from a data perspective," Journal of Big Data, vol. 12, no. 1, art. 71, 2025, doi: 10.1186/s40537-025-01119-4.