Arsitektur Evolutionary Stacking Ensemble Berbasis Algoritma Genetik untuk Klasifikasi Penyakit Jantung Koroner
Keywords:
Penyakit Jantung Koroner, Stacking Ensemble, Algoritma Genetik, Klasifikasi, Hyperparameter TuningAbstract
Deteksi dini penyakit jantung koroner memerlukan sistem klasifikasi yang akurat dan handal. Penelitian ini bertujuan mengoptimalkan kinerja arsitektur Stacking Ensemble melalui penerapan Algoritma Genetik. Dataset penelitian mencakup 56 atribut klinis rekam medis pasien. Algoritma Genetik secara iteratif melakukan penalaan hyperparameter untuk menemukan konfigurasi model terbaik dan mencegah overfitting. Hasil eksperimen menunjukkan model Evolutionary Stacking mencapai tingkat akurasi sebesar 85,25%, meningkat dibandingkan model baseline sebesar 81,97%. Sistem berhasil meningkatkan spesifisitas hingga 66,67% dan mereduksi kasus alarm palsu dari 9 menjadi 6 kasus. Kurva ROC mencatatkan nilai AUC sebesar 0,8734 yang mengonfirmasi stabilitas prediksi model. Kesimpulan penelitian ini menegaskan bahwa integrasi algoritma evolusioner efektif dalam menangani ketimpangan data medis. Arsitektur yang diusulkan terbukti mampu beroperasi sebagai instrumen pendukung keputusan klinis yang efisien bagi tenaga medis.
References
[1] H. G. Lee et al., “Machine learning approaches that use clinical , laboratory , and electrocardiogram data enhance the prediction of obstructive coronary artery disease,” Sci. Rep., vol. 13, no. 1, pp. 1–12, 2023, doi: 10.1038/s41598-023-39911-y.
[2] B. Jaltotage, J. Lu, and G. Dwivedi, “Use of Arti fi cial Intelligence Including Multimodal Systems to Improve the Management of Cardiovascular Disease,” Can. J. Cardiol., vol. 40, no. 10, pp. 1804–1812, 2024, doi: 10.1016/j.cjca.2024.07.014.
[3] S. Zhang, Y. Yuan, Z. Yao, J. Yang, X. Wang, and J. Tian, “Coronary Artery Disease Detection Model Based on Class Balancing Methods and LightGBM Algorithm,” Electronics, vol. 11, no. 9, p. 1495, 2022, doi: 10.3390/electronics11091495.
[4] O. Ayotunde and N. Cavus, “A systematic review on the impact of artificial intelligence on electrocardiograms in cardiology,” Int. J. Med. Inform., vol. 195, no. December 2024, p. 105753, 2025, doi: 10.1016/j.ijmedinf.2024.105753.
[5] C. Krantsevich, “Digital medicine and the curse of dimensionality,” npj Digit. Med, vol. 4, no. 153, pp. 1–8, 2021, doi: 10.1038/s41746- 021-00521-5.
[6] X. Wang et al., “Unveiling novel bladder cancer associations from multicentred primary and secondary care electronic health records by machine learning : a case-control study,” J. Biomed. Inform., vol. 172, no. November, p. 104959, 2025, doi: 10.1016/j.jbi.2025.104959.
[7] M. Salmi, D. Atif, D. Oliva, A. Abraham, and S. Ventura, Handling imbalanced medical datasets : review of a decade of research, vol. 57, no. 10. Springer Netherlands, 2024. doi: 10.1007/s10462-024-10884-2.
[8] C. J. Hellín, A. A. Olmedo, and A. Tayebi, “Unraveling the Impact of Class Imbalance on Deep-Learning Models for Medical Image Classification,” Appl. Sci., vol. 14, no. 8, p. 3419, 2024, doi: doi.org/10.3390/app14083419.
[9] P. Mahajan, S. Uddin, F. Hajati, M. Ali, and M. Ergun, “A comparative evaluation of machine learning ensemble approaches for disease prediction using multiple datasets,” Health Technol. (Berl)., vol. 14, pp. 597–613, 2024, doi: 10.1007/s12553-024-00835-w.
[10] J. Hamdard, J. Hamdard, J. Hamdard, and J. Hamdard, “OPTIMIZING HEART DISEASE PREDICTION MODELS USING GENETIC ALGORITHMS : A METAHEURISTIC APPROACH,” J. Theor. Appl. Inf. Technol., vol. 102, no. 9, pp. 3868–3881, 2024.
[11] K. Natarajan, V. V. Kumar, T. R. M. Mohamed, and A. Nirmaladevi, “Efficient Heart Disease Classification Through Stacked Ensemble with Optimized Firefly Feature Selection,” Int. J. Comput. Intell. Syst., vol. 0, 2024, doi: 10.1007/s44196-024-00538-0.
[12] T. Classifiers, G. A. Radwan, and M. H. Khafagy, “Coronary Artery Disease Prediction by Combining,” J. Inf. Hiding Multimed. Signal Process., vol. 15, no. 4, pp. 221–235, 2024.
[13] A. Jafarnejad, “Predicting Heart Disease Using Automated Machine Learning Based on Genetic Algorithms,” J. Inf. Technol. Manag., vol. 17, no. 2, pp. 91–122, 2025, doi: 10.22059/jitm.2024.382556.3829.
