Implementasi Artificial Neural Network (ANN) untuk Memprediksi Risiko Penyakit Stroke

Authors

  • Bintang Nauli Mariana IPB University
  • Septiana Isna Dian Noor IPB University
  • Haifa Hanadia IPB University
  • Marisa Adelia IPB University
  • Nova Belinda IPB University
  • Mardiana Tri Sukmaningrum IPB University
  • Elis Khatizah IPB University
  • Mohamad Khoirun Najib IPB University
  • Nicholas Abisha IPB University

DOI:

https://doi.org/10.34010/jati.v16i2.19224

Keywords:

Artificial neural networks, Machine Learning, Prediksi Stroke, SHAP, SMOTE

Abstract

Stroke merupakan salah satu penyebab utama kematian dan kecacatan dengan prevalensi yang terus meningkat, sementara deteksi dini masih menjadi tantangan akibat keterbatasan sistem prediktif yang akurat. Penelitian ini dilakukan untuk mengembangkan model prediksi risiko stroke menggunakan Artificial Neural Network (ANN) berbasis data klinis dan demografis, sekaligus meningkatkan interpretabilitas melalui analisis SHAP (Shapley Additive exPlanations). Dataset yang digunakan merupakan data publik Stroke Prediction yang terdiri dari 5.110 data pasien dengan 11 variabel prediktor dan satu variabel target. Tahapan penelitian meliputi eksplorasi data, pra-pemrosesan berupa imputasi nilai hilang, label encoding, normalisasi fitur, serta penanganan ketidakseimbangan kelas menggunakan Synthetic Minority Oversampling Technique (SMOTE). Model ANN dibangun menggunakan arsitektur Multi-Layer Perceptron dengan dua lapisan tersembunyi dan dilatih menggunakan Adam optimizer serta fungsi kerugian binary cross-entropy. Hasil evaluasi menunjukkan kemampuan prediksi yang cukup tinggi, dengan nilai akurasi sebesar 92,73%, presisi 0,90, recall 0,96, specificity 0,89, F1-score 0,93, dan AUC 0,928. Analisis SHAP mengidentifikasi usia, BMI, tipe pekerjaan, kebiasaan merokok, dan kadar glukosa rata-rata sebagai fitur paling berpengaruh, menegaskan bahwa model tidak hanya akurat tetapi juga interpretatif. Metode ini berpotensi digunakan sebagai alat skrining dini risiko stroke berbasis sistem pendukung keputusan.

Views: 112Downloads: 143

Downloads

Download data is not yet available.

References

[1] V. L. Feigin et al., “World Stroke Organization: Global Stroke Fact Sheet 2025,” International Journal of Stroke, vol. 20, no. 2, pp. 132–144, 2025, doi: 10.1177/17474930241308142.

[2] GBD 2019 Stroke Collaborators. Global, regional, and national burden of stroke and its risk factors, 1990–2019: a systematic analysis for the Global Burden of Disease Study 2019. The Lancet Neurology, vol. 20, no. 10, pp. 795–820, 2021, doi.org/10.1016/S1474-4422(21)00252-0.

[3] Kemenkes, “Riset Kesehatan Dasar Nasional,” Riskesdas, p. 76, 2018.

[4] I. Z. Sadiq et al., “Data-driven diabetes mellitus prediction and management : a comparative evaluation of decision tree classifier and artificial neural network models along with statistical analysis,” Scientific Reports, vol. 15, pp. 1–16, 2025, doi.org/10.1038/s41598-025-03718-w.

[5] I. Werdiningsih et al., “Analisis Prediksi Stroke Menggunakan Pendekatan Decision Tree dengan Seleksi Fitur dan Neural Network,” Jurnal Sistem Cerdas, vol. 6, no. 3, pp. 213–221, 2023, doi: 10.37396/jsc.v6i3.310.

[6] H. Park and K. Kim, “An artificial neural network approach to predicting stroke in postmenopausal women,” Iranian Journal of Public Health, vol. 51, no. 4, pp. 964–966, Apr. 2022, doi: 10.18502/ijph.v51i4.9261.

[7] G. Branco, P. Torgo, and R. P. Ribeiro, “Data imbalance in classification: Experimental evaluation,” Information Sciences, vol. 513, pp. 429–441, 2020, doi: 10.1016/j.ins.2019.11.004.

[8] N. A. Yosephine and Ratnadewi, “Penggunaan Artificial Neural Network pada Sinyal Elektrokardiogram untuk Mendeteksi Penyakit Jantung Aritmia Supraventrikular,” INFORMASI : Jurnal Informatika dan Sistem Informasi, vol. 13, no. 1, pp. 14–23, May 2021, doi: 10.37424/informasi.v13i1.69.

[9] W. Rahmadani, A. F. Wijaya, and M. N. Umar, “Penerapan Algoritma Artificial Neural Network Untuk Memprediksi Penyakit Gagal Jantung,” JSI: Jurnal Sistem Informasi (E-Journal), vol. 16, no. 1, pp. 95–104, Apr. 2024, doi: 10.18495/jsi.v16i1.148.

[10] C. W. Yoon and C. D. Bushnell, “Stroke in women: A review focused on epidemiology, risk factors, and outcomes,” Journal of Stroke, vol. 25, no. 1, pp. 2–15, 2023, doi: 10.5853/jos.2022.03468.

[11] J. T. Hancock and T. M. Khoshgoftaar, “Survey on categorical data for neural networks,” J. Big Data, vol. 7, no. 1, p. 28, 2020, doi: 10.1186/s40537-020-00305-w.

[12] A. Elreedy and A. F. Atiya, “A comprehensive analysis of synthetic minority oversampling technique (SMOTE) for handling class imbalance,” Information Sciences, vol. 505, pp. 32–64, 2019, doi: 10.1016/j.ins.2019.07.070.

[13] E. Khatizah, “Konsep Matematika di Balik Jaringan Saraf Tiruan Sebagai fondasi Kecerdasan Buatan,” MILANG Journal of Mathematics and Its Applications, vol. 20, no. 2, pp. 145–156, Dec. 2024, doi:10.29244/milang.20.2.145-156.

[14] C. T. M. Sitanggang, T. Novianti, and S. Amar, “Analisis neural network dengan metode backpropagation dalam melakukan peramalan terhadap produksi daging sapi,” Prosiding Seminar Nasional Waluyo Jatmiko, vol. 16, no. 1, pp. 81–90, 2023, doi: 10.33005/wj.v16i1.46.

[15] T. S. Qaid, H. Mazaar, M. Y. H. Al-shamri, M. S. Alqahtani, A. A. Raweh, and W. Alakwaa, “Hybrid Deep-Learning and Machine-Learning Models for Predicting COVID-19,” Computational Intelligence and Neuroscience., vol. 2021, 2021, doi: https://doi.org/10.1155/2021/9996737.

[16] M. J. Ferdous and R. Shahriyar, “Healthcare Analytics An ensemble convolutional neural network model for brain stroke prediction using brain computed tomography images,” Healthc. Anal., vol. 6, no. July, p. 100368, 2024, doi: 10.1016/j.health.2024.100368.

[17] O. O. Bifarin, “Interpretable machine learning with tree-based Shapley additive explanations: Application to metabolomics datasets for binary classification,” PLOS ONE, vol. 18, no. 5, 2023, doi: 10.1371/journal.pone.0284315.

[18] A. Jadhav, D. Pramod, and K. Ramanathan, “Comparison of Performance of Data Imputation Methods for Numeric Dataset,” Applied Artificial Intelligence, vol. 33, no. 10, pp. 913–933, 2019, doi: 10.1080/08839514.2019.1637138.

[19] M. H. Ariansyah, S. Winarno, E. N. Fitri, and H. M. A. Retha, “Multi-layer perceptrone for diagnosing stroke with the SMOTE method in overcoming data imbalance,” Innovation in Research of Informatics, vol. 5, no. 1, pp. 1-8, 2023, doi: 10.37058/innovatics.v5i1.6565.

[20] R. Miotto, F. Wang, S. Wang, X. Jiang, and J. T. Dudley, “Deep learning for healthcare: Review, opportunities and challenges,” Briefings in Bioinformatics, vol. 19, no. 6, pp. 1236–1246, 2018, doi: 10.1093/bib/bbx044.

[21] P. O. Akinwumi, S. Ojo, T. I. Nathaniel, J. Wanliss, O. Karunwi, and M. Sulaiman, “Evaluating machine learning models for stroke prediction based on clinical variables,” Frontiers in Neurology, vol. 16, 2025, doi:10.3389/fneur.2025.1668420.

[22] M. H. Shirvan, M. H. Moattar, and M. Hosseinzadeh, “Deep generative approaches for oversampling in imbalanced data classification problems: A comprehensive review and comparative analysis,” Applied Soft Computing, vol. 170, 2025, doi:10.1016/j.asoc.2024.112677.

[23] E. E. Diri, G. O. Diri, C. O. Rita, L. G. Nbaakee, G. Unula, and T. I. Kingsley, “ Optimising stroke recurrence prediction using minimal clinical features and machine learning models,” International Journal of Innovative Science and Research Technology, vol. 10, no.9, pp. 780–794, 2025, doi: 10.38124/ijisrt/25sep706.

[24] A. Gupta, N. Mishra, N. Jatana, S. Malik, K. A. Gepreel, F. Asmat, and S. N. Mohanty, “Predicting stroke risk: An effective stroke prediction model based on neural networks,” Journal of Neurorestoratology, vol. 13, no. 1, 2025, doi:10.1016/j.jnrt.2024.100156.

Downloads

Published

30.09.2026

How to Cite

[1]
“Implementasi Artificial Neural Network (ANN) untuk Memprediksi Risiko Penyakit Stroke”, JATI, vol. 16, no. 2, pp. 1–10, Sep. 2026, doi: 10.34010/jati.v16i2.19224.