IMPLEMENTASI ALGORITMA NAÏVE BAYES UNTUK PREDIKSI RISIKO RELAPS PADA SISTEM MONITORING PASIEN REHABILITASI NARKOBA
DOI:
https://doi.org/10.55123/storage.v5i3.8209Keywords:
Gaussian Naïve Bayes, Relaps, Rehabilitasi Narkoba, Smote, Sistem MonitoringAbstract
Penelitian ini bertujuan mengimplementasikan algoritma Gaussian Naïve Bayes pada sistem Analisis Risiko Relaps untuk memprediksi risiko relaps pasien rehabilitasi narkoba secara cepat, terstruktur, dan berbasis data. Sistem dikembangkan menggunakan Python, Streamlit, dan MySQL dengan pendekatan Research and Development. Tahapan penelitian meliputi pengumpulan data, prapemrosesan, encoding, standardisasi, SMOTE, pembagian data 80:20, pelatihan model, evaluasi, dan implementasi sistem. Variabel prediktor mencakup usia, riwayat pakai, hasil tes urine, lama pakai, status kerja, dan dukungan keluarga. Dari 87 data sampel pemeriksaan dengan 76 pasien unik, sistem mengklasifikasikan 44 pasien berisiko tinggi dan 32 pasien berisiko rendah. Evaluasi awal pada 18 data uji menghasilkan accuracy, precision, recall, dan F1-score sebesar 1,00. Meskipun hasil ini menunjukkan performa model yang sangat baik pada data uji, ukuran sampel pengujian yang masih terbatas menyebabkan hasil tersebut belum dapat digeneralisasi secara luas. Oleh karena itu, sistem masih memerlukan pengujian lebih lanjut menggunakan dataset yang lebih besar, lebih beragam, serta validasi silang untuk memastikan stabilitas dan generalisasi model sebelum diterapkan secara operasional dalam skala luas.
Downloads
References
Aryuni, M. et al. (2023) ‘Imbalanced learning in heart disease categorization: Improving minority class prediction accuracy using the SMOTE algorithm’, International Journal of Fuzzy Logic and Intelligent Systems, 23(2), pp. 140–151. Available at: https://doi.org/10.5391/IJFIS.2023.23.2.140.
Buga, R. et al. (2025) ‘Streamlit application and deep learning model for brain metastasis monitoring after Gamma Knife treatment’, Biomedicines, 13(2), p. 423. Available at: https://doi.org/10.3390/biomedicines13020423.
Cobrado, U.N. et al. (2024) ‘Access control solutions in electronic health record systems: A systematic literature review’, Healthcare Analytics, 5, p. 100311.
Hairani, H. et al. (2024) ‘Addressing class imbalance of health data: A systematic literature review on SMOTE-based approaches’, JOIV: International Journal on Informatics Visualization, 8(2).
Kurniawan, W.I. et al. (2025) ‘Application of Naïve Bayes Classifiers for family risk classification’, Journal of Applied Informatics and Computing [Preprint].
Li, Y. et al. (2025) ‘An improved SMOTE algorithm for enhanced imbalanced data classification’, Scientific Reports, 15, p. 18495. Available at: https://doi.org/10.1038/s41598-025-03105-3.
Marfalino, H. et al. (2023) ‘Penerapan sistem pakar dalam diagnosa pengguna narkoba menggunakan metode Naïve Bayes’, Jurnal Sains Informatika Terapan, 2(2), pp. 30–34. Available at: https://doi.org/10.62357/jsit.v2i2.159.
de Mattos, B.P. et al. (2024) ‘Craving for a robust methodology: A systematic review of machine learning algorithms on substance-use disorders treatment outcomes’, International Journal of Mental Health and Addiction [Preprint]. Available at: https://doi.org/10.1007/s11469-024-01403-z.
Navaei, M. and Tabrizi, N. (2022) ‘Machine learning in software development life cycle: A comprehensive review’, in Proceedings of the 17th International Conference on Evaluation of Novel Approaches to Software Engineering, pp. 521–528.
Nugraha, K.A., Okrpana, H. and Sormin, R.K. (2022) ‘Implementasi algoritma Naïve Bayes dalam mengklasifikasi pasien test urine pada BNN Pematangsiantar’, ZAHRA: Bulletin Big Data, Data Science, and Artificial Intelligence, 1(1), pp. 34–43.
Pamungkas, B.P., Vikri, M.J. and Sa’ida, I.A. (2025) ‘Application of SMOTE-ENN method in data balancing for classification of diabetes health indicators with C4.5 algorithm’, Jurnal SISFOKOM Sistem Informasi dan Komputer, 14(2), pp. 183–188. Available at: https://doi.org/10.32736/sisfokom.v14i2.2350.
Puspitasari, N. et al. (2024) ‘Classification for determining the level of drugs dependence using the Naïve Bayes Classifier’, IT Journal Research and Development, 9(1), pp. 68–79. Available at: https://doi.org/10.25299/itjrd.2024.16319.
Revathy, S.P., Sindhuja, M. and Jayashree, R. (2025) ‘Streamlit-based web application for Parkinson’s detection using machine learning’, Journal of Artificial Intelligence and Capsule Networks, 6(4), pp. 466–478. Available at: https://doi.org/10.36548/jaicn.2024.4.006.
Setiawan, Z. et al. (2023) Buku Ajar Data Mining. PT. Sonpedia Publishing Indonesia.
Situmorang, R.D., Sumarno and Hidayati, N. (2022) ‘Penerapan data mining dalam klasifikasi pencegahan narkoba menggunakan algoritma Naïve Bayes di BNN Kota Pematangsiantar’, JOMLAI: Journal of Machine Learning and Artificial Intelligence, 1(4), pp. 295–302. Available at: https://doi.org/10.55123/jomlai.v1i4.1667.
Susanto, A.P. et al. (2023) ‘Effects of machine learning-based clinical decision support systems on decision-making, care delivery, and patient outcomes: A scoping review’, Journal of the American Medical Informatics Association, 30(12), pp. 2050–2063. Available at: https://doi.org/10.1093/jamia/ocad180.
Wibowo, J.J. (2025) ‘A comparative analysis of SMOTE and Naïve Bayes for heart disease classification’, JOIV: International Journal on Informatics Visualization, 9(1), pp. 160–167. Available at: https://doi.org/10.62527/joiv.9.1.3248.
Xu, J. et al. (2025) ‘The risk factors for relapse behavior in individuals with substance use disorders: An interpretable machine learning study’.
Yaseliani, M., Soryani, M. and Setarehdan, S.K. (2024) ‘Diagnostic clinical decision support based on deep learning and decision fusion for psoriasis classification and treatment recommendation’, Computers in Biology and Medicine, 168, p. 107778. Available at: https://doi.org/10.1016/j.compbiomed.2023.107778.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Steve Jeremy Rarumangkay, Yonathan Kazu Datumbanua, Levi Elia Pitoy, Marike Amelda Silvia Kondoj, Franky Gerald Cliford Manoppo
This work is licensed under a Creative Commons Attribution 4.0 International License.
