Implementasi Klasifikasi Dosis Obat Pil Menggunakan Naive Bayes Pada Penyakit Gagal Jantung
Abstract
Penyakit gagal jantung memerlukan pengelolaan dosis obat yang tepat untuk meningkatkan efektivitas pengobatan. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi dosis obat menggunakan algoritma Naive Bayes dengan pendekatan Gaussian dan Multinomial, serta meningkatkan performa model dengan teknik oversampling SMOTE dan VAE. Data pasien diklasifikasikan berdasarkan usia, jenis kelamin, berat badan, riwayat penyakit, metabolisme, dan toleransi obat. Implementasi sistem dilakukan melalui GUI berbasis Tkinter, memungkinkan pengguna memasukkan data pasien dan mendapatkan prediksi dosis obat yang sesuai. Hasil evaluasi menunjukkan bahwa kombinasi Naive Bayes dengan SMOTE memberikan performa terbaik dengan akurasi 73,90%, presisi 74,99%, recall 73,36%, dan F1-score 73,90%. Metode VAE memiliki performa lebih rendah dibandingkan SMOTE. Analisis lebih lanjut menunjukkan bahwa Bernoulli Naive Bayes memiliki akurasi tertinggi dalam klasifikasi tanpa oversampling, sementara model Naive Bayes standar kurang efektif dalam menangani data multi-label. Kesimpulannya, pendekatan Naive Bayes dengan oversampling SMOTE dapat meningkatkan akurasi prediksi dosis obat bagi pasien gagal jantung dan dapat digunakan sebagai alat bantu dalam pengambilan keputusan klinis.
Kata kunci— Naive Bayes, Klasifikasi dosis obat, Gagal Jantung, SMOTE, VAE, GUI
References
[1] H. Nursita and A. Pratiwi, “Peningkatan Kualitas Hidup Pada Pasien Gagal Jantung: A Narrative Review Article,” J. Ber. Ilmu Keperawatan, vol. 13, no. 1, p. 11, 2020, [Online]. Available: https://doi.org/10.23917/bik.v13i1.11916
[2] O. P. Barus, K. Lauwren, J. J. Pangaribuan, and Romindo, “Implementation of the Naive Bayes Algorithm to Predict the Safety of Heart Failure Patients,” Conf. Ser., vol. 4, no. 1, pp. 172–177, 2023, doi: 10.34306/conferenceseries.v4i1.651.
[3] P. Subarkah, W. R. Damayanti, and R. A. Permana, “Comparison of Correlated Algorithm Accuracy Naive Bayes Classifier and Naive Bayes Classifier for Classification of heart failure,” Ilk. J. Ilm., vol. 14, no. 2, pp. 120–125, 2022, doi: 10.33096/ilkom.v14i2.1148.120-125.
[4] C. J. Lee et al., “Heart Failure Statistics 2024 Update: A Report From the Korean Society of Heart Failure,” Int. J. Hear. Fail., vol. 6, no. 2, pp. 56–69, 2024, doi: 10.36628/ijhf.2024.0010.
[5] R. J. Mentz et al., “Influence of documented history of coronary artery disease on outcomes in patients admitted for worsening heart failure with reduced ejection fraction in the EVEREST trial,” Eur. J. Heart Fail., vol. 15, no. 1, pp. 61–68, 2013, doi: 10.1093/eurjhf/hfs139.
[6] B. F. Tetzlaff WF, Meroño T, Menafra M, Martin M, Botta E, Matoso MD, Sorroche P, De Paula JA, Boero LE, “World Journal of Cardiology ,” World J. Cardiol., vol. 9, no. 5, 2017, doi: 10.4330/wjc.v9.i5.448.
[7] S. Ray, “History of Valvular Heart Disease,” Clin. Med. (Northfield. Il)., vol. 10, no. 2, pp. 168–171, 2010.
[8] F. H. Messerli, S. F. Rimoldi, and S. Bangalore, “The Transition From Hypertension to Heart Failure: Contemporary Update,” JACC Hear. Fail., vol. 5, no. 8, pp. 543–551, 2017, doi: 10.1016/j.jchf.2017.04.012.
[9] P. M. Seferović et al., “Heart failure in cardiomyopathies: a position paper from the Heart Failure Association of the European Society of Cardiology,” Eur. J. Heart Fail., vol. 21, no. 5, pp. 553–576, 2019, doi: 10.1002/ejhf.1461.
[10] Dian Rozani, “Rheumatic Heart Disease Causes Heart Failure. How is It Treated?,” Cardiovasc. Cardiometabolic J., vol. 4, no. 1, pp. 38–48, 2023, doi: 10.20473/ccj.v4i1.2023.38-48.
[11] D. Tousoulis, E. Oikonomou, G. Siasos, and C. Stefanadis, “Bidirectional Relationship From Diabetes Mellitus to Heart Failure,” Eur Cardiol, vol. 9, no. 1, pp. 37–42, 2024.
[12] N. M. Hawkins, M. C. Petrie, P. S. Jhund, G. W. Chalmers, F. G. Dunn, and J. J. V. McMurray, “Heart failure and chronic obstructive pulmonary disease: Diagnostic pitfalls and epidemiology,” Eur. J. Heart Fail., vol. 11, no. 2, pp. 130–139, 2009, doi: 10.1093/eurjhf/hfn013.
[13] “Carvedilol - StatPearls - NCBI Bookshelf.” Accessed: Jun. 28, 2024. [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK534868/
[14] “Metoprolol - StatPearls - NCBI Bookshelf.” Accessed: Jun. 28, 2024. [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK532923/
[15] “Lisinopril - StatPearls - NCBI Bookshelf.” Accessed: Jun. 28, 2024. [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK482230/
[16] C. Aspirin, “Cardio spirin ®,” vol. 1003661200, pp. 5–10, 2021.
[17] J. Daniel and J. H. Martin, “Chapter 4 Naive Bayes, Text Classification, and Sentiment | Speech and Language Processing,” 2023.
[18] D. J. Maulana, Siti Saadah, and Prasti Eko Yunanto, “Kmeans-SMOTE Integration for Handling Imbalance Data in Classifying Financial Distress Companies using SVM and Naïve Bayes,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 8, no. 1, pp. 54–61, 2024, doi: 10.29207/resti.v8i1.5140.
[19] C. Zhang et al., Over-Sampling Algorithm Based on VAE in Imbalanced Classification, vol. 10967 LNCS. Springer International Publishing, 2018. doi: 10.1007/978-3-319-94295-7_23.
[20] K. M. Ting, “Confusion Matrix,” Encycl. Mach. Learn. Data Min., no. October, pp. 260–260, 2017, doi: 10.1007/978-1-4899-7687-1_50.
