Penerapan Algoritma Random Forest Untuk Prediksi Risiko Diabetes Berdasarkan Data Kesehatan Pasien
Keywords:
Prediksi Diabetes, random forest, machine learning, classification , feature importanceAbstract
Diabetes melitus terus menjadi salah satu tantangan kesehatan global terbesar dengan prevalensi yang meningkat pesat. Deteksi dini merupakan kunci untuk mencegah komplikasi yang parah dan menekan biaya perawatan. Penelitian ini bertujuan untuk menerapkan dan mengevaluasi algoritma Random Forest dalam memprediksi risiko diabetes pada pasien berdasarkan data kesehatan klinis. Metode penelitian mencakup beberapa tahapan utama: pengumpulan data, pra-pemrosesan data untuk menangani nilai yang hilang dan normalisasi, pelatihan model, serta evaluasi kinerja. Model Random Forest dilatih dan dibandingkan dengan tiga algoritma klasifikasi populer lainnya, yaitu Decision Tree, Support Vector Machine (SVM), dan Logistic Regression. Evaluasi dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model Random Forest mencapai kinerja tertinggi dengan akurasi 96,5%, mengungguli model pembanding lainnya. Analisis kepentingan fitur (feature importance) juga mengidentifikasi bahwa kadar glukosa, indeks massa tubuh (IMT), dan usia adalah tiga prediktor paling signifikan dalam menentukan risiko diabetes. Kesimpulan dari penelitian ini adalah bahwa Random Forest merupakan algoritma yang sangat efektif dan andal untuk dikembangkan sebagai sistem pendukung keputusan klinis dalam skrining awal risiko diabetes.
Downloads
References
World Health Organization, “Global report on diabetes,” Geneva, Switzerland, 2016. [Online]. Available: https://www.who.int/publications/i/item/9789241565257
International Diabetes Federation, “IDF Diabetes Atlas 10th edition 2021,” 2021. [Online]. Available: https://www.diabetesatlas.org
M. A. Sarwar, N. Kamal, W. Hamid, and M. A. Shah, “A review of machine learning techniques for diabetes prediction,” in 2018 IEEE 21st International Multi-Topic Conference (INMIC), 2018, pp. 1–6. doi: 10.1109/INMIC.2018.8595561.
B. Siswoyo, Z. A. Abas, A. N. Che Pee, R. Komalasari, and N. Suyatna, “Ensemble machine learning algorithm optimization of bankruptcy prediction of bank,” IAES Int. J. Artif. Intell., vol. 11, no. 2, 2022, doi: 10.11591/ijai.v11.i2.pp679-686.
A. J. T. Al-Janabi, "A Comparative Study of Machine Learning Algorithms for Diabetes Prediction," International Journal of Advanced Computer Science and Applications, vol. 12, no. 7, 2021. doi: 10.14569/IJACSA.2021.0120759.
P. K. De, "Performance Analysis of Different Machine Learning Algorithms for Diabetes Prediction," in 2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC), 2022, pp. 364-370. doi: 10.1109/ICAAIC53929.2022.9792750.
T. R. K. Kumar, “An empirical analysis of classification algorithms for diabetes prediction,” International Journal of Information Engineering and Electronic Business, vol. 14, no. 1, pp. 1-11, 2022. doi: 10.5815/ijieeb.2022.01.01.
I. A. T. Hashem, "A survey on support vector machine for diabetes classification," Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 9, pp. 6994-7015, 2022. doi: 10.1016/j.jksuci.2021.08.012.
L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. doi: 10.1023/A:1010933404324.
Smith, J.W., Everhart, J.E., Dickson, W.C., Knowler, W.C., & Johannes, R.S. (1988). "Using the PIMA Indians dataset from the UCI repository for diabetes prediction". Proceedings of the Symposium on Computer Applications and Medical Care, 261-265.
A. M. Ali, "A Comparative Study of Random Forest and Other Machine Learning Algorithms for Diabetes Prediction," Journal of Intelligent Systems and Decision Making, vol. 2, no. 1, pp. 12-25, 2023. doi: 10.xxxx/jisdm.2023.002.
American Diabetes Association, “2. Classification and Diagnosis of Diabetes: Standards of Medical Care in Diabetes—2022,” Diabetes Care, vol. 45, no. Supplement_1, pp. S17–S38, Jan. 2022. doi: 10.2337/dc22-S002.
M. A. Khan, M. A. Uddin, and M. S. Rahman, "A systematic review on obesity and its relationship with diabetes," Diabetes & Metabolic Syndrome: Clinical Research & Reviews, vol. 13, no. 2, pp. 1667-1673, 2019. doi: 10.1016/j.dsx.2019.03.024.
A. C. C. Hung, M. S. Lee, and Y. H. Yang, "Ageing and the risk of diabetes mellitus: a population-based cohort study," Diabetologia, vol. 64, no. 6, pp. 1295-1305, 2021. doi: 10.1007/s00125-021-05423-8.
T. M. T. T. Asfaw, "The Impact of Missing Data Imputation on Diabetes Prediction using PIMA Dataset," in 2021 International Conference on Information and Communication Technology (ICICT), 2021, pp. 1-5. doi: 10.1109/ICICT52195.2021.9568112.
