SISTEM PREDIKSI MULTI-PENYAKIT BERBASIS GEJALA DENGAN KELUARAN PROBABILITAS TIGA TERATAS MENGGUNAKAN ALGORITMA RANDOM FOREST
DOI:
https://doi.org/10.70248/jcsit.v3i4.4478Abstract
Beberapa penyakit umum seperti malaria, demam berdarah dengue (DBD), tifoid, infeksi saluran pernapasan akut (ISPA), dan Gastroenteritis memiliki gejala awal yang saling tumpang tindih sehingga sering menyulitkan identifikasi dini pada fasilitas kesehatan tingkat pertama, salah satunya Klinik Banda Neira yang saat ini masih melakukan identifikasi gejala secara manual. Penelitian ini bertujuan membangun sistem pendukung keputusan (decision support system) berbasis web menggunakan algoritma Random Forest sebagai alat bantu skrining awal bagi tenaga kesehatan, bukan sebagai penentu diagnosis mutlak, yang menampilkan tiga kemungkinan penyakit dengan probabilitas tertinggi (top-3 probability) berdasarkan gejala yang diinput pengguna. Dataset penelitian merupakan integrasi 4.027 data yang terdiri atas 886 data (22%) rekam medis Klinik Banda Neira dan 3.141 data (78%) dataset publik; sebelum digabungkan, kedua sumber data diselaraskan (harmonisasi) terlebih dahulu ke dalam struktur atribut yang identik, yaitu sepuluh variabel gejala biner (demam, batuk, mual, muntah, diare, sakit kepala, nyeri otot, menggigil, sesak napas, dan ruam merah) serta lima label penyakit yang sama. Tahapan penelitian meliputi preprocessing data, pembagian data latih-uji secara stratified (80:20), pelatihan model, hyperparameter tuning menggunakan GridSearchCV, serta evaluasi menggunakan accuracy, precision, recall, F1-score, confusion matrix, dan 5-fold cross-validation. Pengujian black box terhadap sembilan skenario menunjukkan seluruh fitur sistem berjalan sesuai rancangan. Hasil evaluasi menunjukkan algoritma Random Forest menghasilkan akurasi 87,59%, precision (weighted) 89,09%, recall (weighted) 87,59%, F1-score (weighted) 87,78%, serta rata-rata akurasi cross-validation 87,24% (standar deviasi 1,28%). Confusion matrix menunjukkan kesalahan klasifikasi terbesar antara kelas DBD dan Tifoid akibat kemiripan gejala awal, sedangkan feature importance menunjukkan gejala batuk sebagai fitur dengan kontribusi tertinggi. Dengan demikian, algoritma Random Forest terbukti mampu memberikan kinerja klasifikasi yang baik dan stabil sebagai sistem pendukung keputusan awal bagi tenaga medis, dengan keterbatasan utama berupa representasi gejala yang masih bersifat biner tanpa mempertimbangkan derajat keparahan
References
Agrawal, S., Khan, M., Hamdulay, K. F., Kumar, S., Parepalli, A., Patil, R., & Nelakuditi, M. (2025). Etioepidemiological and laboratory profile of tropical fever in patients presenting with acute febrile illness in Wardha District in Central India: An observational study. Cureus, 17(1), e77861. https://doi.org/10.7759/cureus.77861
Aguilar-Ruiz, J. S., & Michalak, M. (2024). Classification performance assessment for imbalanced multiclass data. Scientific Reports, 14, 10759. https://doi.org/10.1038/s41598-024-61365-z
Agusyul, A. Y., & Firmansyah (2023). Prediksi penyakit jantung menggunakan algoritma Random Forest. Jurnal Minfo Polgan, 12(2), 2239– 2246. https://doi.org/10.33395/jmp.v12i2.13214
Alaka, S. A., Menon, B. K., Brobbey, A., Williamson, T., Goyal, M., & Demchuk, A. M. (2023). Machine learning models for stroke outcome prediction using Random Forest. Frontiers in Neurology, 14, 1182456. https://doi.org/10.3389/fneur.2023.1182456
Alhur, A. A., Sani, J., & Ahmed, M. M. (2025). Predicting COPD admissions using machine learning and SHAP: An exploratory multi-hospital study in Riyadh, Saudi Arabia. Intelligence-Based Medicine, 12, 100312. https://doi.org/10.1016/j.ibmed.2025.100312
Badan Pusat Statistik Provinsi Maluku (2025). Statistik kesehatan Provinsi Maluku 2024.
Bhat, S., Jain, S., & Dutta, P. (2022). Disease prediction using machine learning techniques and Random Forest classifier. Healthcare Analytics, 2, 100118. https://doi.org/10.1016/j.health.2022.100118
Bria, Y. P., Nani, P. A., Siki, Y. C. H., Mamulak, N. M. R., Meolbatak, E. M., & Guntur, R. D. (2025). Leveraging a Random Forest classifier and SVMSMOTE for an early-stage dengue prediction. Engineering, Technology & Applied Science Research, 15(3), 23436–23442. https://doi.org/10.48084/etasr.10762
Cappelli, F., Castronuovo, G., Grimaldi, S., & Telesca, V. (2024). Random forest and feature importance measures for discriminating the most influential environmental factors in predicting cardiovascular and respiratory diseases. International Journal of Environmental Research and Public Health, 21(7), 867. https://doi.org/10.3390/ijerph21070867
Dalal, S., Goel, P., Onyema, E. M., Alharbi, A., Mahmoud, A., Algarni, M. A., & Awal, H. (2023). Application of machine learning for cardiovascular disease risk prediction. Computational Intelligence and Neuroscience, 2023, 9418666. https://doi.org/10.1155/2023/9418666
Elmi, A. H., Abdullahi, A., & Barre, M. A. (2024). A machine learning approach to cardiovascular disease prediction with advanced feature selection. Indonesian Journal of Electrical Engineering and Computer Science, 33(2), 1030–1041. https://doi.org/10.11591/ijeecs.v33.i2.pp1030-1041
Fernandez-Lozano, C., Hervella, P., Mato-Abad, V., Rodríguez-Yáñez, M., Suárez-Garaboa, S., López-Dequidt, I., Estany-Gestal, A., Sobrino, T., Campos, F., Castillo, J., Rodríguez-Yáñez, S., & Iglesias-Rey, R. (2021). Random forest-based prediction of stroke outcome. Scientific Reports, 11(1), 10071. https://doi.org/10.1038/s41598-021-89434-7
Grover, S., Bhartia, S., Akshama, & Seeja, K. R. (2022). Predicting severity of Parkinson’s disease using deep learning and Random Forest. Procedia Computer Science, 218, 101–110. https://doi.org/10.1016/j.procs.2022.12.406
Hin, S., Lopez-Jimena, B., Bakheit, M., Klein, V., Stack, S., Fall, C., Sall, A., Enan, K., Mustafa, M., Gillies, L., Rusu, V., Goethel, S., Paust, N., Zengerle, R., Frischmann, S., Weidmann, M., & Mitsakakis, K. (2021). Fully automated point-of-care differential diagnosis of acute febrile illness. PLOS Neglected Tropical Diseases, 15(2), e0009177. https://doi.org/10.1371/journal.pntd.0009177
Kaur, P., Singh, M., & Joshi, N. (2024). Chronic disease prediction using ensemble machine learning approaches. Healthcare Analytics, 5, 100266. https://doi.org/10.1016/j.health.2024.100266
Kementerian Kesehatan Republik Indonesia (2023). Pedoman teknis penanggulangan malaria.
Kementerian Kesehatan Republik Indonesia (2025). Profil kesehatan Indonesia 2024.
Khofiyah, S. N., & Kuncoro, A. P. (2025). Heart disease prediction using Random Forest algorithm and synthetic minority oversampling technique (SMOTE). Komputa: Jurnal Ilmiah Komputer dan Informatika, 14(1), 1–10. https://doi.org/10.34010/komputa.v14i1.14678
Lakshmi, K. L., Umadevi, M., & Bellamkonda, L. P. (2025). Optimized truncated singular value decomposition and hybrid deep neural network with Random Forest for automated disease prediction. Biomedical Signal Processing and Control, 100, 107010. https://doi.org/10.1016/j.bspc.2024.107010
Mahdiana, D., Ebine, M., & Wibowo, A. (2025). Random Forest and artificial neural network data mining for environmental and public health risk modeling in flood-prone urban areas of Indonesia. Jurnal Teknik Informatika (JUTIF), 6(6). https://doi.org/10.52436/1.jutif.2025.6.6.5387
Markoulidakis, I., Rallis, I., Georgoulas, I., Kopsiaftis, G., Doulamis, A., & Doulamis, N. (2021). Multiclass confusion matrix reduction method and its application on net promoter score classification problem. Technologies, 9(4), 81. https://doi.org/10.3390/technologies9040081
Meng, D., Xu, J., & Zhao, J. (2021). Analysis and prediction of hand, foot and mouth disease incidence in China using Random Forest and XGBoost. PLOS ONE, 16(12), e0261629. https://doi.org/10.1371/journal.pone.0261629
Muharom, L. A., Irawan, D., & Warisaji, T. T. (2025). Ensemble learning dengan soft voting classifier untuk klasifikasi pasien tifus di Puskesmas Balung. BIOS: Jurnal Teknologi Informasi dan Rekayasa Komputer, 6(2). https://doi.org/10.37148/bios.v6i2.186
Muliani, E., Ayudhia, A., Maulidya, Saputra, N. A. B., & Wiranda, N. (2025). Implementasi algoritma Random Forest dengan variasi parameter n_estimators untuk klasifikasi penyakit hati. CESS (Journal of Computer Engineering, System and Science), 10(2), 563–571. https://doi.org/10.24114/cess.v10i2.66740
Narasimhan, G., & Victor, A. (2025). A hybrid approach with metaheuristic optimization and Random Forest in improving heart disease prediction. Scientific Reports, 15, 10971. https://doi.org/10.1038/s41598-024-73867-x
Omankwu, O. C. B., Osodoeke, E. C., & Ubah, V. I. (2024). Disease prediction using Random Forest machine learning algorithm. NIPES Journal of Science and Technology Research, 6(1). https://doi.org/10.5281/zenodo.11005308
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830. https://jmlr.org/papers/v12/pedregosa11a.html
Ramírez, S. (n.d.). FastAPI: A modern, fast (high-performance) web framework for Python. https://fastapi.tiangolo.com/
Song, J., Gao, Y., Yin, P., Li, Y., Li, Y., Zhang, J., Su, Q., Fu, X., & Pi, H. (2021). The Random Forest model has the best accuracy among the four pressure ulcer prediction models using machine learning algorithms. Risk Management and Healthcare Policy, 14, 1175–1187. https://doi.org/10.2147/RMHP.S297838
Susanto, E. R., & Pranajaya, A. E. (2025). Optimasi Random Forest untuk prediksi penyakit jantung menggunakan SMOTEENN dan Grid Search. Jurnal Pendidikan dan Teknologi Indonesia, 5(7), 1965–1979. https://doi.org/10.52436/1.jpti.855
Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K. I. (2020). An overview of clinical decision support systems: Benefits, risks, and strategies for success. npj Digital Medicine, 3, 17. https://doi.org/10.1038/s41746-020-0221-y
Tuama, M. H. (2025). A comparative evaluation of random forest and XGBoost models for disease detection using medical indicators. International Journal of Professional Studies, 19, 11–18. https://doi.org/10.37648/ijps.v19i01.002
Wang, L., Li, J., Lin, Y., Yuan, H., Fang, Z., Fei, A., & Shen, G. (2024). Establishment and external validation of an early warning model of diabetic peripheral neuropathy based on random forest and logistic regression. BMC Endocrine Disorders, 24, 196. https://doi.org/10.1186/s12902-024-01728-9
World Health Organization (2024a). World malaria report 2024. https://www.who.int/teams/global-malaria-programme/reports/world-malaria-report-2024
World Health Organization (2024b). Diarrhoeal disease. https://www.who.int/news-room/fact-sheets/detail/diarrhoeal-disease
Yang, X., Li, Y., Liu, L., & Zang, Z. (2025). Prediction of respiratory diseases based on random forest model. Frontiers in Public Health, 13, 1537238. https://doi.org/10.3389/fpubh.2025.1537238
Zhou, X., Zhang, J., Deng, X.-M., Fu, F.-M., Wang, J.-M., Zhang, Z.-Y., Zhang, X.-Q., Luo, Y.-X., & Zhang, S.-Y. (2024). Using random forest and biomarkers for differentiating COVID-19 and Mycoplasma pneumoniae infections. Scientific Reports, 14, 22673. https://doi.org/10.1038/s41598-024-74057-5
