Implementasi Model Artificial Neural Network (ANN) Untuk Prediksi Penyakit Diabetes Melitus Tipe 2
Abstrak
Diabetes Melitus (DM) tipe 2 adalah penyakit kronis dengan prevalensi global yang terus melonjak, deteksi dini perlu dilakukan untuk menghindari komplikasi serius. Tantangan utama dalam membangun model prediktif berbasis data medis adalah ketidakseimbangan kelas yang sering menurunkan sensitivitas model. Riset ini bertujuan mengevaluasi model ANN untuk mengatasi data yang tidak seimbang dan hyperparameter tuning guna mengoptimalkan performa pada data rekam medis DM Tipe 2. Pendekatan hybrid yang mengintegrasikan Artificial Neural Network (ANN) dengan teknik Synthetic Minority Over-sampling Technique (SMOTE) untuk mengatasi imbalanced data, serta optimalisasi hyperparameter melalui Randomized Search. Dataset bersumber dari Mendeley data yang diambil dari data rekam medis pasien di Medical City Hospital, Irak, meliputi variabel klinis seperti HbA1C, indeks massa tubuh (BMI), dan profil lipid. Evaluasi dilakukan dalam empat skenario untuk mengukur dampak masing-masing komponen terhadap performa model. Hasil menunjukkan bahwa kombinasi SMOTE dan algoritma ANN secara signifikan meningkatkan akurasi dan recall, dengan model terbaik (skenario ke-2) mencapai akurasi 97,50% dan recall 89,96%. Pendekatan algoritma ANN mampu terbukti efektif dalam meningkatkan keandalan prediksi DM tipe 2, untuk mendukung pengembangan sistem deteksi dini berbasis kecerdasan buatan. Kata kunci— Diabetes melitus tipe 2, Artificial Neural Network, SMOTE, Imbalanced data, Hyperparameter tuning
Unduhan
Referensi
[1] J. Li, V. Pandian, P. M. Davidson, Y. Song, N. Chen, and D. Y. T. Fong, “Burden and attributable risk factors of non-communicable diseases and subtypes in 204 countries and territories, 1990-2021: a systematic analysis for the global burden of disease study 2021,” Int. J. Surg., vol. 111, no. 3, pp. 2385–2397, Mar. 2025, doi: 10.1097/JS9.0000000000002260.
[2] N. Novia Kusumaningsih and A. Alwi, “Tantangan Penyakit Tidak Menular di Tengah Perubahan Gaya Hidup,” Indo-MathEdu Intellectuals Journal, vol. 6, no. 2, pp. 2393–2403, Apr. 2025, doi: 10.54373/imeij.v6i2.2834.
[3] R. Pahlevi, “Jumlah Penderita Diabetes Indonesia Terbesar Kelima di Dunia, “https://databoks.katadata.co.id/,” 2025.
[4] A. Kulkarni, A. R. Thool, and S. Daigavane, Understanding the Clinical Relationship Between Diabetic Retinopathy, Nephropathy, and Neuropathy: A Comprehensive Review. Cureus, 2024. doi: 10.7759/cureus.56674.
[5] N. Katiyar, H. K. Thakur, and A. Ghatak, “Recent advancements using machine learning & deep learning approaches for diabetes detection: a systematic review,” e-Prime - Advances in Electrical Engineering, Electronics and Energy, vol. 9, Sep. 2024, doi: 10.1016/j.prime.2024.100661.
[6] A. Z. Mustaqim, N. A. Fadil, and D. A. Tyas, “Artificial Neural Network for Classification Task in Tabular Datasets and Image Processing: A Systematic Literature Review,” Jurnal Online Informatika, vol. 8, no. 2, pp. 158–168, Dec. 2023, doi: 10.15575/join.v8i2.1002.
[7] N. Faulina, “Sciencestatistics Journal of Statistics, Probability, and Its Application Implementation Of Artificial Neural Network (ANN) Classification In Type 2 Diabetes Mellitus Cases,” vol. 2, no. 2, pp. 80–92, 2024.
[8] A. Malik and C. Tepe, “Improving Early Diabetes Diagnosis : A Machine Learning Approach for Class Imbalance Mitigation,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 11, no. 3, pp. 861–874, Jun. 2025, doi: 10.32628/cseit25113322.
[9] S. Prasanth, K. Banujan, and K. Btgs, “Hyper Parameter Tuned Ensemble Approach for Gestational Diabetes Prediction,” in 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2021, Institute of Electrical and Electronics Engineers Inc, Sep. 2021, pp. 18–23. doi: 10.1109/3ICT53449.2021.9581926.
[10] W. Pannakkong, K. Thiwa-Anont, K. Singthong, P. Parthanadee, and J. Buddhakulsomsiri, “Hyperparameter Tuning of Machine Learning Algorithms Using Response Surface Methodology: A Case Study of ANN, SVM, and DBN,” Math. Probl. Eng., vol. 2022, 2022, doi: 10.1155/2022/8513719.
[11] G. R. ; S. M. J. I., “Type 2 Diabetes,” in StatPearls [Internet], StatPearls, 2023. Accessed: Apr. 02, 2025. [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK513253/
[12] R. S. Nurhalizah, R. Ardianto, and P. Purwono, “Analisis Supervised dan Unsupervised Learning pada Machine Learning: Systematic Literature Review,” Jurnal Ilmu Komputer dan Informatika, vol. 4, no. 1, pp. 61–72, Aug. 2024, doi: 10.54082/jiki.168.
[13] V. V Virginia, U. M. Mbanaso, E. S. Chaku, I. O. Clementina, and G. Aimufua, “Deep learning and convolutional neural networks (CNNs),” GAS Journal of Engineering and Technology (GASJET), vol. 2, no. 11, p. 2025, 2025, doi: 10.5281/zenodo.17552650.
[14] P. Theotokis, “Human Brain Inspired Artificial Intelligence Neural Networks,” J. Integr. Neurosci., vol. 24, no. 4, Apr. 2025, doi: 10.31083/JIN26684.
[15] I. D. Mienye and T. G. Swart, “A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications,” Information (Switzerland), vol. 15, no. 12, Dec. 2024, doi: 10.3390/info15120755.
[16] K. Wang, L. Wang, and J. Sun, “The data analysis of sports training by ID3 decision tree algorithm and deep learning,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-99996-5.
[17] P. Prestasi, A. Mahasiswa, M. Nilai, M. Kuliah, and D. Tingkat, “Penerapan Artificial Neural Network (ANN),” 2023.
[18] F. Z. El-Hassani, F. Belhabib, N. E. Joudar, and K. Haddouch, “Evolutionary algorithm-based hyperparameter tuning of one-dimensional CNNs for diabetes mellitus prediction,” Evol. Intell., vol. 17, no. 5–6, pp. 3655–3674, Oct. 2024, doi: 10.1007/s12065-024-00950-7.
[19] H. Ulutas, R. B. Günay, and M. E. Sahin, “Detecting diabetes in an ensemble model using a unique PSO-GWO hybrid approach to hyperparameter optimization,” Neural Comput. Appl., vol. 36, no. 29, pp. 18313–18341, Oct. 2024, doi: 10.1007/s00521-024-10160-y.
[20] M. Altalhan, A. Algarni, and M. T.-H. Alouane, “Imbalanced Data Problem in Machine Learning: A Review,” IEEE Access, vol. 13, pp. 13686–13699, 2025, doi: 10.1109/ACCESS.2025.3531662.
[21] D. Tourt, Q. E. Booker, and C. M. Rebman, “Strategic application of SMOTE and its variants to enhance AI-driven healthcare classification in imbalanced datasets,” Issues in Information Systems, vol. 26, no. 2, pp. 70–85, 2025, doi: 10.48009/2_iis_106.
[22] N. G. Ramadhan and A. Romadhony, “Preprocessing Handling to Enhance Detection of Type 2 Diabetes Mellitus based on Random Forest.”
[23] G. L. Aruna Kumari, P. Padmaja, and J. G. Suma, “A novel method for prediction of diabetes mellitus using deep convolutional neural network and long short-term memory,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 26, no. 1, pp. 404–413, Apr. 2022, doi: 10.11591/ijeecs.v26.i1.pp404-413.
[24] N. Nipa, M. H. Riyad, S. Satu, Walliullah, K. C. Howlader, and M. A. Moni, “Clinically adaptable machine learning model to identify early appreciable features of diabetes,” Intelligent Medicine, vol. 4, no. 1, pp. 22–32, Feb. 2024, doi: 10.1016/j.imed.2023.01.003.
[25] R. Ahlam, “Diabetes Dataset,” 2025.
[26] R. Islam, A. Sultana, and M. R. Islam, “A comprehensive review for chronic disease prediction using machine learning algorithms,” Journal of Electrical Systems and Information Technology, vol. 11, no. 1, Jul. 2024, doi: 10.1186/s43067-024-00150-4.
