Bapak Analisis dan Prediksi Diabetes Menggunakan Artificial Neural Network dengan Dataset CDC Diabetes Health Indicators : Analisis dan Prediksi Diabetes Menggunakan Artificial Neural Network dengan Dataset CDC Diabetes Health Indicators

Dodi Dwi Riskianto Dwi; Muhammad Afandi; M. Raihan Ramadhan; Sudriyanto Sudriyanto

doi:10.30787/restia.v4i1.2096

Penulis

Dodi Dwi Riskianto Dwi Universitas Nurul Jadid
Muhammad Afandi Universitas Nurul Jadid, Probolinggo
M. Raihan Ramadhan Universitas Nurul Jadid, Probolinggo
Sudriyanto Universitas Nurul Jadid, Probolinggo

DOI:

https://doi.org/10.30787/restia.v4i1.2096

Kata Kunci:

Diabetes, Artificial Neural Network, Prediksi, Indikator Kesehatan, Deep Learning

Abstrak

Diabetes melitus merupakan salah satu penyakit tidak menular yang prevalensinya terus meningkat secara global, termasuk di Indonesia. Deteksi dini terhadap risiko diabetes menjadi penting guna mencegah komplikasi lebih lanjut. Penelitian ini bertujuan untuk membangun model prediksi diabetes menggunakan algoritma Artificial Neural Network (ANN) dengan pendekatan multilayer perceptron berbasis TensorFlow. Dataset yang digunakan adalah CDC Diabetes Health Indicators dengan enam variabel input, yaitu usia, indeks massa tubuh (BMI), jenis kelamin, tekanan darah tinggi, aktivitas fisik, dan status merokok. Data diproses melalui normalisasi dan dibagi menggunakan metode stratified sampling. Model dilatih selama 10 epoch dengan optimasi Adam dan fungsi aktivasi ReLU pada hidden layer. Hasil pengujian menunjukkan bahwa model mampu mencapai akurasi validasi sebesar 86,45%, dengan nilai AUC-ROC sebesar 0,89. Model ini menunjukkan kinerja klasifikasi yang baik dan dapat digunakan sebagai alat bantu skrining awal risiko diabetes pada layanan kesehatan primer. Penelitian ini berkontribusi dalam pemanfaatan pembelajaran mesin untuk pengambilan keputusan klinis berbasis data non-laboratorium.

Referensi

S. I. Oktora and D. B. Butar, “Determinants of Diabetes Mellitus Prevalence in Indonesia,” J. Kesehat. Masy., vol. 18, no. 2, pp. 266–273, 2022.

A. R. Kandula, V. V. Samhitha, V. Harshitha, R. N. Sindhuri, and S. A. Nagavalli, “Machine Learning based Screening for Diabetes Risk Prediction,” in 2024 3rd International Conference on Automation, Computing and Renewable Systems (ICACRS), IEEE, 2024, pp. 1188–1193.

N. Nagarjuna and H. N. Lakshmi, “Predictive Modeling of Diabetes Mellitus Utilizing Machine Learning Techniques,” CVR J. Sci. Technol., vol. 26, no. 1, pp. 112–117, 2024.

T. Elansari, M. Ouanan, and H. Bourray, “Modeling of Multilayer Perceptron Neural Network Hyperparameter Optimization and Training,” 2023.

D. Kurniawan, T. T. Wulansari, and N. A. D. Febrianti, “Model Prediction Using Artificial Neural Network (ANN) to Strengthen Diagnostic Analysis of Diabetes Melitus,” ComTech Comput. Math. Eng. Appl., vol. 15, no. 2, pp. 83–91, 2024.

S. M. Lawan and S. J. Kawu, “Artificial Neural Network (ANN) Prediction of Guide Vane for Effective Utilization of Pump as Turbine (PAT),” in 2024 IEEE International Conference on Power and Energy (PECon), IEEE, 2024, pp. 34–39.

P. Dhiman et al., “Methodological conduct of prognostic prediction models developed using machine learning in oncology: a systematic review,” BMC Med. Res. Methodol., vol. 22, no. 1, p. 101, 2022.

S. Demir and E. K. Sahin, “Random forest importance-based feature ranking and subset selection for slope stability assessment using the ranger implementation,” Avrupa Bilim ve Teknol. Derg., no. 48, pp. 23–28, 2023.

S. Prakash, S. Singh, and A. Mankar, “Bridging data gaps: A comparative study of different imputation methods for numeric datasets,” in 2024 International Conference on Data Science and Network Security (ICDSNS), IEEE, 2024, pp. 1–7.

K. Song, R. Solozabal, H. Li, M. Takac, L. Ren, and F. Karray, “Robustly train normalizing flows via kl divergence regularization,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2024, pp. 15047–15055.

T. Filimonova, H. Samoylenko, A. Selivanova, Y. Yurchenko, and A. Parashchak, “CONSTRUCTION OF A NEURAL NETWORK FOR HANDWRITTEN DIGITS RECOGNITION BASED ON TENSORFLOW LIBRARY APPLYING AN ERROR BACKPROPAGATION ALGORITHM.,” Eastern-European J. Enterp. Technol., vol. 126, no. 2, 2023.

Z. Lin, S. Zhang, Y. Zhou, H. Wang, and S. Wang, “Learning rate burst for superior SGDM and AdamW integration,” J. Intell. Fuzzy Syst., p. JIFS-239157, 2024.

J. Qiu, “An analysis of model evaluation with cross-validation: techniques, applications, and recent advances,” Adv. Econ. Manag. Polit. Sci., vol. 99, pp. 69–72, 2024.

M. Owusu-Adjei, J. Ben Hayfron-Acquah, T. Frimpong, and G. Abdul-Salaam, “Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems,” PLOS Digit. Heal., vol. 2, no. 11, p. e0000290, 2023.

G. S. Sahoo, S. Dass, and F. Prakash, “The Synergy of Advanced Language Models, Sequential Skeleton Features, and GAN-Enhanced Data Augmentation for Unprecedented Precision,” in 2023 International Conference on System, Computation, Automation and Networking (ICSCAN), IEEE, 2023, pp. 1–6.

T. F. Monaghan et al., “Foundational statistical principles in medical research: sensitivity, specificity, positive predictive value, and negative predictive value,” Medicina (B. Aires)., vol. 57, no. 5, p. 503, 2021.

R. H. Stern, “Interpretation of the area under the ROC curve for risk prediction models. arXiv,” arXiv Prepr. arXiv2102.11053, 2021.

P. H. Artanti, “Penerapan Neural Network dengan optimasi Ant Colony Optimization dan Backpropagation untuk membangun model prediksi diabetes tahap awal,” 2023, Universitas Islam Negeri Maulana Malik Ibrahim.