Deteksi Dini Kesehatan Berdasarkan Nilai Kadar Gula Darah, Kolesterol, dan Asam Urat Non-Invasif dengan Multi-Layer Perceptron

Agrippina Waya Rahmaning Gusti; Kemalasari; J S Peter Parasian C

doi:10.30595/jrre.v7i2.27002

Authors

Agrippina Waya Rahmaning Gusti Politeknik Elektronika Negeri Surabaya
Kemalasari Politeknik Elektronika Negeri Surabaya
J S Peter Parasian C Politeknik Elektronika Negeri Surabaya

DOI:

https://doi.org/10.30595/jrre.v7i2.27002

Keywords:

Deteksi non-invasif, Multi-layer perceptron, Penyakit tidak menular, Fotopletismograf, Sensor MAX30105

Abstract

Penyakit tidak menular menjadi penyebab utama kematian global dengan persentase lebih dari 70% per tahun. Tingginya kadar gula darah, asam urat, dan kolesterol merupakan pemicu utama penyakit tersebut. Metode pemantauan yang tersedia saat ini bersifat invasif sehingga menurunkan tingkat kepatuhan pasien. Penelitian ini bertujuan untuk mengembangkan perangkat deteksi noninvasif dalam mengukur ketiga parameter tersebut dengan menggunakan sensor fotopletismografi (PPG) MAX30105 dan model Multi-Layer Perceptron (MLP). Data dikumpulkan dari 80 responden dan dibagi menjadi 50 data latih serta 30 data uji terpisah. Model yang dilatih menggunakan Bayesian regularization backpropagation menunjukkan akurasi prediksi pada data uji sebesar 90,4% untuk gula darah, 90,2% untuk kolesterol, dan 87,7% untuk asam urat. Akurasi tersebut melampaui hasil penelitian sebelumnya yang berbasis regresi linear. Perangkat ini memiliki potensi besar untuk deteksi dini penyakit tidak menular dan dapat mengurangi risiko komplikasi kesehatan.

References

[1] World Health Organization, “Global health estimates 2021: deaths by cause, age, sex, by country and by region, 2000-2021” Accessed: August 11, 2025. [Online]. Availabe: https://www.who.int/data/gho/data/themes/mortality-and-global-health-estimates/ghe-leading-causes-of-death

[2] H. Tang, M. Li, L. Z. Liu, Y. Zhou, and X. Liu, “Changing inequity in health service utilization and financial burden among patients with hypertension in China: evidence from China Health and Retirement Longitudinal Study (CHARLS), 2011–2018,” Int. J. Equity Health, vol. 22, pp. 246, 2023.

[3] S. A. Kristina and K. A. Santosa, “An Estimated Mortality and Disability Adjusted Life Years (DALYs) of Non-communicable Diseases in Indonesia,” Int. J. Pharm. Res., vol. 12, 2020.

[4] U. P. Gujral et al., “Association between varying cut-points of intermediate hyperglycemia and risk of mortality, cardiovascular events and chronic kidney disease: a systematic review and meta-analysis,” BMJ Open Diabetes Res. Care, vol. 9, pp. e001776, 2021.

[5] D. Pan, L. Xu, L. Zhang, D. Shi, and M. Guo, "Associations between remnant cholesterol levels and mortality in patients with diabetes", World journal of diabetes, vol. 15, pp. 712–723, 2024.

[6] Y. Zhang et al., “Noninvasive and Individual‐Centered Monitoring of Uric Acid for Precaution of Hyperuricemia via Optical Supramolecular Sensing,” Adv. Sci., vol. 9, pp. 2104463, 2022.

[7] D.-H. Min and H.-K. Yoon, “Suggestion for a new deterministic model coupled with machine learning techniques for landslide susceptibility mapping,” Sci. Rep., vol. 11, pp. 6594, 2021.

[8] A. W. R. Gusti, Kemalasari, M. Rochmad, and F. Az Zahro, “Rancang Bangun Alat Ukur Kadar Gula Darah, Kolestrol, dan Asam Urat Non-Invasif Berbasis Internet of Things (IoT),” Indones. J. Comput. Sci., vol. 12, 2023.

[9] R. N. Fauzi et al., “Non-Invasive Detection System for Blood Sugar, Cholesterol, Uric Acid, and Body Temperature Using MAX30105 and MLX90614 Sensors,” 2022 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), pp. 1–7, 2022.

[10] J. Chu, W-T. Yang, W-R. Lu, Y-T. Chang, T-H. Hsieh, and F-L. Yang, "90% Accuracy for Photoplethysmography-Based Non-Invasive Blood Glucose Prediction by Deep Learning with Cohort Arrangement and Quarterly Measured HbA1c", Sensors, vol. 21, pp. 7815, 2021.

[11] N. Assani, P. Matić, N. Kaštelan, and I. R. Čavka, “A Review of Artificial Neural Networks Applications in Maritime Industry,” IEEE Access, vol. 11, pp. 139823–139848, 2023.

[12] I. Khan et al., “Design of Neural Network with Levenberg-Marquardt and Bayesian Regularization Backpropagation for Solving Pantograph Delay Differential Equations,” IEEE Access, vol. 8, pp. 137918–137933, 2020.

[13] A. Altaye, I. Farkas, and P. Víg, “Impacts of Artificial Neural Network Training Algorithms on the Accuracy of PV System Voltage and Current Predictions”, EJENERGY, vol. 5, pp. 1–6, 2025.

[14] A. Suliman and B. Omarov, “Early Stopping Criteria for Levenberg-Marquardt Based Neural Network Training Optimization,” Int. J. Eng. Technol., vol. 7, pp. 1194, 2018.

[15] D. Sutarya, “Sistem Monitoring Kadar Gula Darah, Kolestrol dan Asam Urat secara Non Invasive menggunakan Sensor”, Jurnal Ilmiah Teknologi Energi, Teknologi Media Komunikasi dan Instrumentasi Kendali, vol. 1, pp. 25-34, 2021.

[16] K. S. Krishnasree and M. R. N. Rao, “Diagnosis of heart disease using neural networks—Comparative study of Bayesian regularization with multiple regression model,” J. Theor. Appl. Inf. Technol., vol. 88, pp. 638–643, 2016.