DetectDiab: Observation of Diabetic Retinopathy Progression Based on Deep Learning Object Detection Using a Web Application with Client-Side Processing

Sabila Azaria Lapusa; Devina Almira Gunawan

doi:10.31039/ljis.2026.6.378

Authors

Sabila Azaria Lapusa SMA Kesatuan Bangsa, Indonesia
Devina Almira Gunawan SMA Kesatuan Bangsa, Indonesia

DOI:

https://doi.org/10.31039/ljis.2026.6.378

Keywords:

Diabetic Retinopathy, Client-Side Processing, Artificial Intelligence, Deep Learning

Abstract

Diabetic retinopathy is a serious complication of diabetes that affects the retinal tissue and can cause oxygen deficiency, abnormal blood vessel growth in the eye, and severe visual impairment or even blindness. Limited access to healthcare services in rural and remote areas in Indonesia affects this condition, as it is difficult for people to get regular eye examinations. On the other hand, the increasing use of biometric data in digital services requires serious attention to security and privacy aspects, given that people's biometric data is very important to protect. Therefore, this study aims to develop an AI-based application that can recognize the severity of diabetic retinopathy from retinal images uploaded by users online or offline (without a network). Since this study uses Client-Side Processing, fundus photos will not be uploaded to any server to protect users' personal data. The application was created by collecting retinal data from the APTOS 2019 Blindness Detection public dataset, followed by AI training using Edge Impulse with the Bring Your Own Mode (BYOM) method. The AI training results were launched on the Detectdiab website application. It was then tested and validated by ophthalmologists, medical personnel, and other volunteers. This research has successfully developed DetectDiab, a prototype website application that functions for early detection and observation of the progression of diabetic retinopathy. This application was built using the MobileNetV2 deep learning model with the highest accuracy of 78% compared to other models. However, optimization is still needed in the mild class to achieve higher accuracy. Client-Side Processing technology using TensorFlow WebAssembly (WASM) enables retinal image analysis to be performed entirely on the user's device, ensuring data privacy and security.

References

Akhtar, S., Aftab, S., Ali, O., Ahmad, M., Khan, M. A., Abbas, S., & Ghazal, T. M. (2025). A deep learning based model for diabetic retinopathy grading. Scientific Reports, 15, 3763. https://doi.org/10.1038/s41598-025-87171-9

Amrullah, M. A., & Irawan, M. I. (2023). Implementasi jaringan syaraf konvolusional dengan Inception-V3 untuk deteksi katarak menggunakan gambar digital funduskopi. Jurnal Sains dan Seni ITS, 12(1), A27–A33.

Ardyansyah, M. A. (2023). Sistem deteksi level diabetic retinopathy melalui citra fundus mata dengan menggunakan metode CNN (Convolutional Neural Network). G-Tech: Jurnal Teknologi Terapan, 7(4), 1673–1682.

Ardyansyah, M., & Gunawansyah, S. (2023). Application of CNN in classifying fundus images of eye diseases. International Journal of Informatics.

Ariawan, I. (2012). Pengembangan model dan perangkat pembelajaran geometri bidang berbantuan open software Geogebra. https://doi.org/10.23887/JPPUNDIKSHA.V45I2.1827

Elsen, R., Zhao, H., & Grangier, D. (2023). Client-side deep learning in the browser: Feasibility and performance. Website Technology Journal.

Elvira, E. E., & Suryawijaya, E. E. (2019). Retinopati diabetes. Majalah Kedokteran, 46(3), 220–223.

Zerihum, E., Abera, F., Kune, G., Girma, F., Tesgera, M., Robi, M. (2024). Undiagnosed status and associated factors of diabetes mellitus among adults living in eastern Ethiopia: Unmasking a silent killer of prevalence of diabetes mellitus. Clinical Epidemiology and Global Health. https://doi.org/10.1016/j.cegh.2023.101483

Fortuna, T. A., Karuniawati, H., Purnamasari, D., & Purlinda, D. E. (2023). Faktor–faktor yang mempengaruhi komplikasi pada pasien diabetes mellitus di RSUD Dr. Moewardi. Pharmacon: Jurnal Farmasi Indonesia, 20(1), 27–35.

Munarto, R. (2019). Klasifikasi katarak objek optic disc citra fundus retina menggunakan Support Vector Machine.

Mutimmah, D., & Prayekti, N. (2021). Pemodelan pot tanaman sukulen melalui penggabungan benda geometri bidang dan kurva Bezier. AKSIOMA: Jurnal Program Studi Pendidikan Matematika, 10(2), 1252–1260.

Nadeem, M. W., et al. (2022). A survey on deep learning applications in medical image analysis. Computers in Biology and Medicine.

Nopriana, T. (2015). Diposisi matematis siswa melalui model pembelajaran geometri Van Hiele. https://doi.org/10.24853/fbc.1.2.80-94

Ogurtsova, K., Guariguata, L., Barengo, N. C., Ruiz, P. L. D., Sacre, J. W., Karuranga, S., ... Magliano, D. J. (2022). IDF diabetes atlas: Global estimates of undiagnosed diabetes in adults for 2021. Diabetes Research and Clinical Practice, 183, 109118.

Purnama, F. N., Nintyastuti, I. K., & Rizki, M. (2023). Retinopati diabetik: Manifestasi klinis, diagnosis, tatalaksana dan pencegahan. Jurnal Oftalmologi Indonesia, 2(1), 39–42.

Putri, A., & Rachmawati, D. (2023). Analisis akses layanan kesehatan terhadap kesejahteraan masyarakat di wilayah 3T. Jurnal Pembangunan Kesehatan Masyarakat Indonesia, 11(2), 133–145.

Quamila, N. (2025). Viral warga Bekasi scan retina mata-dapat uang ratusan ribu dari Worldcoin, ini bahayanya jika data biometrik bocor. Beautynesia. https://www.beautynesia.id/life/viral-warga-bekasi-scan-retina-mata-dapat-uang-ratusan-ribu-dari-worldcoin-ini-bahayanya-jika-data-biometrik-bocor/b-304474 diakses pada 18 Oktober 2025.

Resti, H. Y., & Cahyati, W. H. (2022). Kejadian diabetes melitus pada usia produktif di Puskesmas Kecamatan Pasar Rebo, Kota Jakarta Timur. HIGEIA (Journal of Public Health Research and Development), 6(3), 350–361.

Retta, E., Kusumajaya, H., & Arjuna, A. (2023). Faktor–faktor yang berhubungan dengan pemilihan pengobatan herbal pada pasien diabetes mellitus. Jurnal Penelitian Perawat Profesional, 5(4), 1541–1552.

Saputra, D. H., Imran, B., & Juhartini. (2023). Object detection untuk mendeteksi citra buah-buahan menggunakan metode YOLO. Jurnal Kecerdasan Buatan dan Teknologi Informasi.

Sirojul Qulub, M., & Agustin, S. (2024). Identifikasi penyakit mata dengan klasifikasi citra foto fundus menggunakan Convolutional Neural Network (CNN). JATI (Jurnal Mahasiswa Teknik Informatika).

Supriadi, N. (2015). Pembelajaran geometri berbasis Geogebra sebagai upaya meningkatkan kemampuan komunikasi matematis. Al-Jabar: Jurnal Pendidikan Matematika, 6(2), 99–109.

Szegedy, C., Toshev, A., & Erhan, D. (2013). Deep neural networks for object detection. Neural Information Processing Systems.

Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. International Conference on Machine Learning (ICML).

Tan, T. E., & Wong, T. Y. (2023). Diabetic retinopathy: Looking forward to 2030. Frontiers in Endocrinology, 13, 1077669.

Viedma, A., et al. (2022). Deep learning based methods for retinal image analysis. Biomedical Signal Processing and Control.

Viedma, I. A., Alonso-Caneiro, D., Read, S. A., & Collins, M. J. (2022). Deep learning in retinal optical coherence tomography (OCT): A comprehensive survey. Neurocomputing, 507, 247–264.

Yuliana, S., Prasetyo, R., & Lestari, W. (2022). Ketimpangan akses pelayanan kesehatan dan implikasinya terhadap perekonomian desa. Jurnal Sosial Ekonomi dan Kebijakan Publik, 7(1), 67–79.

DetectDiab: Observation of Diabetic Retinopathy Progression Based on Deep Learning Object Detection Using a Web Application with Client-Side Processing

Authors

DOI:

Keywords:

Abstract

References

Downloads

Published

How to Cite

Issue

Section

License