Implementasi Model AI Berbasis EfficientNetV2L untuk Pra-Skrining Diabetes Melitus Tipe 2 Menggunakan Citra Digital Lidah pada Aplikasi Web

Sigit Sugiharto; Okti Trihastuti Dyah Retnaningrum; Maulidta Karunianingtyas Wirawati

doi:10.55681/armada.v4i10.4807

Authors

Sigit Sugiharto Informatika Medis, Universitas Widya Husada Semarang, Indonesia
Okti Trihastuti Dyah Retnaningrum Informatika Medis, Universitas Widya Husada Semarang, Indonesia
Maulidta Karunianingtyas Wirawati Pendidikan Profesi Ners, Universitas Widya Husada Semarang, Indonesia

DOI:

https://doi.org/10.55681/armada.v4i10.4807

Keywords:

Diabetes Melitus Tipe 2, Citra Lidah; Biomarker Visual, Efficientnetv2l, Deep Learning, Aplikasi Web, Pra-Skrining Non-Invasif

Abstract

Diabetes Melitus Tipe 2 (DMT2) merupakan penyakit kronis yang memerlukan deteksi dini, sementara pemeriksaan berbasis darah bersifat invasif dan membutuhkan fasilitas khusus. Citra digital lidah berpotensi menjadi alternatif non-invasif, tetapi integrasinya dalam aplikasi web masih terbatas. Penelitian ini bertujuan mengembangkan dan mengevaluasi sistem pra-skrining DMT2 berbasis citra digital lidah menggunakan arsitektur deep learning EfficientNetV2L yang terintegrasi dengan aplikasi web. Metode penelitian meliputi audit dataset, verifikasi kualitas dan label citra, pembagian data, prapemrosesan, augmentasi, transfer learning, fine-tuning, evaluasi model, serta pengujian aplikasi web. Evaluasi menggunakan metrik akurasi, precision, recall, dan F1-score. Pengujian terhadap 50 citra, terdiri atas 25 citra diabetes dan 25 citra nondiabetes, menghasilkan akurasi 96%, dengan macro-average precision, recall, dan F1-score masing-masing sebesar 0,96. Temuan menunjukkan kemampuan klasifikasi yang relatif seimbang pada kedua kelas serta potensi penerapan sistem sebagai alat bantu pra-skrining DMT2. Namun, validasi pada populasi dan perangkat pengambilan citra yang lebih beragam diperlukan sebelum penerapan klinis. Sistem ini tidak menggantikan pemeriksaan klinis maupun laboratorium.

Downloads

Download data is not yet available.

References

Berisha, A., & Berisha Salihi, V. (2024). Pakistan Journal of Life and Social Sciences Relationship between Glycemic Control and Coated Tongue in Type 2 Diabetes Mellitus Patients. Pak. j. Life Soc. Sci, 22(2), 20191–20195. https://doi.org/10.57239/PJLSS-2024-22.2.001480

Dalimunthe, M. S. Z., & Nurhasanah, R. (2024). Type 2 Diabetes Mellitus Tongue Dataset. 2. https://doi.org/10.17632/HYB44JF936.2

Hsu, P. C., Wu, H. K., Huang, Y. C., Chang, H. H., Lee, T. C., Chen, Y. P., Chiang, J. Y., & Lo, L. C. (2019). The tongue features associated with type 2 diabetes mellitus. Medicine (United States), 98(19). https://doi.org/10.1097/MD.0000000000015567

Hussien, G. H., & Nemer, Z. N. (2025). A Comprehensive Review of Advances in Tongue Image Classification Techniques for Diabetes Identification. Iraqi Journal of Intelligent Computing and Informatics (IJICI), 4(1), 33–56. https://doi.org/10.52940/IJICI.V4I1.78

Li, J., Chen, Q., Hu, X., Yuan, P., Cui, L., Tu, L., Cui, J., Huang, J., Jiang, T., Ma, X., Yao, X., Zhou, C., Lu, H., & Xu, J. (2021). Establishment of noninvasive diabetes risk prediction model based on tongue features and machine learning techniques. International Journal of Medical Informatics, 149, 104429. https://doi.org/10.1016/J.IJMEDINF.2021.104429

Li, T., Zuo, L., Wang, P., Yang, L., Liu, Z., Wang, X., Tan, J., Yang, Y., Wang, J., Zhou, Y., Jin, L., Zhai, G., Chen, J., Peng, Q., Zhang, G., & Wang, S. (2025). TonguExpert: A Deep Learning-Based Algorithm Platform for Fine-Grained Extraction and Classification of Tongue Phenotypes. Phenomics 2024 5:2, 5(2), 109–122. https://doi.org/10.1007/S43657-024-00210-9

Ogurtsova, K., Guariguata, L., Barengo, N. C., Ruiz, P. L. D., Sacre, J. W., Karuranga, S., Sun, H., Boyko, E. J., & Magliano, D. J. (2022). IDF diabetes Atlas: Global estimates of undiagnosed diabetes in adults for 2021. Diabetes Research and Clinical Practice, 183. https://doi.org/10.1016/j.diabres.2021.109118

Ong, K. L., Stafford, L. K., McLaughlin, S. A., Boyko, E. J., Vollset, S. E., Smith, A. E., Dalton, B. E., Duprey, J., Cruz, J. A., Hagins, H., Lindstedt, P. A., Aali, A., Abate, Y. H., Abate, M. D., Abbasian, M., Abbasi-Kangevari, Z., Abbasi-Kangevari, M., ElHafeez, S. A., Abd-Rabu, R., … Vos, T. (2023). Global, regional, and national burden of diabetes from 1990 to 2021, with projections of prevalence to 2050: a systematic analysis for the Global Burden of Disease Study 2021. The Lancet, 402(10397), 203–234. https://doi.org/10.1016/S0140-6736(23)01301-6

Qiu, D., Zhang, X., Wan, X., Li, J., Xu, Z., Lin, S., Zhang, F., Song, X., Zhang, R., Chen, Y., & Zheng, Y. (2023). A novel tongue feature extraction method on mobile devices. Biomedical Signal Processing and Control, 80, 104271. https://doi.org/10.1016/J.BSPC.2022.104271

Sun, H., Saeedi, P., Karuranga, S., Pinkepank, M., Ogurtsova, K., Duncan, B. B., Stein, C., Basit, A., Chan, J. C. N., Mbanya, J. C., Pavkov, M. E., Ramachandaran, A., Wild, S. H., James, S., Herman, W. H., Zhang, P., Bommer, C., Kuo, S., Boyko, E. J., & Magliano, D. J. (2022). IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045. Diabetes Research and Clinical Practice, 183. https://doi.org/10.1016/j.diabres.2021.109119

Tan, M., & Le, Q. V. (2021). EfficientNetV2: Smaller Models and Faster Training. International Conference on Machine Learning.

Thirunavukkarasu, U., Umapathy, S., Ravi, V., & Alahmadi, T. J. (2024). Tongue image fusion and analysis of thermal and visible images in diabetes mellitus using machine learning techniques. Scientific Reports 2024 14:1, 14(1), 14571-. https://doi.org/10.1038/s41598-024-64150-0

Tian, Z., Sun, X., Wang, D., & Wang, H. (2024). Association between color value of tongue and T2DM based on dose-response analyses using restricted cubic splines in China A cross-sectional study. Medicine (United States), 103(25), e38575. https://doi.org/10.1097/MD.0000000000038575

Wen, S., Li, Y., Xu, C., Jin, J., Xu, Z., Yuan, Y., Chen, L., Ren, Y., Gong, M., Wang, C., Dong, M., Zhou, Y., Yuan, X., Li, F., & Zhou, L. (2024). The Relationship Between Computerized Face and Tongue Image Segmentation and Metabolic Parameters in Patients with Type 2 Diabetes Based on Machine Learning. Diabetes, Metabolic Syndrome and Obesity, 17, 4049–4068. https://doi.org/10.2147/DMSO.S491897