A Smart System for Non-Invasive Early Detection of Diabetes through Deep Learning-Based Nail Image Analysis and Expert Systems

Muhammad Zulfikri; Wirajaya Kusuma; Naufal A.  Furqan

doi:10.52436/1.jutif.2026.7.2.5347

Authors

Muhammad Zulfikri Information Technology, Bumigora University, Indonesia
Wirajaya Kusuma Software Engineering, Bumigora University, Indonesia
Naufal A. Furqan Information Technology, Bumigora University, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.2.5347

Keywords:

Deep learning, Diabetes mellitus, Early detection, Expert system, Nail images

Abstract

Public health in Indonesia faces significant challenges in the early detection of diseases, particularly in areas with limited medical services. Diabetes Mellitus can lead to serious complications, but its detection is often hindered by limited access to invasive and expensive diagnostic methods. This study aims to develop a non-invasive early detection system through nail image analysis using a deep learning method based on EfficientNet-B7 and a rule-based expert system. The system classifies nail images into five categories: Healthy, Beaus lines, Onycholysis, Onychomycosis, and Paronychia. The evaluation results show an accuracy of 97.11% on the test set, demonstrating excellent performance in detecting nail conditions associated with diabetes. The application of the expert system using Forward Chaining and Certainty Factor provides in-depth medical explanations for the model's predictions, making this system a potential solution for diabetes screening that is fast, affordable, and accessible across various healthcare facilities.

Downloads

Download data is not yet available.

References

U. Sujianto and I. Riniatsih, “Peningkatan Pengetahuan dan Kesadaran Masyarakat Terhadap Deteksi Dini Penyakit Deabetes Melitus dan Hipertensi,” J. Pengabdi. Perawat, vol. 1, no. 1, pp. 1–6, 2022, doi: 10.32584/jpp.v1i1.1513.

L. C. Ratri et al., “The Potential of Nail Glycation Examination for Detecting Diabetes Mellitus: A Systematic Review and Meta-Analysis,” Res. J. Pharm. Technol., vol. 17, no. 9, pp. 4528–4534, 2024, doi: 10.52711/0974-360X.2024.00700.

S. Widaty et al., “Clinical and microbiological characteristics of onychomycosis in a tertiary hospital: a cross-sectional study,” Med. J. Indones., vol. 33, no. 1, pp. 17–23, 2024, doi: 10.13181/mji.oa.247201.

M. Wahidin et al., “Projection of diabetes morbidity and mortality till 2045 in Indonesia based on risk factors and NCD prevention and control programs,” Sci. Rep., vol. 14, no. 1, 2024, doi: 10.1038/s41598-024-54563-2.

I. Leila, Huned Materwala, and Juma Al Kaabi 2, “Association of Risk Factors with Type 2 Diabetes : A Systematic Review,” Comput. Struct. Biotechnol. J., vol. 7, no. 4, pp. 1759–1785, 2021, doi: 10.23887/jst-undiksha.v14i2.100794.

P. Vidyasagar and B. P. Kumar, “Toe nail changes in diabetes mellitus,” IP Indian J. Clin. Exp. Dermatology, vol. 7, no. 1, pp. 40–46, 2021, doi: 10.18231/j.ijced.2021.008.

M. Satasia and A. H. Sutaria, “Nail Whispers Revealing Dermatological and Systemic Secrets: An Analysis of Nail Disorders Associated With Diverse Dermatological and Systemic Conditions,” Cureus, vol. 15, no. 9, pp. 1–20, Sep. 2023, doi: 10.7759/cureus.45007.

D. Lazaro-Pacheco, P. F. Taday, and P. M. Paldánius, “Exploring in-vivo infrared spectroscopy for nail-based diabetes screening,” Biomed. Opt. Express, vol. 15, no. 3, pp. 1926–1942, Mar. 2024, doi: 10.1364/BOE.520102.

I. Kurniastuti, A. Andini, and M. R. Dwisapta, “Implementation of Neural Network for Classification of Diabetes Mellitus through Finger Nail Image,” in Procedia Computer Science, Elsevier, Jan. 2024, pp. 1625–1632. doi: 10.1016/J.PROCS.2024.03.166.

C. Unigarro, J. Hernandez, and H. Florez, “Artificial Neural Networks for Image Processing in Precision Agriculture: A Systematic Literature Review on Mango, Apple, Lemon, and Coffee Crops,” Informatics, vol. 12, no. 2, 2025, doi: 10.3390/informatics12020046.

C. Krupadanam, R. Narendran, and V. Thiruchelvam, “Comparing the accuracy of a convolutional neural network algorithm with K-nearest neighbors algorithm for the cardiac diagnosis,” AIP Conf. Proc., vol. 3161, no. 1, p. 20243, 2024, doi: 10.1063/5.0229269.

G. Shandilya et al., “Autonomous detection of nail disorders using a hybrid capsule CNN: a novel deep learning approach for early diagnosis,” BMC Med. Inform. Decis. Mak., vol. 24, no. 1, pp. 1–19, 2024, doi: 10.1186/s12911-024-02840-5.

V. Gaurav, C. Grover, M. Tyagi, and S. Saurabh, “Artificial Intelligence in Diagnosis and Management of Nail Disorders: A Narrative Review,” Indian Dermatol. Online J., vol. 16, no. 1, pp. 40–49, Jan. 2025, doi: 10.4103/idoj.idoj_460_24.

I. Rehan, K. Rehan, S. Sultana, and M. Ur Rehman, “Fingernail Diagnostics: Advancing type II diabetes detection using machine learning algorithms and laser spectroscopy,” in Microchemical Journal, Elsevier, Jun. 2024, p. 110762. doi: 10.1016/J.MICROC.2024.110762.

D. R. Raman, S. Nishanthi, and P. Babysha, “Diagnosis of Diabetic Retinopathy by using EfficientNet-B7 CNN Architecture in Deep Learning,” in 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS), 2023, pp. 430–435. doi: 10.1109/ICSCSS57650.2023.10169453.

M. Ebadi Jalal, O. S. Emam, C. Castillo-Olea, B. García-Zapirain, and A. Elmaghraby, “Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning,” Sci. Rep., vol. 15, no. 1, p. 2068, 2025, doi: 10.1038/s41598-025-85277-8.

Z. Huang, L. Su, J. Wu, and Y. Chen, “Rock Image Classification Based on EfficientNet and Triplet Attention Mechanism,” Appl. Sci., vol. 13, no. 5, 2023, doi: 10.3390/app13053180.

L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data, vol. 8, no. 1, 2021, doi: 10.1186/s40537-021-00444-8.

D. Moch., Syahrir; I, Nyoman, Switrayana; I, Made, Angga, Wahyu, “Integrasi Bagging dan Stacking untuk Memperbaiki Kinerja Algoritma Klasifikasi C4.5 dan K-Nearest Neighbor (KNN),” J. Sains dan Teknol., vol. 14, no. 2, pp. 218–228, 2025.

Y. Segal, O. Hadar, and L. Lhotska, “Using EfficientNet-B7 (CNN), Variational Auto Encoder (VAE) and Siamese Twins’ Networks to Evaluate Human Exercises as Super Objects in a TSSCI Images,” J. Pers. Med., vol. 13, no. 5, 2023, doi: 10.3390/jpm13050874.

Z. E. Fitri, E. M. Ramadania, N. S. Wibowo, I. P. D. Lesmana, and A. M. N. Imron, “A Combination of Forward Chaining and Certainty Factor Methods for Early Detection of Fever : Dengue Hemorrhagic Fever, Malaria and Typhoid,” Sci. J. Informatics, vol. 9, no. 1, pp. 23–31, 2022, doi: 10.15294/sji.v9i1.33007.

D. A. P and L. Isyriyah, “Rancang Model Expert System pada Diagnosa Penyakit Diabetes Melitus dengan Metode Forward Chaining,” J. Teknol. dan Manaj. Inform., vol. 7, no. 1, pp. 51–61, 2021, doi: 10.26905/jtmi.v7i1.5930.

B. Saputra, A. Utami, Edriyansyah, and Y. Irawan, “Expert System for Diagnosing Diseases in Toddlers Using the Certainty Factor Method,” J. Appl. Eng. Technol. Sci., vol. 4, no. 1, pp. 32–41, 2022, doi: 10.37385/jaets.v4i1.916.

M. Zulfikri, W. Kusuma, S. Hadi, H. Husain, R. Hammad, and L. Z. A. Mardedi, “Speed Bump System Based on Vehicle Speed using Adaptive Background Subtraction with Haar Cascade Classifier,” Sistemasi, vol. 13, no. 3, p. 1054, 2024, doi: 10.32520/stmsi.v13i3.3921.

L. Z. A. Mardedi, M. Zulfikri, M. Syahrir, K. A. Latif, and Apriani, “Face Recognition for Personal Data Collection using Eigenface, Support Vector Machine, and Viola Jones Method,” Sistemasi, vol. 14, no. 1, pp. 135–146, 2025, doi: https://doi.org/10.32520/stmsi.v14i1.

M. Daga, D. Parikh, and S. P. Ramu, “DeepSeqCoco: A Robust Mobile Friendly Deep Learning Model for Detection of Diseases in Cocos Nucifera,” in IEEE Access, 2025, pp. 89367–89385. doi: 10.1109/ACCESS.2025.3571800.

U. Haziq et al., “Improving lung cancer detection with enhanced convolutional sequential networks,” Sci. Rep., vol. 15, no. 1, p. 32099, 2025, doi: 10.1038/s41598-025-06653-y.

C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, p. 60, 2019, doi: 10.1186/s40537-019-0197-0.

Y. Pamungkas and D. S. Eljatin, “Hyperparameter Tuning of EfficientNet Method for Optimization of Malaria Detection System Based on Red Blood Cell Image,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 13, no. 3, pp. 360–368, 2024, doi: 10.32736/sisfokom.v13i3.2257.

Z. Can and Ş. Işık, “Diagnosing Diseases From Fingernail Images,” Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimar. Fakültesi Derg., vol. 30, no. 3, pp. 464–470, 2022, doi: 10.31796/ogummf.1111749.