Bioinformatic-Based Automated Nail Disease Diagnosis Utilising an Advanced Deep Learning Framework

The prevalence, diagnostic complexity, and visual similarity of nail disorders in different pathological conditions make them a widespread healthcare challenge that requires early and accurate identification to support timely intervention and improve healthcare accessibility, particularly in environments with limited access to specialized dermatological services. The performance of different deep learning approaches in automated nail disease classification has been better, but the existing convolutional neural network (CNN)-based methods remain constrained by limited feature representation, insufficient generalization capability, class imbalance, and lack of model interpretability. Hence, the purpose of this work is to create a novel Hybrid EfficientNet–Swin Transformer Network (HEFT-Net) that relies on medical images for automated multi-class nail disease diagnosis; EfficientNet-based convolutional feature extraction is combined with Swin Transformer-based global contextual representation learning in the proposed network to improve the ability to differentiate between different/complex nail disease patterns. The proposed HEFT-Net also incorporates attention-based feature fusion for improved feature extraction (strictly via adaptive combination of complementary representations and self-supervised learning) under limited image availability; focal loss optimization is also considered for better handling of the issue of imbalance among disease categories. Additionally, the proposed framework incorporates an explainable artificial intelligence (XAI) module for visual interpretation of disease-related regions, as well as to improve clinical transparency. Performance evaluation of the new framework was done for multi-class classification of nail diseases, where it performed exceedingly well in diagnostic capability compared with traditional CNN-based approaches. The proposed HEFT-Net recorded around 92.5 % accuracy, 92.1 % precision, 91.8 % recall, and 91.9% F1-score values. Therefore, the robustness, interpretability, and efficiency of the proposed framework as a computer-aided diagnostic framework were demonstrated, making it a significant potential for automated nail disease screening and intelligent healthcare applications.

Nail disease diagnosis, HEFT-Net, Efficient Net, Swin transformer, Deep learning, Self-supervised learning, Explainable artificial intelligence, Medical image classification

R. Ardianto, D. Yusuf, R. B. B. Sumantri, D. Febrina, R. R. Al-Hakim, and A. S. S. Ariyanto, “Bioinformatics-driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes,” in BIO Web of Conferences, EDP Sciences, 2025, p. 1024.

R. Bhuvanya et al., “Deep learning-based nail disease diagnosis leveraging the DERMANet architecture with ConvNeXt and CBAM,” Array, p. 100750, 2026.

M. Galluzzo et al., “Efficacy of tildrakizumab for the treatment of difficult-to-treat areas: scalp, nail, palmoplantar and genital psoriasis,” J. Clin. Med., vol. 11, no. 9, p. 2631, 2022.

J. K. Hwang et al., “Nail psoriasis and nail lichen planus: updates on diagnosis and management,” J. Am. Acad. Dermatol., vol. 90, no. 3, pp. 585–596, 2024.

A. Kaur and N. Gurrapu, “Smart diagnosis: Transforming nail disease identification with deep learning,” in 2025 International Conference on Next Generation Communication & Information Processing (INCIP), IEEE, 2025, pp. 807–812.

Aishwarya, A. Goel, and R. Nijhawan, “A deep learning approach for classification of onychomycosis nail disease,” in Proceedings of ICETIT 2019: Emerging Trends in Information Technology, Springer, 2019, pp. 1112–1118.

S. Sonthalia, M. Agrawal, and V. N. Sehgal, “Topical ciclopirox olamine 1%: revisiting a unique antifungal,” Indian Dermatol. Online J., vol. 10, no. 4, p. 481, 2019.

M. A. Chessa et al., “Pathogenesis, clinical signs and treatment recommendations in brittle nails: a review,” Dermatol. Ther. (Heidelb)., vol. 10, no. 1, pp. 15–27, 2020.

M. W. Cashman and S. B. Sloan, “Nutrition and nail disease,” Clin. Dermatol., vol. 28, no. 4, pp. 420–425, 2010.

K. Ri, “Perilaku hidup bersih dan sehat (phbs) penguatan kapabilitas anak dan keluarga,” Penguatan Kapabilitas Anak Dan Kel., pp. 1–14, 2020.

N. F. Fahmi, D. A. Anggraini, and Y. K. Abror, “Pola infeksi jamur kuku (onikomikosis) jari tangan dan kaki pada pekerja tempat penitipan hewan pada media potato dextrose agar (PDA),” J. Ilmu Kesehat. Bhakti Husada Heal. Sci. J., vol. 12, no. 2, pp. 107–123, 2021.

N. Sharma and P. Kaushik, “Integration of AI in healthcare systems—A discussion of the challenges and opportunities of integrating AI in healthcare systems for disease detection and diagnosis,” AI Dis. Detect. Adv. Appl., pp. 239–263, 2025.

H. Istiqomah, P. Purwono, and R. Ardianto, “Prediksi kanker darah menggunakan metode Convolutional Neural Network,” J. Ilmu Komput. dan Inform., vol. 4, no. 1, pp. 51–60, 2024.

Z. S. Naser, H. N. Khalid, A. S. Ahmed, M. S. Taha, and M. M. Hashim, “Artificial Neural Network-Based Fingerprint Classification and Recognition.,” Rev. d’Intelligence Artif., vol. 37, no. 1, 2023.

M. M. Hashim, H. J. Alhamdane, A. H. Herez, and M. S. Taha, “Based on Competitive Marketing: A New Framework mechanism in Social Media,” in IOP Conference Series: Materials Science and Engineering, IOP Publishing, 2020, p. 12121.

F. S. Hanoon, M. Çevik, and M. S. Taha, “A fault classification for defective solar cells in electroluminescence imagery based on deep learning approach,” in AIP Conference Proceedings, AIP Publishing, 2024.

Z. N. Nuimi, Z. S. Al-Eqabi, H. F. Hasan, and M. S. Taha, “Decoupling Transient from Steady-state Performance in Fractional-order PI Control of a DC Microgrid: A Bi-objective Formulation Validated Against Single-metric and Recent-metaheuristic Benchmarks.,” Int. J. Intell. Eng. Syst., vol. 19, no. 9, p. 337, 2026.

S. A. Schnawa, M. Rafie, and M. S. Taha, “DAE-DBN: An Effective Lung Cancer Detection Model Based on Hybrid Deep Learning Approaches,” in International Conference of Reliable Information and Communication Technology, Springer, 2023, pp. 108–118.

N. A. Yaseen, R. S. Hameed, M. M. Hashim, and M. S. Taha, “Enhancing Road Safety through Advanced Machine Learning: A Comparative Study of Tree Ensembles, Neural Networks, and Integrated Models for Multi-class Accident Severity Prediction under Class Imbalance.,” Int. J. Intell. Eng. Syst., vol. 19, no. 9, p. 467, 2026.

B. M. Ismael, M. A. Ngadi, J. B. M. Sharif, and M. S. Taha, “Multi-Agent Reinforcement Learning for User-Router Assignment in Multi-Radio Multi-Channel Wireless Mesh Networks.,” Int. J. Intell. Eng. Syst., vol. 18, no. 8, p. 316, 2025.

A. S. Ahmed, I. N. Abood, and M. S. Taha, “Adaptive Multi-objective Optimization for Obstacle-aware Wireless Sensor Network Deployment: A Comparative Analysis of State-of-the-Art Algorithms.,” Int. J. Intell. Eng. Syst., vol. 19, no. 2, p. 707, 2026.

I. N. Abood, A. S. Ahmed, and M. S. Taha, “An Efficient Genetic Algorithm-based Approach for Association Rule Hiding in Privacy-preserving Data Mining: A Parallel Processing Framework.,” Int. J. Intell. Eng. Syst., vol. 18, no. 11, p. 824, 2025.

S. F. Abdulghani, B. A. Shtayt, M. S. Taha, and M. M. Hashim, “Effective Knowledge Graph Representation for Cybersecurity Using AI-Based X Data and Named Entity Relation Technique,” in International Conference on Cybersecurity and Artificial Intelligence Strategies, Springer, 2025, pp. 71–89.