Federated and Explainable Spiking Neural Networks for Fair and Privacy-Preserving Nail Disease Diagnostics

Authors

• CH Pavani Reddy, Research scholar, Department of Electronics and Communication Engineering, Bharatiya Engineering Science & Technology Innovation University (BESTIU), Gownivaripalli, Gorantla Mandal, Sri Satya Sai District, Andhra Pradesh, IndiaFollow
• Krishnanaik Vankdoth, Professor, Department of Electronics and Communication Engineering, Chaitanya Deemed to be University, Hyderabad, IndiaFollow

Corresponding Author

Dr Krishnanaik Vankdoth

Subject Area

Electronics and Communication Engineering

Article Type

Original Study

Abstract

Automated nail disease diagnostics provide a non-invasive pathway for identifying underlying systemic health conditions; however, conventional centralized deep learning approaches often raise concerns related to privacy, fairness, and interpretability. Although the original NeuroNail-SNN framework demonstrated an energy-efficient and edge-ready diagnostic solution, its broader clinical adoption remained limited by unresolved trust, transparency, and ethical considerations. In this study, we propose the Federated and Explainable NeuroNail-SNN, which extends the original spiking neural architecture by integrating federated learning (FL), explainable artificial intelligence (XAI), fairness evaluation, and uncertainty quantification within a unified framework. Federated learning enables decentralized model training across hospitals and mobile clinics without sharing raw patient images, thereby preserving data privacy. The explainability module introduces spike saliency maps and temporal spike activity visualizations to improve transparency and clinician confidence. Fairness analysis ensures consistent diagnostic performance across demographic groups, including skin tone, gender, and age, while uncertainty quantification reduces the risk of misdiagnosis by flagging low-confidence predictions for further clinical review. Experimental results across distributed federated nodes demonstrate that the proposed model achieves 97.85% classification accuracy, with only negligible loss relative to centralized training, while maintaining equitable subgroup performance with a fairness gap below 2.5%. These findings establish NeuroNail-SNN as both an efficient and trustworthy diagnostic framework, effectively bridging the gap between neuromorphic AI research and real-world clinical deployment.

Keywords

Spiking Neural Networks, Federated Learning, Explainable AI, Fairness, Privacy-Preserving AI, Nail Disease Diagnostics

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.

Recommended Citation

Reddy, CH Pavani and Vankdoth, Krishnanaik (2026) "Federated and Explainable Spiking Neural Networks for Fair and Privacy-Preserving Nail Disease Diagnostics," Mansoura Engineering Journal: Vol. 51 : Iss. 6 , Article 3.
Available at: https://doi.org/10.58491/2735-4202.3494