Artificial Intelligence in Inherited Epidermolysis Bullosa: Current Evidence, Challenges, and Future Directions

Area of Science:

• Genodermatoses and Computational Biology
• Medical Diagnostics and Therapeutics
• Artificial Intelligence in Medicine

Background:

• Epidermolysis Bullosa (EB) is a rare genetic skin disorder causing severe blistering and chronic wounds, with limited treatment options.
• Key challenges in EB management include delayed diagnosis, objective wound monitoring, early cancer detection, and disease-modifying therapies.
• Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), is emerging as a tool to address these unmet needs in EB.

Purpose of the Study:

• To review current evidence on AI applications in Epidermolysis Bullosa research and clinical practice.
• To explore AI's role in genetic diagnostics, wound assessment, inflammatory endotyping, drug repurposing, and novel therapeutic technologies for EB.
• To identify translational barriers and propose interventions for accelerating AI adoption in EB.

Main Methods:

• Structured narrative review synthesizing evidence from research studies and registered clinical trials on AI in EB.
• Analysis of AI applications in genomics (variant detection), wound care (monitoring, prediction), and drug discovery (repurposing).
• Discussion of emerging AI-driven therapeutic technologies and translational challenges.

Main Results:

• Deep learning models accelerate pathogenic variant detection, reducing diagnostic latency in EB.
• AI platforms enable automated wound segmentation, remote monitoring, and healing trajectory prediction.
• Computational transcriptomics identified potential drug repurposing candidates for EB.
• AI integration with biosensors and 3D bioprinting shows future therapeutic promise.

Conclusions:

• AI offers significant potential to improve diagnosis, wound management, and therapeutic development for Epidermolysis Bullosa.
• Addressing challenges like limited datasets, algorithmic bias, and interpretability is crucial for AI implementation.
• Standardized data collection through disease registries and imaging protocols is vital for advancing AI in EB.