Artificial intelligence techniques in inherited retinal diseases: a review

Area of Science:

• Ophthalmology
• Medical Artificial Intelligence
• Genetics

Background:

• Inherited retinal diseases (IRDs) are a leading cause of vision loss in adults.
• The complexity of IRDs presents diagnostic and management challenges.
• Artificial intelligence (AI) shows potential for addressing these challenges.

Purpose of the Study:

• To review and consolidate AI applications in diagnosing and managing IRDs.
• To identify knowledge gaps and future research directions in AI for IRDs.
• To explore the role of machine learning, deep learning, and explainable AI in IRD clinical pathways.

Main Methods:

• Literature review of existing studies on AI in IRDs.
• Analysis of AI techniques including machine learning and deep learning.
• Discussion of explainable AI for clinical transparency and trust.

Main Results:

• AI offers potential in disease detection, progression prediction, and personalized treatment for IRDs.
• Fragmented knowledge exists regarding AI's varied applications in this field.
• Explainable AI is crucial for clinical adoption.

Conclusions:

• AI presents significant opportunities for advancing IRD diagnosis and management.
• Further research is needed to bridge existing gaps in AI for IRDs.
• Interdisciplinary collaboration and development of robust, interpretable AI models are essential for clinical translation.