Current Applications of Artificial Intelligence for Fuchs Endothelial Corneal Dystrophy: A Systematic Review

Area of Science:

• Ophthalmology
• Medical Imaging
• Artificial Intelligence

Background:

• Fuchs endothelial corneal dystrophy (FECD) is a prevalent, age-related condition causing visual impairment.
• Systematic reviews are crucial for synthesizing evidence on emerging technologies in managing complex eye diseases.

Purpose of the Study:

• To systematically review and synthesize evidence on artificial intelligence (AI) models for the diagnosis and management of FECD.
• To assess the application, performance, and limitations of AI in FECD clinical contexts.

Main Methods:

• A comprehensive literature search was conducted across major databases (MEDLINE, PubMed, Web of Science, Scopus) from 2000 to 2024.
• Included studies focused on AI applications in FECD diagnosis and management, extracting data on model development, validation, and performance.
• Study quality was assessed using the QUADAS-2 tool, adhering to PRISMA guidelines.

Main Results:

• Nineteen studies were analyzed, primarily using neural networks for image analysis (confocal microscopy, OCT).
• AI applications included assessing corneal endothelium, edema, and predicting transplant outcomes.
• While many models showed promising performance, only three underwent external validation, and bias was noted in study designs.

Conclusions:

• AI holds significant potential for improving FECD diagnosis and prognosis.
• Further research is essential to validate AI tools for real-world clinical utility and applicability in FECD management.