Age-related macular degeneration (AMD) is a retinal condition leading to central vision loss, with exudative AMD (eAMD) being a particularly aggressive form. Traditional diagnostic methods are resource-intensive, whereas artificial intelligence (AI) offers a promising approach for rapid and accurate detection, potentially improving patient outcomes. This review assesses the diagnostic accuracy of AI in triaging eAMD.
The review found that AI algorithms demonstrated high diagnostic accuracy for detecting eAMD, with pooled sensitivity and specificity of 0.93 and 0.96, respectively, based on internal validation. Externally validated algorithms had slightly lower sensitivity (0.94) but still showed high specificity (0.99). The authors concluded that” Low‐ to very low‐certainty evidence suggests that algorithm-based tests may correctly identify most individuals with eAMD without increasing unnecessary referrals in both primary and specialty care settings.”
References:
