Literature
AI Diagnostic Performance for Tricuspid Regurgitation Detection
Evidence suggests artificial intelligence demonstrates promising diagnostic accuracy for tricuspid regurgitation detection with pooled AUROC of 0.89, potentially addressing underdiagnosis challenges in this condition that affects complex pediatric populations. Signal observed that echocardiography-based AI models achieved sensitivity of 0.87 and specificity of 0.88, though substantial heterogeneity exists across studies and methodological gaps remain.
However, heterogeneity and methodological gaps necessitate larger prospective, multicenter studies with standardized reporting (e.g., TRIPOD-AI) to confirm clinical utility.
Relevance: Tricuspid regurgitation is relevant to pulmonary hypertension research interests and occurs in complex congenital heart disease populations including Fontan patients, though this review focused primarily on adult populations.