Key result
Artificial intelligence tools demonstrated high pooled diagnostic accuracy (80.50%; 95% CI 80.4-80.60) and sensitivity (89.29%) for detecting left ventricular hypertrophy.
Why the study?
Although studies show the utility of artificial intelligence for diagnosing left ventricular hypertrophy, its accuracy compared with common electrocardiographic criteria required systematic evaluation.
Do artificial intelligence tools improve the diagnostic accuracy, sensitivity, and specificity for detecting left ventricular hypertrophy compared to conventional electrocardiographic criteria?
Population
Nine studies comprising 31 657 patients in testing and 100 271 in training datasets
Comparison
AI tools vs electrocardiographic criteria including Sokolow-Lyon and Cornell
Design
Meta-analysis
Authors
Loading...
May enhance ECG-based LVH detection; extends diagnostic meta-analyses but requires prospective outcome trials before practice change.
Meta-Analysis (n=131,928)
Do artificial intelligence tools improve the diagnostic accuracy, sensitivity, and specificity for detecting left ventricular hypertrophy compared to conventional electrocardiographic criteria?
Effect estimate: accuracy 80.50 (95% CI 80.4-80.60)
Artificial intelligence tools demonstrate higher diagnostic accuracy, sensitivity, and specificity compared to conventional ECG criteria for detecting left ventricular hypertrophy.
Suchal et al. (2024) conducted a meta-analysis in Left ventricular hypertrophy (LVH) (n=131,928). Artificial intelligence (AI) tools vs. Electrocardiographic criteria (Sokolow-Lyon and Cornell) was evaluated on Diagnostic accuracy for the detection of LVH (accuracy 80.50, 95% CI 80.4-80.60). Artificial intelligence tools demonstrated high pooled diagnostic accuracy (80.50%; 95% CI 80.4-80.60) and sensitivity (89.29%) for detecting left ventricular hypertrophy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: