Key result
ECG-based machine learning algorithms accurately detect congenital long QT syndrome with a pooled 0.95 AUC.
Why the study?
The study was conducted to discover the performance of machine learning algorithms in identifying congenital long QT syndrome.
Do electrocardiogram-based machine learning algorithms accurately identify Congenital long QT syndrome?
Population
8 studies evaluating detection of congenital long QT syndrome
Comparison
Machine learning algorithms for detecting LQTS
Design
Systematic review and meta-analysis
Authors
Loading...
Supports ECG machine learning deployment for congenital long QT syndrome screening; extends single-study validations through pooled meta-analysis.
Meta-Analysis (n=16,584)
Do electrocardiogram-based machine learning algorithms accurately identify Congenital long QT syndrome?
Odds Ratio: 65 (95% CI 39–109)
Electrocardiogram-based machine learning algorithms demonstrate high diagnostic accuracy for detecting congenital long QT syndrome, highlighting their potential for intelligent ECG interpretation.
Wu et al. (2023) conducted a meta-analysis in Congenital long QT syndrome (LQTS) (n=16,584). Electrocardiogram-based machine learning vs. Standard clinical and genetic diagnosis was evaluated on Diagnostic accuracy for detecting LQTS (Diagnostic Odds Ratio) (DOR 65, 95% CI 39-109). Electrocardiogram-based machine learning algorithms accurately detected congenital long QT syndrome with a pooled area under the curve of 0.95 and a diagnostic odds ratio of 65.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: