Arrhythmias & electrophysiology
Deep Learning–Augmented Electrocardiography (ECG) Analysis for Screening and Genotype Prediction of Congenital Long QT Syndrome
Authors' conclusion
The deep learning model improved detection of congenital LQTS from resting ECGs and allowed for differentiation between the 2 most common genetic subtypes.
Study context
- Population
- Patients with suspected inherited arrhythmia (HiRO Registry, 2012–2021); Long QT syndrome (LQTS) cohort = probands and relatives with pathogenic or likely pathogenic KCNQ1 or KCNH2 variants
- Participants
- 990 patients · 4,521 ECGs
- Comparison
- Convolutional neural network (CNN)-based ECG analysis vs QTc-based detection
- Outcome
- AUC, F1 score and sensitivity for detecting LQTS and differentiating genotypes (LQTS1 vs LQTS2)
Methodological detailsmulticentre, external validation, cross-sectional validation
- Multicentre
- External validation
- Cross-sectional validation
Performance
As reported in the abstract
LQTS detection, external validation (101 patients)
| Test or model | AUC | AUC, genotype differentiation | Sensitivity | F1 score |
|---|---|---|---|---|
| CNN | 0.93 (95% CI, 0.89-0.96) | 0.91 (95% CI, 0.86-0.96) | 0.90 (95% CI, 0.86-0.94) | 0.84 (95% CI, 0.78-0.90) |
| QTc | Not reported in the abstract | Not reported in the abstract | 0.36 (95% CI, 0.23-0.47) | 0.22 (95% CI, 0.13-0.31) |
AUC
CNN0.93 (95% CI, 0.89-0.96)
QTcNot reported in the abstract
AUC, genotype differentiation
CNN0.91 (95% CI, 0.86-0.96)
QTcNot reported in the abstract
Sensitivity
CNN0.90 (95% CI, 0.86-0.94)
QTc0.36 (95% CI, 0.23-0.47)
F1 score
CNN0.84 (95% CI, 0.78-0.90)
QTc0.22 (95% CI, 0.13-0.31)
Further findings
| Outcome | CNN | QTc | |
|---|---|---|---|
| LQTS detection with normal or borderline QTc (subgroup) | |||
| F1 score | 0.70 (95% CI, 0.40-1.00) | Not reported in the abstract | QTc: not reported in the abstract |
| Sensitivity | 0.78 (95% CI, 0.53-0.95) | Not reported in the abstract | QTc: not reported in the abstract |
| LQTS detection, cross-sectional validation cohort (406 patients) | |||
| AUC | 0.81 (95% CI, 0.80-0.85) | 0.74 (95% CI, 0.69-0.78) |
Original publication
Deep Learning–Augmented ECG Analysis for Screening and Genotype Prediction of Congenital Long QT Syndrome. JAMA Cardiol. Published 1 April 2024. doi:10.
Summarised from the published abstract; every number is checked against it