A deep learning approach identifies new ECG features in congenital long QT syndrome.

BACKGROUND: Congenital long QT syndrome (LQTS) is a rare heart disease caused by various underlying mutations. Most general cardiologists do not routinely see patients with congenital LQTS and may not always recognize the accompanying ECG features. In addition, a proportion of disease carriers do not display obvious abnormalities on their ECG. Combined, this can cause underdiagnosing of this potentially life-threatening disease. METHODS: This study presents 1D convolutional neural network models trained to identify genotype positive LQTS patients from electrocardiogram as input. The deep learning (DL) models were trained with a large 10-s 12-lead ECGs dataset provided by Amsterdam UMC and externally validated with a dataset provided by University Hospital Leuven. The Amsterdam dataset included ECGs from 10000 controls, 172 LQTS1, 214 LQTS2, and 72 LQTS3 patients. The Leuven dataset included ECGs from 2200 controls, 32 LQTS1, and 80 LQTS2 patients. The performance of the DL models was compared with conventional QTc measurement and with that of an international expert in congenital LQTS (A.A.M.W). Lastly, an explainable artificial intelligence (AI) technique was used to better understand the prediction models. RESULTS: Overall, the best performing DL models, across 5-fold cross-validation, achieved on average a sensitivity of 84 ± 2%, 90 ± 2% and 87 ± 6%, specificity of 96 ± 2%, 95 ± 1%, and 92 ± 4%, and AUC of 0.90 ± 0.01, 0.92 ± 0.02, and 0.89 ± 0.03, for LQTS 1, 2, and 3 respectively. The DL models were also shown to perform better than conventional QTc measurements in detecting LQTS patients. Furthermore, the performances held up when the DL models were validated on a novel external cohort and outperformed the expert cardiologist in terms of specificity, while in terms of sensitivity, the DL models and the expert cardiologist in LQTS performed the same. Finally, the explainable AI technique identified the onset of the QRS complex as the most informative region to classify LQTS from non-LQTS patients, a feature previously not associated with this disease. CONCLUSIONS: This study suggests that DL models can potentially be used to aid cardiologists in diagnosing LQTS. Furthermore, explainable DL models can be used to possibly identify new features for LQTS on the ECG, thus increasing our understanding of this syndrome.

Enhancing rare variant interpretation in inherited arrhythmias through quantitative analysis of consortium disease cohorts and population controls.

PURPOSE: Stringent variant interpretation guidelines can lead to high rates of variants of uncertain significance (VUS) for genetically heterogeneous disease like long QT syndrome (LQTS) and Brugada syndrome (BrS). Quantitative and disease-specific customization of American College of Medical Genetics and Genomics/Association for Molecular Pathology (ACMG/AMP) guidelines can address this false negative rate. METHODS: We compared rare variant frequencies from 1847 LQTS (KCNQ1/KCNH2/SCN5A) and 3335 BrS (SCN5A) cases from the International LQTS/BrS Genetics Consortia to population-specific gnomAD data and developed disease-specific criteria for ACMG/AMP evidence classes-rarity (PM2/BS1 rules) and case enrichment of individual (PS4) and domain-specific (PM1) variants. RESULTS: Rare SCN5A variant prevalence differed between European (20.8%) and Japanese (8.9%) BrS patients (p = 5.7 × 10-18) and diagnosis with spontaneous (28.7%) versus induced (15.8%) Brugada type 1 electrocardiogram (ECG) (p = 1.3 × 10-13). Ion channel transmembrane regions and specific N-terminus (KCNH2) and C-terminus (KCNQ1/KCNH2) domains were characterized by high enrichment of case variants and >95% probability of pathogenicity. Applying the customized rules, 17.4% of European BrS and 74.8% of European LQTS cases had (likely) pathogenic variants, compared with estimated diagnostic yields (case excess over gnomAD) of 19.2%/82.1%, reducing VUS prevalence to close to background rare variant frequency. CONCLUSION: Large case-control data sets enable quantitative implementation of ACMG/AMP guidelines and increased sensitivity for inherited arrhythmia genetic testing.

A phenotype-enhanced variant classification framework to decrease the burden of missense variants of uncertain significance in type 1 long QT syndrome.

BACKGROUND: Pathogenic/likely pathogenic (P/LP) variants in the KCNQ1-encoded Kv7.1 potassium channel cause type 1 long QT syndrome (LQT1). Despite the revamped 2015 American College of Medical Genetics (ACMG) variant interpretation guidelines, the burden of KCNQ1 variants of uncertain significance (VUS) in patients with LQTS remains ∼30%. OBJECTIVE: The purpose of this study was to determine whether a phenotype-enhanced (PE) variant classification approach could reduce the VUS burden in LQTS genetic testing. METHODS: Retrospective analysis was performed on 79 KCNQ1 missense variants in 356 patients from Mayo Clinic and an independent cohort of 42 variants in 225 patients from Amsterdam University Medical Center (UMC). Each variant was classified initially using the ACMG guidelines and then readjudicated using a PE-ACMG framework that incorporated the LQTS clinical diagnostic Schwartz score plus 4 "LQT1-defining features": broad-based/slow upstroke T waves, syncope/seizure during exertion, swimming-associated events, and a maladaptive LQT1 treadmill stress test. RESULTS: According to the ACMG guidelines, Mayo Clinic variants were classified as follows: 17 of 79 P variants (22%), 34 of 79 LP variants (43%), and 28 of 79 VUS (35%). Similarly, for Amsterdam UMC, the variant distribution was 9 of 42 P variants (22%), 14 of 42 LP variants (33%), and 19 of 42 variants VUS (45%). After PE-ACMG readjudication, the total VUS burden decreased significantly from 28 (35%) to 13 (16%) (P = .0007) for Mayo Clinic and from 19 (45%) to 12 (29%) (P = .02) for Amsterdam UMC. CONCLUSION: Phenotype-guided variant adjudication decreased significantly the VUS burden of LQT1 case-derived KCNQ1 missense variants in 2 independent cohorts. This study demonstrates the value of incorporating LQT1-specific phenotype/clinical data to aid in the interpretation of KCNQ1 missense variants identified during genetic testing for LQTS.