Search

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.

AimsFamilial recurrence studies provide strong evidence for a genetic component to the predisposition to sporadic, non-syndromic Tetralogy of Fallot (TOF), the most common cyanotic congenital heart disease (CHD) phenotype. Rare genetic variants have been identified as important contributors to the risk of CHD, but relatively small numbers of TOF cases have been studied to date. Here, we use whole exome sequencing to assess the prevalence of rare, potentially deleterious variants in candidate genes previously associated with both syndromic and non-syndromic TOF, in the largest cohort of non-syndromic TOF patients reported to date.Methods & Results829 non-syndromic TOF patients underwent whole exome sequencing. A systematic review of the literature was conducted which revealed 77 genes in which mutations had been reported in patients with TOF. The presence of rare, deleterious variants in the 77 candidate genes was determined, defined by a minor allele frequency of ≤ 0.001 and scaled combined annotation-dependent depletion (CADD) score of ≥ 20. We found a clustering of heterozygous rare, deleterious variants inNOTCH1(P=1.89E-15),DOCK6(P=2.93E-07),MYOM2(P= 7.35E-05),TTC37(P=0.016),MESP1(P=0.024) andTBX1(P=0.039), after correcting for multiple testing.NOTCH1was most frequently found to harbour deleterious variants. Changes were observed in 49 patients (6%; 95% confidence interval [CI]: 4.5% - 7.8%) and included six truncating/frameshift variants and forty missense variants. Sanger sequencing of the unaffected parents of thirteen cases identified fivede novovariants. Variants were not confined to a single functional domain of the NOTCH1 protein but significant clustering of variants was evident in the EGF-like repeats (P=0.018). ThreeNOTCH1missense variants (p.G200R, p.C607Y andde novop.N1875S) were subjected to functional evaluation and showed a reduction in Jagged1 ligand-induced NOTCH signalling. p.C607Y, which exhibited the most significant reduction in signalling, also perturbed S1 cleavage of the NOTCH1 receptor in the Golgi.ConclusionTheNOTCH1locus is a frequent site of genetic variants predisposing to non-syndromic TOF with 6% of patients exhibiting rare, deleterious variants. Our data supports the polygenic origin of TOF and suggests larger studies may identify additional loci.

To the Editor: We read with interest the report by Coronel et al1 of a case of Brugada syndrome with structural abnormalities of the heart. We would like to comment on the ECG presentation of the patient, which, in our opinion, raises an important interpretation issue. According to the criteria proposed by a group of experts that included 2 authors of the aforementioned report,2 the ECG of the patient reported in the article by Coronel et al1 does not appear to be diagnostic for Brugada syndrome. In fact, the Second Consensus Conference2 states that only “type 1 is diagnostic of Brugada syndrome and is characterized by a coved ST-segment elevation ≥2 mm, followed by a negative T wave, observed in >1 right precordial lead.” In the tracings of the patient presented by Coronel and colleagues,1 the ST-segment elevation is present only in lead V1, does not show a coved morphology in >1 lead, and has no negative T wave. As the authors discuss in the article,1 the presence of a mutation in the SCN5A gene is …