Hypertrophic cardiomyopathy (HCM) is an uncommon but important cause of sudden cardiac death.
This study sought to develop an artificial intelligence approach for the detection of HCM based on ...12-lead electrocardiography (ECG).
A convolutional neural network (CNN) was trained and validated using digital 12-lead ECG from 2,448 patients with a verified HCM diagnosis and 51,153 non-HCM age- and sex-matched control subjects. The ability of the CNN to detect HCM was then tested on a different dataset of 612 HCM and 12,788 control subjects.
In the combined datasets, mean age was 54.8 ± 15.9 years for the HCM group and 57.5 ± 15.5 years for the control group. After training and validation, the area under the curve (AUC) of the CNN in the validation dataset was 0.95 (95% confidence interval CI: 0.94 to 0.97) at the optimal probability threshold of 11% for having HCM. When applying this probability threshold to the testing dataset, the CNN’s AUC was 0.96 (95% CI: 0.95 to 0.96) with sensitivity 87% and specificity 90%. In subgroup analyses, the AUC was 0.95 (95% CI: 0.94 to 0.97) among patients with left ventricular hypertrophy by ECG criteria and 0.95 (95% CI: 0.90 to 1.00) among patients with a normal ECG. The model performed particularly well in younger patients (sensitivity 95%, specificity 92%). In patients with HCM with and without sarcomeric mutations, the model-derived median probabilities for having HCM were 97% and 96%, respectively.
ECG-based detection of HCM by an artificial intelligence algorithm can be achieved with high diagnostic performance, particularly in younger patients. This model requires further refinement and external validation, but it may hold promise for HCM screening.
Display omitted
Background:The usefulness of electrocardiographic (ECG) voltage criteria for diagnosing hypertrophic cardiomyopathy (HCM) in pediatric patients is poorly defined.Methods and Results:ECGs at the 1st ...grade (mean ±SD age 6.6±0.3 years) were available for 11 patients diagnosed with HCM at around the 7th grade (13.2±0.3 years). ECGs were available for another 64 patients diagnosed with HCM in the 1st (n=15), 7th (n=32), and 10th (n=17) grades. Fifty-one voltage criteria were developed by grade and sex using 62,841 ECGs from the general population. Voltage criteria were set at the 99.95th percentile (1/2,000) point based on the estimated prevalence of childhood HCM (2.9 per 100,000 1/34,483) to decrease false negatives. Conventional criteria were from guidelines for school-aged children in Japan. Of 11 patients before diagnosis, 2 satisfied conventional criteria in 1st grade; 5 (56%) of the remaining 9 patients fulfilled 2 voltage criteria (R wave in limb-lead I RI+S wave in lead V3 SV3 and R wave in lead V3 RV3+SV3). Robustness analysis for sensitivity showed RV3+SV3 was superior to RI+SV3. For all patients after diagnosis, RI+SV4 was the main candidate. However, conventional criteria were more useful than voltage criteria.Conclusions:Early HCM prediction was possible using RV3+SV3 in >50% of patients in 1st grade. Voltage criteria may help diagnose prediagnostic or early HCM, and prevent tragic accidents, although further prospective studies are required.
MYBPC3 is the most frequently mutated gene in hypertrophic cardiomyopathy (HCM). Several loss-of-function founder variants have been reported in MYBPC3 from various geographic regions, altogether ...suggestive of a modest or absent effect of these variants on reproductive fitness. One of them, a MYBPC3 splice variant, NM_000256.3:c.3330+2T > G, was first described in homozygous state in newborns presenting with a severe, recessive form of HCM among the Amish population and was later associated with adult-onset dominant HCM in heterozygous carriers. We here report this splice variant in heterozygous state in eight unrelated Swiss families with HCM, making it the most prevalent cardiomyopathy variant in western Switzerland. This variant was identified in patients using targeted (n = 5) or full-genome sequencing (n = 3). Given the prevalence of this variant in the Old Order Amish, Mennonites and Swiss populations, and given that both Amish and Mennonites founders originated from the Bern Canton in Switzerland, the MYBPC3, NM_000256.3:c.3330+2T > G variant appears to be of Swiss origin. Neighboring regions that hosted the first Amish settlements (Alsace, South Germany) should be on the lookout for that variant. The existence of MYBPC3 founder variants in different populations suggests that individuals with early-onset clinical disease may be the tip of the iceberg of a much larger number of asymptomatic carriers. Alternatively, reproductive fitness could even be slightly increased in some variant carriers to compensate for the reduction of fitness in the more severely affected ones, but this remains to be investigated.
Cardiomyopathies are a heterogeneous group of heart muscle diseases and an important cause of heart failure (HF). Current knowledge on incidence, pathophysiology and natural history of HF in ...cardiomyopathies is limited, and distinct features of their therapeutic responses have not been systematically addressed. Therefore, this position paper focuses on epidemiology, pathophysiology, natural history and latest developments in treatment of HF in patients with dilated (DCM), hypertrophic (HCM) and restrictive (RCM) cardiomyopathies. In DCM, HF with reduced ejection fraction (HFrEF) has high incidence and prevalence and represents the most frequent cause of death, despite improvements in treatment. In addition, advanced HF in DCM is one of the leading indications for heart transplantation. In HCM, HF with preserved ejection (HFpEF) affects most patients with obstructive, and ∼10% of patients with non‐obstructive HCM. A timely treatment is important, since development of advanced HF, although rare in HCM, portends a poor prognosis. In RCM, HFpEF is common, while HFrEF occurs later and more frequently in amyloidosis or iron overload/haemochromatosis. Irrespective of RCM aetiology, HF is a harbinger of a poor outcome. Recent advances in our understanding of the mechanisms underlying the development of HF in cardiomyopathies have significant implications for therapeutic decision‐making. In addition, new aetiology‐specific treatment options (e.g. enzyme replacement therapy, transthyretin stabilizers, immunoadsorption, immunotherapy, etc.) have shown a potential to improve outcomes. Still, causative therapies of many cardiomyopathies are lacking, highlighting the need for the development of effective strategies to prevent and treat HF in cardiomyopathies.