Bauke K.O. Arends , Peter-Paul M. Zwetsloot , Pauline S. Heeres , Wouter A.C. van Amsterdam , Maarten J. Cramer , Esther T. Kruitwagen - van Reenen , Pim van der Harst , Dirk van Osch , René van Es
{"title":"Left ventricular systolic dysfunction screening in muscular dystrophies using deep learning-based electrocardiogram interpretation","authors":"Bauke K.O. Arends , Peter-Paul M. Zwetsloot , Pauline S. Heeres , Wouter A.C. van Amsterdam , Maarten J. Cramer , Esther T. Kruitwagen - van Reenen , Pim van der Harst , Dirk van Osch , René van Es","doi":"10.1016/j.jelectrocard.2025.154048","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Routine echocardiographic monitoring is recommended in muscular dystrophy patients to detect left ventricular systolic dysfunction (LVSD) but is often challenging due to physical limitations. This study evaluates whether artificial intelligence-based electrocardiogram interpretation (AI-ECG) can detect and predict LVSD in muscular dystrophy patients.</div></div><div><h3>Methods</h3><div>Patients aged >16 years who underwent an ECG and echocardiogram within 90 days at the University Medical Center Utrecht were included. Patients with Duchenne (DMD), Becker (BMD), limb-girdle muscular dystrophy (LGMD). myotonic dystrophy (MD), and female DMD/BMD carriers, were identified. A convolutional neural network (CNN) was trained on a derivation cohort of patients without muscular dystrophy to detect LVSD and tested on muscular dystrophy patients. A Cox proportional hazards model assessed AI-ECG's predictive value for new-onset LVSD.</div></div><div><h3>Results</h3><div>The derivation cohort included 53,874 ECG-echocardiogram pairs from 30,978 patients, while the muscular dystrophy test set comprised 390 ECG-echo pairs from 390 patients. LVSD prevalence varied from 81.3 % in DMD to 13.4 % in MD. The model achieved an AUROC of 0.83 (0.79–0.87) in the muscular dystrophy test set, with sensitivity 0.87 (0.81–0.93), specificity 0.58 (0.52–0.63), NPV 0.91 (0.86–0.95), and PPV 0.49 (0.43–0.56). AI-ECG predicted new-onset LVSD with an AUROC of 0.72 (0.66–0.78), with AI-ECG probability being a significant predictor.</div></div><div><h3>Conclusions</h3><div>AI-ECG can detect LVSD in muscular dystrophy patients, offering a non-invasive, accessible tool for risk stratification and an alternative to routine echocardiography. It may also predict new-onset LVSD, enabling earlier intervention. Further research should explore external validation, pediatric application, and integration within the clinical care plan.</div></div>","PeriodicalId":15606,"journal":{"name":"Journal of electrocardiology","volume":"92 ","pages":"Article 154048"},"PeriodicalIF":1.3000,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of electrocardiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022073625001761","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Routine echocardiographic monitoring is recommended in muscular dystrophy patients to detect left ventricular systolic dysfunction (LVSD) but is often challenging due to physical limitations. This study evaluates whether artificial intelligence-based electrocardiogram interpretation (AI-ECG) can detect and predict LVSD in muscular dystrophy patients.
Methods
Patients aged >16 years who underwent an ECG and echocardiogram within 90 days at the University Medical Center Utrecht were included. Patients with Duchenne (DMD), Becker (BMD), limb-girdle muscular dystrophy (LGMD). myotonic dystrophy (MD), and female DMD/BMD carriers, were identified. A convolutional neural network (CNN) was trained on a derivation cohort of patients without muscular dystrophy to detect LVSD and tested on muscular dystrophy patients. A Cox proportional hazards model assessed AI-ECG's predictive value for new-onset LVSD.
Results
The derivation cohort included 53,874 ECG-echocardiogram pairs from 30,978 patients, while the muscular dystrophy test set comprised 390 ECG-echo pairs from 390 patients. LVSD prevalence varied from 81.3 % in DMD to 13.4 % in MD. The model achieved an AUROC of 0.83 (0.79–0.87) in the muscular dystrophy test set, with sensitivity 0.87 (0.81–0.93), specificity 0.58 (0.52–0.63), NPV 0.91 (0.86–0.95), and PPV 0.49 (0.43–0.56). AI-ECG predicted new-onset LVSD with an AUROC of 0.72 (0.66–0.78), with AI-ECG probability being a significant predictor.
Conclusions
AI-ECG can detect LVSD in muscular dystrophy patients, offering a non-invasive, accessible tool for risk stratification and an alternative to routine echocardiography. It may also predict new-onset LVSD, enabling earlier intervention. Further research should explore external validation, pediatric application, and integration within the clinical care plan.
期刊介绍:
The Journal of Electrocardiology is devoted exclusively to clinical and experimental studies of the electrical activities of the heart. It seeks to contribute significantly to the accuracy of diagnosis and prognosis and the effective treatment, prevention, or delay of heart disease. Editorial contents include electrocardiography, vectorcardiography, arrhythmias, membrane action potential, cardiac pacing, monitoring defibrillation, instrumentation, drug effects, and computer applications.