Detection of Hypertrophic Cardiomyopathy in Athletes Using Artificial Intelligence-Enhanced ECG
A comprehensive systematic review has been prepared on AI-enhanced ECG analyses aimed at distinguishing physiological cardiac adaptations from pathological findings in athletes.
A new systematic review study has been conducted to examine the diagnostic accuracy and external validity of artificial intelligence and machine learning-supported electrocardiography methods in detecting hypertrophic cardiomyopathy in athletes.
Background of the Research
Hypertrophic cardiomyopathy is known as a clinically significant myocardial disorder associated with ventricular arrhythmias and sudden cardiac events. The primary goal in the cardiovascular evaluation of athletes is to identify the disease at an early stage and differentiate physiological adaptations due to training from pathological findings.
The Role of Artificial Intelligence
Artificial intelligence-enhanced electrocardiography technologies can complement traditional interpretation methods by detecting complex combinations of ECG features. This approach holds the potential to support standardized evaluation processes and prioritization for imaging tests.
Methods and Database Searches
The systematic review was registered on the PROSPERO platform as a diagnostic test accuracy study guided by PRISMA-DTA. Comprehensive searches were conducted across multiple databases, including PubMed, Embase, CENTRAL, Scopus, Web of Science, Europe PMC, IEEE Xplore, ClinicalTrials.gov, and WHO ICTRP, up to June 2026.
Scope of the Study
The studies included in the research evaluated athletes or clearly defined athlete screening populations. During this process, existing hypertrophic cardiomyopathy was examined against an imaging-supported clinical reference standard using artificial intelligence or machine learning methods on ECG signals.