Does a deep learning electrocardiogram algorithm accurately detect left ventricular systolic dysfunction in an external validation cohort?
An AI-ECG algorithm demonstrated robust performance in detecting left ventricular systolic dysfunction in an external validation cohort, though population-specific cut-offs may be required.
The AI-ECG detected LVSD with robust test performance in a population that was very different from that used to develop the algorithm. Population-specific cut-offs may be necessary for clinical implementation. Differences in population characteristics, ECG and echocardiographic data quality may affect test performance.
Attia et al. (Sat,) studied this question.