
Meta-Analysis of the Performance of AI-Driven ECG Interpretation in the Diagnosis of Valvular Heart Diseases
Artificial intelligence (AI) applied to electrocardiogram (ECG) interpretation shows high accuracy for early detection of valvular heart diseases (VHDs), based on a meta-analysis of data from 713,537 patients, with pooled accuracy and sensitivity of 81% and 83%, respectively. However, the low positive predictive value (PPV) of 13% suggests that AI should be used in conjunction with clinical judgment for VHD screening in primary care settings.