The study, titled "Multi-Center Validation of an Artificial Intelligence-Enabled ECG Model to Predict 1-Year Risk of Atrial Fibrillation or Flutter," was recently published in Heart Rhythm.

AF is the most prevalent cardiac arrhythmia and is associated with an increased risk of stroke, heart failure and death. Because AF is frequently asymptomatic and paroxysmal, it can be difficult to detect; however, the application of artificial intelligence (AI) to electrocardiogram (ECG) interpretation offers a promising avenue for improving diagnosis.

This study evaluated the Tempus ECG-AF software1 across three geographically distinct clinical sites. ECG data were aggregated, and patient charts were manually reviewed to identify eligible patients: aged 65 and older with no prior AF and no history of pacemaker or defibrillator use. Study endpoints were defined as a new AF diagnosis within one year or one year of AF-free follow-up. Among the 4,017 patients evaluated, the ECG-AI-derived risk score surpassed pre-specified performance thresholds, and the resulting data supported Tempus' FDA clearance of this technology.