Fully automated AI-assisted echocardiography reduced median analysis time to 94 seconds versus 490 seconds for human workflow, while maintaining noninferior LVEF accuracy.
Cross-Sectional (n=40)
Single-blind
No
Does a fully automated artificial intelligence system reduce total analysis time and preserve LVEF accuracy compared to a trained cardiac sonographer in TTE examinations?
Fully automated AI-assisted echocardiographic analysis significantly reduces workflow time while maintaining noninferior accuracy for LVEF measurement.
Absolute Event Rate: 94% vs 490%
p-value: p=<0.001
Abstract Background Transthoracic echocardiography (TTE) requires time-intensive integration of quantitative measurements and qualitative visual assessment. Fully automated artificial intelligence (AI)-based analysis may reduce total analysis time while preserving accuracy, but systematic real-world validation remains limited. Methods This prospective, single-center pilot study enrolled 40 TTE examinations. Identical deidentified DICOM datasets were independently provided to a trained cardiac sonographer and a fully automated AI system comprising quantitative and qualitative visual interpretation modules. All outputs were compared with a cardiologist-adjudicated reference standard. Primary endpoints were total analysis time and noninferiority of AI-derived left ventricular ejection fraction (LVEF) versus the reference standard, with a prespecified margin of 3 percentage points (one-sided α = 0.025). Results Median analysis time was 94 s (interquartile range IQR, 82–106 s) for the AI workflow versus 490 s (IQR, 438–626 s) for the human workflow (P < 0.001). AI-derived LVEF met the noninferiority criterion (mean difference, 0.00 percentage points; upper one-sided 95% confidence bound, 1.41 percentage points; P < 0.001), with an intraclass correlation coefficient (ICC) of 0.902 (95% confidence interval, 0.822–0.947). ICCs for secondary quantitative indices ranged from 0.625 to 0.989. For aortic regurgitation severity grading, AI’s overall accuracy was 75.0% (quadratic weighted κ = 0.762), compared with 82.5% for human interpretation (κ = 0.812, McNemar P = 0.579). Conclusions Fully automated AI-assisted TTE analysis substantially reduced total analysis time while maintaining noninferior LVEF accuracy and acceptable performance across secondary quantitative and qualitative indices. These findings support the use of AI as a practical workflow accelerator in routine echocardiography.
Sun et al. (Wed,) conducted a cross-sectional in Transthoracic echocardiography (TTE) (n=40). Fully automated AI-based echocardiographic analysis vs. Human analysis (trained cardiac sonographer) was evaluated on Total analysis time (seconds) (p=<0.001). Fully automated AI-assisted echocardiography reduced median analysis time to 94 seconds versus 490 seconds for human workflow, while maintaining noninferior LVEF accuracy.