Abstract Body (Do not enter title and authors here): Background: This randomized crossover trial aimed to investigate whether an artificial intelligence (AI)-based automatic analysis tool for echocardiography could streamline the daily examination workflow of sonographers in real-world clinical practice.
Methods: A single-center, randomized crossover trial was conducted with four certified sonographers who performed screening echocardiography for cardiovascular risk assessment. Each study day, the use of AI for automatic echocardiography analysis was randomly assigned, with sonographers either using AI assistance (AI days) or performing exams without it (non-AI days). Expert echocardiologists reviewed and finalized all reports. The primary endpoint was examination efficiency, defined as the time for one examination and the number of examinations performed per day.
Results: Sonographers scanned 585 patients over 38 study days, equally divided between AI days (n = 317) and non-AI days (n = 268). The scanning characteristics were comparable between the two groups, with most patients having no significant cardiovascular disease. AI assistance significantly reduced the time per examination to 13.0±3.5 minutes compared to 14.3±4.2 minutes on non-AI days (p < 0.001), and increased the average number of examinations per day to 16.7±2.5 from 14.1±2.5 (p = 0.003). Despite the higher number of examinations, sonographers reported less mental fatigue on AI days (4.1±1.1 vs. 4.7±0.6 on a Likert scale, p = 0.039). The number of echocardiographic parameters analyzed per study increased 3.4-fold on AI days compared to non-AI days (85±12 vs. 25±1, p < 0.001). Differences between AI’s initial measurements and the final expert-endorsed reports were within clinically acceptable limits in 90% of cases for nearly all parameters. Notably, AI days allowed sonographers to focus more on image acquisition, significantly improving the quality of echocardiographic images (p < 0.001).
Conclusions: This real-world randomized trial demonstrated that AI-based automatic analysis significantly improves the efficiency of screening echocardiography by reducing examination time, while maintaining image quality and reducing sonographer fatigue.