Artificial Intelligence-based Automated Echocardiographic Analysis and the Workflow of Sonographers: A randomized crossover trial

Abstract

Abstract Background This randomized crossover trial aimed to evaluate whether an artificial intelligence (AI)-based automatic analysis tool for echocardiography could improve the daily workflow of sonographers in real-world clinical practice. Methods A single-center randomized crossover trial was conducted with four certified sonographers. Each study day, the use of AI-based automatic echocardiography analysis was randomly assigned: either AI assistance (AI days) or manual workflow (non-AI days). The AI tool automatically analyzed echocardiographic images and provided measurements, enabling sonographers to focus on verifying AI-generated values. Expert echocardiologists reviewed and finalized all reports. The primary endpoint was examination efficiency, measured by examination time per patient and the number of examinations performed per day. Secondary endpoints included sonographer fatigue, the number of analyzed echocardiographic parameters, and image quality. Results A total of 585 patients were scanned over 38 study days (AI days: 317; non-AI days: 268) between Jan 30 and Mar 26, 2024. Baseline characteristics were comparable between groups. AI assistance significantly reduced examination time (13.0 ± 3.5 minutes vs. 14.3 ± 4.2 minutes, p<0.001) and increased the average number of daily examinations (16.7 ± 2.5 vs. 14.1 ± 2.5, p=0.003). Despite the higher workload, sonographers reported lower mental fatigue scores on AI days (4.1 ± 1.1 vs. 4.7 ± 0.6, p=0.039). The number of echocardiographic parameters analyzed per examination increased 3.4-fold on AI days (85 ± 12 vs. 25 ± 1, p<0.001). Differences between AI-generated measurements and final expert-endorsed values were within acceptable clinical limits for 90% of parameters. Notably, image quality significantly improved on AI days (p<0.001). Conclusions This real-world randomized trial demonstrated that AI-based echocardiographic analysis can enhance workflow efficiency, reduce sonographer fatigue, and improve image quality without compromising diagnostic integrity. Integrating AI into clinical practice holds promise for optimizing high-volume echocardiography workflows. Highlights Artificial intelligence (AI)-assisted echocardiography improved sonographer workflow efficiency. AI assistance significantly reduced examination time and increased daily scan volume. Sonographer mental fatigue was lower despite the increased workload on AI days. AI integration markedly increased the number of analyzed echocardiographic parameters. AI-enhanced workflow improved echocardiographic image quality without compromising accuracy. Graphical abstract This first-ever trial to randomize the use of an AI-based automated tool on a daily basis revealed that AI significantly enhanced the efficiency of screening echocardiography, reducing examination time despite a 3.4-fold increase in the number of parameters measured. This improved efficiency increased the number of examinations per day without increasing sonographers’ fatigue; in fact, it mitigated mental fatigue. Furthermore, being freed from the need to perform time-consuming measurements allowed sonographers to focus on image acquisition, which led to improved image quality.

Ähnliche Arbeiten