Artificial Intelligence in Echocardiography and Point-of-Care Ultrasound: Applications, Clinical Integration, and Future Directions

Résumé fourni par la source

Artificial intelligence (AI) is increasingly used in echocardiography and point-of-care ultrasound (POCUS) to support image acquisition, view recognition, image-quality assessment, segmentation, automated quantification, disease classification, reporting, and bedside decision support. This narrative review summarizes clinically relevant applications, with emphasis on clinical integration, pediatric and congenital heart disease considerations, and safe implementation. The strongest clinical evidence supports automated left ventricular segmentation and ejection fraction estimation, AI-guided acquisition, and workflow efficiency. Video-based deep learning has enabled beat-to-beat assessment of ventricular function, and a randomized workflow trial showed that AI-generated initial ejection fraction assessment was noninferior to sonographer assessment and required fewer cardiologist corrections. Regulatory-authorized acquisition and analysis tools demonstrate growing clinical adoption for specified adult indications. Recent multiview and disease-phenotyping models extend AI toward more comprehensive interpretation, while AI-enabled POCUS may improve focused image acquisition by non-expert users. However, external validation, pediatric and congenital heart disease data, cross-device generalizability, clinical outcome evidence, uncertainty communication, automation bias, and medicolegal responsibility remain important limitations. AI should currently be viewed as an augmentative rather than autonomous technology. The safest near-term model is human-AI collaboration, in which validated tools improve acquisition, reproducibility, and workflow while clinicians retain responsibility for interpretation and patient-centered decisions. Pediatric and congenital heart disease applications require age- and anatomy-specific datasets, multicenter validation, local performance monitoring, and clinician-supervised deployment. AI can assist across the echocardiography workflow, from acquisition guidance and view recognition to segmentation, quantification, disease screening, and structured reporting. The most mature clinical evidence supports left ventricular segmentation, ejection fraction estimation, AI-guided acquisition, and workflow efficiency rather than autonomous diagnosis. AI-enabled POCUS may improve acquisition by non-expert users, but image adequacy, interpretation, and clinical integration must remain clinician-supervised. Pediatric and congenital heart disease applications are promising but remain less mature than adult applications and require anatomy-specific datasets and multicenter validation. Safe implementation requires external validation, local monitoring, bias assessment, uncertainty display, audit trails, and institutional governance.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.