Future Guidelines for Artificial Intelligence in Echocardiography

The application of artificial intelligence (AI) in echocardiography has shown tremendous growth in the past decade, with the exciting potential for standardization, reducing variability, automating measurements, and recognizing uncommon diseases. 1 Alsharqi M. Woodward W.J. Mumith J.A. Markham D.C. Upton R. Leeson P. Artificial intelligence and echocardiography. Echo Res Pract. 2018; 5: R115-R125 Crossref PubMed Scopus (81) Google Scholar With the advent of advanced techniques in machine learning, such as neural networks and the accessibility of large digital data sets from electronic health records, the breadth and pace with which these advancements are occurring are accelerating. This abundance of new studies varies in scope, aim, and generalizability. Standardized methods, such as the Consolidated Standards of Reporting Trials–Artificial Intelligence (CONSORT-AI) and Proposed Recommendations for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME) checklist, have been developed to evaluate AI studies in a systematic fashion. 2 Liu X. Cruz Rivera S. Moher D. Calvert M.J. Denniston A.K. Spirit A.I. et al. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat Med. 2020; 26: 1364-1374 Crossref PubMed Scopus (183) Google Scholar ,3 Sengupta P.P. Shrestha S. Berthon B. Messas E. Donal E. Tison G.H. et al. Proposed Requirements for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME): a checklist: reviewed by the American College of Cardiology Healthcare Innovation Council. JACC Cardiovasc Imaging. 2020; 13: 2017-2035 Crossref PubMed Scopus (54) Google Scholar Undoubtedly, as the field of AI matures within the practice of echocardiography, these new technologies will be incorporated into echocardiography guidelines. The potential application of AI in echocardiography is constantly expanding (Figure 1). In this editorial, we provide a fundamental conceptual framework to approach clinical guideline development in this growing field (Figure 2). Figure 2Schematic of the direction of AI in echocardiography guidelines. Guidelines developed for AI in echocardiography should address these key points to ensure safe, equitable, and reliable implementation of these new technologies in clinical practice. View Large Image Figure Viewer Download Hi-res image