Echocardiography is a foundational imaging modality for assessing cardiac structure and function, with a long history of technological advancement. As artificial intelligence (AI) becomes increasingly embedded across healthcare, its potential to enhance the echocardiography workflow, from image acquisition and analysis to reporting and risk stratification, has expanded rapidly. Research activity in this field has grown substantially, yet clinical adoption remains variable and often limited by practical, technical, and governance challenges. In response, the British Society of Echocardiography has developed this position statement to provide a structured, consensus‑driven evaluation of the opportunities, limitations, and requirements for the safe, equitable, and effective integration of AI into echocardiography services. Although centred on the UK context, the principles outlined may be relevant to other healthcare systems with similar models of echocardiography delivery.
S. Bennett, C. Wild, Maria F Paton et al.· Echo Research and Practice· 0 citations
In severe rheumatic mitral stenosis with sinus rhythm, left atrial appendage (LAA) dysfunction increases thromboembolic risk, yet clinical guidelines provide no recommendations, and its assessment via transesophageal echocardiography is not feasible for routine or repeated use. This study assessed whether left atrial (LA) strain imaging could noninvasively predict LAA contractile dysfunction.
We prospectively enrolled 138 patients with severe rheumatic MS in sinus rhythm who underwent transthoracic and transesophageal echocardiography. LAA inactivity was defined as LAA emptying velocity <25 cm/s. LA reservoir (LASr), conduit, and contractile strain were quantified using speckle-tracking echocardiography. Multivariable logistic regression and receiver-operating characteristic (ROC) analyses were performed to evaluate predictors of LAA inactivity. LAA inactivity was observed in 108 patients (78.2%), and LAA thrombus was detected in 8 patients (5.8%)—all in sinus rhythm. In multivariate analysis, LASr was the strongest independent predictor of LAA inactivity (OR 0.61 per 1% increase; 95% CI: 0.50–0.75; p < 0.0001). LASr yielded an AUC of 0.950 (95% CI: 0.911-0.989), with a threshold of ≤22.95% showing a sensitivity of 93.5%, and specificity of 90% for predicting LAA inactivity. Impaired LA strain identified patients with elevated fibrinogen, D-dimer, and the presence of LAA thrombus.
LA strain imaging provides a robust noninvasive predictor of LAA dysfunction in severe rheumatic MS patients in sinus rhythm. These findings support the potential clinical utility of LA strain in improving risk stratification and guiding anticoagulation decisions in this under-recognized high-risk population.
J. Yusuf, Gaurav Sharma, Ankit Bansal et al.· European Heart Journal Open· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
