Echocardiography plays a crucial role in the diagnosis and management of cardiovascular disease. However, interpretation remains largely reliant on the subjective expertise of the operator. As a result inter-operator variability and experience can lead to incorrect diagnoses. Artificial intelligence (AI) technologies provide new possibilities for echocardiography to generate accurate, consistent and automated interpretation of echocardiograms, thus potentially reducing the risk of human error. In this review, we discuss a subfield of AI relevant to image interpretation, called machine learning, and its potential to enhance the diagnostic performance of echocardiography. We discuss recent applications of these methods and future directions for AI-assisted interpretation of echocardiograms. The research suggests it is feasible to apply machine learning models to provide rapid, highly accurate and consistent assessment of echocardiograms, comparable to clinicians. These algorithms are capable of accurately quantifying a wide range of features, such as the severity of valvular heart disease or the ischaemic burden in patients with coronary artery disease. However, the applications and their use are still in their infancy within the field of echocardiography. Research to refine methods and validate their use for automation, quantification and diagnosis are in progress. Widespread adoption of robust AI tools in clinical echocardiography practice should follow and have the potential to deliver significant benefits for patient outcome.

No abstract

Aims Heart failure (HF) with mid-range ejection fraction (HFmrEF) shares similar diagnostic criteria to HF with preserved ejection fraction (HFpEF). Whether left atrial (LA) function differs between HFmrEF and HFpEF is unknown. We, therefore, used 2D-speckle-tracking echocardiography (2D-STE) to assess LA phasic function in patients with HFpEF and HFmrEF. Methods and results Consecutive outpatients diagnosed with HF according to current European recommendations were prospectively enrolled. There were 110 HFpEF and 61 HFmrEF patients with sinus rhythm, and 37 controls matched by age. LA phasic function was analysed using 2D-STE. Peak-atrial longitudinal strain (PALS), peak-atrial contraction strain (PACS), and PALS−PACS were measured reflecting LA reservoir, pump, and conduit function, respectively. Among HF groups, most of left ventricular (LV) diastolic function measures, and LA volume were similar. Both HF groups had abnormal LA phasic function compared with controls. HFmrEF patients had worse LA phasic function than HFpEF patients even among patients with LA enlargement. Among patients with normal LA size, LA reservoir, and pump function remained worse in HFmrEF. Differences in LA phasic function between HF groups remained significant after adjustment for confounders. Global PALS and PACS were inversely correlated with brain natriuretic peptide, LA volume, E/A, E/e′, pulmonary artery systolic pressure, and diastolic dysfunction grade in both HF groups. Conclusion LA phasic function was worse in HFmrEF patients compared with those with HFpEF regardless of LA size, and independent of potential confounders. These differences could be attributed to intrinsic LA myocardial dysfunction perhaps in relation to altered LV function.

No abstract