Noninvasive assessment of left ventricular end-diastolic pressure using machine learning-derived phasic left atrial strain

The Clinical Applications of Left Atrial Strain: A Comprehensive Review

Left atrial (LA) strain imaging, which measures the deformation of the LA using speckle-tracing echocardiography (STE), has emerged recently as an exciting tool to help provide diagnostic and prognostic information for patients with a broad range of cardiovascular (CV) pathologies. Perhaps due to the LA's relatively thin-walled architecture compared with the more muscular structure of the left ventricle (LV), functional changes in the left atrium often precede changes in the LV, making LA strain (LAS) an earlier marker for underlying pathology than many conventional echocardiographic parameters. LAS imaging is typically divided into three phases according to the stage of the cardiac cycle: reservoir strain, which is characterized by LA filling during systole; conduit strain, which describes LA deformation during passive LV filling; and booster strain, which provides information on the LA atrium during LA systole in late ventricular diastole. While additional large-population studies are still needed to further solidify the role of LAS in routine clinical practice, this review will discuss the current evidence of its use in different pathologies and explore the possibilities of its applications in the future.

Artificial intelligence-enabled ECG for left ventricular diastolic function and filling pressure

Assessment of left ventricular diastolic function plays a major role in the diagnosis and prognosis of cardiac diseases, including heart failure with preserved ejection fraction. We aimed to develop an artificial intelligence (AI)-enabled electrocardiogram (ECG) model to identify echocardiographically determined diastolic dysfunction and increased filling pressure. We trained, validated, and tested an AI-enabled ECG in 98,736, 21,963, and 98,763 patients, respectively, who had an ECG and echocardiographic diastolic function assessment within 14 days with no exclusion criteria. It was also tested in 55,248 patients with indeterminate diastolic function by echocardiography. The model was evaluated using the area under the curve (AUC) of the receiver operating characteristic curve, and its prognostic performance was compared to echocardiography. The AUC for detecting increased filling pressure was 0.911. The AUCs to identify diastolic dysfunction grades ≥1, ≥2, and 3 were 0.847, 0.911, and 0.943, respectively. During a median follow-up of 5.9 years, 20,223 (20.5%) died. Patients with increased filling pressure predicted by AI-ECG had higher mortality than those with normal filling pressure, after adjusting for age, sex, and comorbidities in the test group (hazard ratio (HR) 1.7, 95% CI 1.645-1.757) similar to echocardiography and in the indeterminate group (HR 1.34, 95% CI 1.298-1.383). An AI-enabled ECG identifies increased filling pressure and diastolic function grades with a good prognostic value similar to echocardiography. AI-ECG is a simple and promising tool to enhance the detection of diseases associated with diastolic dysfunction and increased diastolic filling pressure.