In symptomatic patients with suspected coronary artery disease (CAD), computed tomographic angiography (CTA) improves patient selection for invasive coronary angiography (ICA) compared with functional testing. The impact of measuring fractional flow reserve by CTA (FFR_CT) is unknown. At 11 sites, 584 patients with new onset chest pain were prospectively assigned to receive either usual testing (n = 287) or CTA/FFR_CT (n = 297). Test interpretation and care decisions were made by the clinical care team. The primary endpoint was the percentage of those with planned ICA in whom no significant obstructive CAD (no stenosis ≥50% by core laboratory quantitative analysis or invasive FFR < 0.80) was found at ICA within 90 days. Secondary endpoints including death, myocardial infarction, and unplanned revascularization were independently and blindly adjudicated. Subjects averaged 61 ± 11 years of age, 40% were female, and the mean pre-test probability of obstructive CAD was 49 ± 17%. Among those with intended ICA (FFR_CT-guided = 193; usual care = 187), no obstructive CAD was found at ICA in 24 (12%) in the CTA/FFR_CT arm and 137 (73%) in the usual care arm (risk difference 61%, 95% confidence interval 53–69, P< 0.0001), with similar mean cumulative radiation exposure (9.9 vs. 9.4 mSv, P = 0.20). Invasive coronary angiography was cancelled in 61% after receiving CTA/FFR_CT results. Among those with intended non-invasive testing, the rates of finding no obstructive CAD at ICA were 13% (CTA/FFR_CT) and 6% (usual care; P = 0.95). Clinical event rates within 90 days were low in usual care and CTA/FFR_CT arms. Computed tomographic angiography/fractional flow reserve by CTA was a feasible and safe alternative to ICA and was associated with a significantly lower rate of invasive angiography showing no obstructive CAD.

Artificial intelligence (AI) has transformed key aspects of human life. Machine learning (ML), which is a subset of AI wherein machines autonomously acquire information by extracting patterns from large databases, has been increasingly used within the medical community, and specifically within the domain of cardiovascular diseases. In this review, we present a brief overview of ML methodologies that are used for the construction of inferential and predictive data-driven models. We highlight several domains of ML application such as echocardiography, electrocardiography, and recently developed non-invasive imaging modalities such as coronary artery calcium scoring and coronary computed tomography angiography. We conclude by reviewing the limitations associated with contemporary application of ML algorithms within the cardiovascular disease field.

Valvular regurgitation represents an important cause of cardiovascular morbidity and mortality. Imaging is pivotal in the evaluation of native valve regurgitation and echocardiography is the primary imaging modality for this purpose. The imaging assessment of valvular regurgitation should integrate quantification of the regurgitation, assessment of the valve anatomy and function, and the consequences of valvular disease on cardiac chambers. In clinical practice, the management of patients with valvular regurgitation largely relies on the results of imaging. It is crucial to provide standards that aim at establishing a baseline list of measurements to be performed when assessing native valve regurgitation. The present document aims to present clinical guidance for the multi-modality imaging assessment of native valvular regurgitation.