Aims: Studies have demonstrated the ability of a new automated algorithm for volumetric analysis of 3D echocardiographic (3DE) datasets to provide accurate and reproducible measurements of left ventricular and left atrial (LV, LA) volumes at end-systole and end-diastole. Recently, this methodology was expanded using a machine learning (ML) approach to automatically measure chamber volumes throughout the cardiac cycle, resulting in LV and LA volume–time curves. We aimed to validate ejection and filling parameters obtained from these curves by comparing them to independent well-validated reference techniques. Methods and results: We studied 20 patients referred for cardiac magnetic resonance (CMR) examinations, who underwent 3DE imaging the same day. Volume–time curves were obtained for both LV and LA chambers using the ML algorithm (Philips HeartModel), and independently conventional 3DE volumetric analysis (TomTec), and CMR images (slice-by-slice, frame-by-frame manual tracing). Automatically derived LV and LA volumes and ejection/filling parameters were compared against both reference techniques. Minor manual correction of the automatically detected LV and LA borders was needed in 4/20 and 5/20 cases, respectively. Time required to generate volume–time curves was 35 ± 17 s using ML algorithm, 3.6 ± 0.9 min using conventional 3DE analysis, and 96 ± 14 min using CMR. Volume–time curves obtained by all three techniques were similar in shape and magnitude. In both comparisons, ejection/filling parameters showed no significant inter-technique differences. Bland–Altman analysis confirmed small biases, despite wide limits of agreement. Conclusion: The automated ML algorithm can quickly measure dynamic LV and LA volumes and accurately analyse ejection/filling parameters. Incorporation of this algorithm into the clinical workflow may increase the utilization of 3DE imaging.

Recent studies suggested that even non-obstructive coronary artery disease (CAD) increases major cardiovascular adverse events (MACE) rate. Aim of this study was to evaluate whether coronary computed tomography angiography (CCTA) may detect specific plaque characteristics that may affect prognosis in patients with non-obstructive CAD. We enrolled 245 patients who underwent CCTA between April 2004 and April 2007 for suspected CAD and were found to have non-obstructive CAD. Positive remodelling index (PRI), low-attenuation plaque (LAP), plaque burden (PB), spotty calcification (SC), and napkin-ring sign (NRS) have been evaluated for each coronary plaque detected. Acute coronary syndrome, all-cause/cardiac death, and very late elective revascularization (vl-ER) were the endpoints of the study. A total of 28 events were recorded (2 STEMI, 4 NSTEMI, 6 UA, 2 cardiac deaths, 4 non-cardiac death, and 10 vl-ERs) at long-term follow-up (98 ± 20 months). When adjusted for significant clinical variables PRI > 1.4 (HR 3.31 CI 95% 1.11–9.91, P = 0.0392), LAP (HR 8.45 CI 95% 2.22–32.21, P = 0.0019), PB > 0.7 (HR 5.25 CI 95% 1.45–19.03, P = 0.0120), and NRS (HR 12.52 CI 95% 1.51–103.90, P = 0.0198) were still significantly associated with higher rate of hard cardiac events at follow-up. The Kaplan–Meyer curves confirmed lower cumulative hard cardiac events-free survival in patients presenting at least one coronary plaque with two or more high-risk characteristics when compared with patients with no lesion with more than one high-risk plaque characteristics (log-rank P < 0.0001). High-risk plaque characteristics at CCTA (PRI > 1.4, PB > 0.7, LAP, and NRS) seem to be promising for risk stratification of patients with non-obstructive CAD.