Non-hyperaemic assessment of coronary ischaemia: application of machine learning techniques.

Aims: Hyperaemic and non-hyperaemic pressure ratios (NHPR) are routinely used to identify significant coronary lesions. Machine learning (ML) techniques may help better understand these indices and guide future practice. This study assessed the ability of a purpose-built ML algorithm to classify coronary ischaemia during non-hyperaemia compared with the existing gold-standard technique (fractional flow reserve, FFR). Further, it investigated whether ML could identify components of coronary and aortic pressure cycles indicative of ischaemia. Methods and results: Seventy-seven coronary vessel lesions (39 FFR defined ischaemia, 53 patients) with proximal and distal non-hyperaemic pressure waveforms and FFR values were assessed using supervised and unsupervised learning techniques in combination with principal component analysis (PCA). Fractional flow reserve measurements were obtained from the right coronary artery (13), left anterior descending (46), left circumflex (11), left main (1), obtuse marginal (2), and diagonal (4). The most accurate supervised learning classification utilized whole-cycle aortic with diastolic distal blood pressure waveforms, yielding a classification accuracy of 86.9% (sensitivity 86.8%, specificity 87.2%, positive predictive value 86.8%, negative predictive value 87.2%). Principal component analysis showed subtle variations in coronary pressures at the start of diastole have significant relation to ischaemia, and whole-cycle aortic pressure data are important for determining ischaemia. Conclusions: Our ML algorithm classifies significant coronary lesions with accuracy similar to previous studies comparing time-domain NHPRs with FFR. Further, it has identified characteristics of pressure waveforms that relate to function. These results provide an application of ML to ischaemia requiring only standard data from non-hyperaemic pressure measurements.

Exploring the relationship between biomechanical stresses and coronary atherosclerosis.

The pathophysiology of coronary atherosclerosis is multifaceted. Plaque initiation and progression are governed by a complex interplay between genetic and environmental factors acting through processes such as lipid accumulation, altered haemodynamics and inflammation. There is increasing recognition that biomechanical stresses play an important role in atherogenesis, and integration of these metrics with clinical imaging has potential to significantly improve cardiovascular risk prediction. In this review, we present the calculation of coronary biomechanical stresses from first principles and computational methods, including endothelial shear stress (ESS), plaque structural stress (PSS) and axial plaque stress (APS). We discuss the current experimental and human data linking these stresses to the natural history of coronary artery disease and explore the future potential for refining treatment options and predicting future ischaemic events.

Acute Effects of Transcatheter Aortic Valve Replacement on Central Aortic Hemodynamics in Patients With Severe Aortic Stenosis.

Severe aortic stenosis induces abnormalities in central aortic pressure, with consequent impaired organ and tissue perfusion. Relief of aortic stenosis by transcatheter aortic valve replacement (TAVR) is associated with both a short- and long-term hypertensive response. Counterintuitively, patients who are long-term normotensive post-TAVR have a worsened prognosis compared with patients with hypertension, yet the underlying mechanisms are not understood. We investigated immediate changes in invasively measured left ventricular and central aortic pressure post-TAVR in patients with severe aortic stenosis using aortic reservoir pressure, wave intensity analysis, and indices of aortic function. Fifty-four patients (mean age 83.6±6.2 years, 50.0% female) undergoing TAVR were included. We performed reservoir pressure and wave intensity analysis on invasively acquired pressure waveforms from the ascending aorta and left ventricle immediately pre- and post-TAVR. Following TAVR, there were increases in systolic, diastolic, mean, and pulse aortic pressures (all P<0.05). Post-TAVR reservoir pressure was unchanged (54.5±12.4 versus 56.6±14.0 mm Hg, P=0.30) whereas excess pressure increased 47% (29.0±10.9 versus 42.6±15.5 mm Hg, P<0.001). Wave intensity analysis (arbitrary units, au) demonstrated increased forward compression wave (64.9±35.5 versus 124.4±58.9, ×103 au, P<0.001), backward compression wave (11.6±5.5 versus 14.4±6.9, ×103 au, P=0.01) and forward expansion wave energies (43.2±27.3 versus 82.8±53.1, ×103 au, P<0.001). Subendocardial viability ratio improved with aortic function effectively unchanged post-TAVR. Increased central aortic pressure following TAVR relates to increased transmitted power and energy to the proximal aorta with increased excess pressure but unchanged reservoir pressure. These changes provide a potential mechanism for the improved prognosis associated with relative hypertension post-TAVR.

Periprocedural Myocardial Injury Predicts Short- and Long-Term Mortality in Patients Undergoing Transcatheter Aortic Valve Replacement.

BACKGROUND: The aim was to assess whether periprocedural myocardial injury (PPMI) predicts outcomes in patients undergoing transcatheter aortic valve replacement (TAVR). PPMI is a strong predictor of outcomes following coronary intervention, but its impact in the context of TAVR remains unclear. We performed a systematic review and meta-analysis to ascertain the association between PPMI and short- or long-term outcomes. METHODS AND RESULTS: Electronic searches identified studies reporting PPMI following TAVR. Primary end point was 30-day all-cause mortality, with secondary end points, including 1-year all-cause mortality, neurological events, post-TAVR pacemaker implantation, and aortic regurgitation. Analyses were performed using random effects modeling and reported as summary odds ratio (OR) with 95% CI. Nine studies comprising 3442 patients (mean age 81.0±6.6 years, 51.2% female) were included. PPMI occurred in 25.5% of patients following TAVR. The pooled all-cause mortality at 30-days and 1-year was 5.2% and 18.6%, respectively. The occurrence of PPMI following TAVR was associated with significantly increased risk of both 30-day (OR, 4.23; CI, 1.95-9.19; P<0.001) and 1-year all-cause mortality (OR, 1.77; CI, 1.05-2.99; P<0.001). Similarly, PPMI was associated with post-TAVR neurological events (OR, 2.72; CI, 1.69-4.37; P<0.001) and post-TAVR permanent pacing (OR, 1.43; CI, 1.02-2.00; P=0.04) but not with a statistically significant increase in aortic regurgitation post-TAVR (OR, 1.39; CI, 0.93-2.08; P=0.11). CONCLUSIONS: PPMI is common following TAVR and is strongly associated with 30-day and 1-year mortality. Detection of PPMI has potential to identify TAVR patients at highest risk of subsequent adverse events.