In this prospective multicenter trial of chest pain patients without known CAD, 64-multidetector row CCTA possesses high diagnostic accuracy for detection of obstructive coronary stenosis at both thresholds of 50% and 70% stenosis. Importantly, the 99% negative predictive value at the patient and vessel level establishes CCTA as an effective noninvasive alternative to ICA to rule out obstructive coronary artery stenosis. (A Study of Computed Tomography [CT] for Evaluation of Coronary Artery Blockages in Typical or Atypical Chest Pain; NCT00348569).

Coronary risk stratification using a risk factor only-based scheme is a weak discriminator of the overall atherosclerotic plaque burden in individual patients. Patients with little or no plaque might be subjected to lifelong drug therapy, whereas many others with substantial plaque might be undertreated or not treated at all.

The new American Heart Association/American College of Cardiology guideline matches statin assignment to total plaque burden better than the older guidelines, with only a modest increase in the number of patients who were assigned statins.

Rapid kilovolt peak-switching dual-energy CT resulted in significant BH reduction and improvements in SNR and CNR in the myocardium and coronary arteries.

C oronary CT angiography has proven prognostic value for cardiac events (1-6). It depicts vessel lumen and wall characteristics including stenoses, remodeling, plaque thickness, and degree of calcification (7). Imaging improves prognostic accuracy beyond that offered by traditional risk estimation methods, and data suggest that it might be useful for primary assessment of coronary risk under some circumstances (8-10). A practical problem has been how to score atherosclerotic features for use in prognosis estimation models. The most common approach is to divide the coronary tree into 16 segments and then score each segment according to certain simple criteria (11-13). For example, the segmental plaque score scores the amount of plaque from 0 to 3 for each segment and takes the sum. The Coronary Artery Disease Reporting and Data System (CAD-RADS), a standardized reporting system, was recently introduced for clinical use (14). These scoring systems are necessarily an abstraction from the underlying pathologic condition, and there is the chance of discarding useful information along the way. Machine learning can explore a large number of possible models and construct a good model without overlooking important input features or including unnecessary ones (15). In this study, patients were followed after coronary CT angiography for the occurrence of death and myocardial infarction. The hypothesis was that machine learning, compared with conventional scoring systems, could find a combination of arterial features that better discriminated patients who did not experience an adverse event from those who did. We analyzed data as summarized by the reading radiologists (ie, from human visual analysis, not