Oracle of Our Time: Machine Learning for Predicting Cardiovascular Events.
Radiology. 2019 Jun 25:191165. doi: 10.1148/radiol.2019191165. [Epub ahead of print]
Schoepf UJ, Tesche C.
Coronary CT angiography is a reliable and clinically proven method for the evaluation of coronary artery disease. The anatomic, morphologic assessment of coronary stenosis allows for cardiovascular risk stratification and therapeutic decision making, in addition to providing prognostic value for the occurrence of adverse cardiac outcomes. Coronary CT angiography–derived risk scores have demonstrated superior prognostic value over clinically established cardiovascular risk scores, which are effective tools for population-based assessment but ineffective for individual risk stratification (1). Coronary CT angiography risk scores are mainly on the basis of classification of coronary artery disease severity by using the standard 16-segment coronary tree model. This classification includes presence, extent, location, and severity of coronary plaques in the computation of a single risk score that is typically incorporated into a multivariable prediction analysis (2). However, this approach does not consider potential unexpected interactions and dependencies between various predictor variables in an individual patient.
Read Full Article Here: https://doi.org/10.1148/radiol.2019191165