Using a classification and regression tree (CART) analysis, researchers from Johns Hopkins University School of Medicine and Providence Research Network have developed a streamlined risk stratification process among patients with atherosclerotic cardiovascular disease (ASCVD). The study findings were published in the American Journal of Preventive Cardiology.
In the current study, researchers retrospectively analyzed electronic health records (EHR) from 28 hospitals in the western United States. Adults with clinical ASCVD and at least 1 lipid panel analysis indicating triglycerides less than 400 mg/dL were included. Very high-risk (VHR) status was defined as 2 or more major ASCVD events or 1 major event with 2 or more high-risk conditions. Data were separated into training and validation sets for the CART analysis to determine the features that best distinguished patients with ASCVD with VHR from those with non-VHR (NVHR).
The VHR and NVHR cohorts included participants with a mean age of 73.1±11.9 years and 70.1±13.4 years; 55% and 54% were men; and 91% and 93% were White, respectively.
The VHR cohort had increased rates of recent acute coronary syndrome (ACS; 47% vs 2%), history of myocardial infarction (MI; 38% vs 0.3%), ischemic stroke (42% vs 7%), symptomatic peripheral artery disease (PAD; 27% vs 3%), hypertension (88% vs 70%), congestive heart failure (29% vs 17%), chronic kidney disease (39% vs 27%), and diabetes mellitus (39% vs 27%, respectively).
The CART analysis identified recent ACS, ischemic stroke, hypertension, PAD, history of MI, and age as the most important predictors of VHR status.
On the basis of these predictors, the model indicated that 96% of patients with recent ACS were VHR, 96% of patients with ischemic stroke and hypertension were VHR, 92% of patients with only a history of MI were VHR, 90% of patients with only symptomatic PAD were VHR, and patients with ischemic stroke and aged 65 years and older were VHR.
These findings were based on a patient population dominated by White men and may not be generalizable to a more diverse population.
“More than half of adults with ASCVD in our study met the definition of VHR, which is consistent with previous reports. In an attempt to simplify assignment of VHR status, however, we showed that use of [5] rules identified in our CART analysis could appreciably reduce the number of risk factors that need to be considered,” the study authors noted. “Such an approach is appealing, in part, because EHR-based tools are either not widely available or under-utilized. By considering a more limited number of risk factors, clinicians may be able to better employ the mental heuristics used to quickly tabulate VHR vs NHVR status. Such an approach simplifies ASCVD risk assessment and may help to streamline decision making at the point of care.”
Disclosure: One study author declared affiliations with biotech, pharmaceutical, and/or device companies. Please see the original reference for a full list of disclosures.
Reference
Sajja A, Li H-F, Spinelli KJ, et al. A simplified approach to identification of risk status in patients with atherosclerotic cardiovascular disease. Am J Prev Cardiol. 2021;7:100187. doi:10.1016/j.ajpc.2021.100187