Skip to main content
. 2022 Nov 24;4(3):158–168. doi: 10.1016/j.hroo.2022.11.004

Figure 3.

Figure 3

Receiver-operating characteristic (ROC) curves for identifying oral anticoagulation (OAC) prescription: machine learning (ML) vs CHA2DS2-VASc (congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, prior stroke or transient ischemic attack or thromboembolism, vascular disease, age 65–74 years, sex category) score. ROC curves for (1) the CHA2DS2-VASc score, (2) 4 ML models (XGBoost, random forest, logistic regression, LASSO regression) using only covariates considered in the CHA2DS2-VASc score, and (3) 4 “enhanced” ML models that were trained on additional clinical comorbidities, medication usage, vital signs, laboratory data, insurance information, and socio- and geodemographic variables. Metrics were calculated on held-out test data. AUROC = area under the receiver operating characteristic curve; CI = confidence interval.