Skip to main content
. 2021 Dec 1;42(5):746–756. doi: 10.1177/0271678X211063802

Table 3.

Scores for each model on validation cohort.

Model Sensitivity, % Specificity, % Accuracy, % F-1 score The Matthews correlation coefficient AUROC AUPRC
ML model 74 (59–87) 54 (48–59) 55 (50–60) 0.18 (0.13–0.23) 0.14 (0.06–0.20) 0.72 (0.66–0.79) 0.15 (0.09–0.23)
CHADS2 score 52 (50–77) 52 (48–56) 53 (49–56) 0.15 (0.11–0.20) 0.08 (0.01–0.15) 0.61 (0.52–0.69) 0.10 (0.07–0.15)
CHA2DS2-VASc score 74 (61–86) 40 (37–44) 43 (39–46) 0.15 (0.10–0.19) 0.07 (0.01–0.14) 0.62 (0.54–0.70) 0.11 (0.07–0.16)

AUROC: area under the receiver operating curve; AUPRC: area under the precision-recall curve.