Skip to main content
. 2023 Oct 18;34(8):533–541. doi: 10.1097/MCA.0000000000001305

Table 2.

Diagnostic performance of AI-FFR vs. invasive FFR

AI-FFR performance in the overall population
N = 304 (vessels)
AI-FFR performance around the cutoff (0.75–0.85)
N = 105 (vessels)
Accuracy 93.7% 94.3%
AUC 0.93 (0.88–0.97) 0.94 (0.88–0.98)
Sensitivity 91.3% (82.0–97.0) 95.1% (83.0–99.5%)
Specificity 94.5% (91.0–97.0) 93.8% (84.6–98.0%)
Positive predictive value 82.9 (72.5–90.6) 90.7 (77.8–96.9)
Negative predictive value 97.4 (94.4–99.0) 96.8 (88.3–99.8)

Data between brackets is 95% confidence intervals.

AUC, area under the curve.