Skip to main content
. 2024 Sep 26;10:e54421. doi: 10.2196/54421

Table 3.

Comparative performance metrics of predictive models by racea.

Models AUCb Balanced accuracy Sensitivity Specificity
Model 1, mean (SD)

All 0.80 (0.01) 0.73 (0.01) 0.75 (0.02) 0.71 (0.01)

Whites 0.80 (0.01) 0.72 (0.01) 0.74 (0.03) 0.71 (0.01)

Blacks 0.80 (0.01) 0.73 (0.01) 0.74 (0.01) 0.72 (0.01)
Model 2, mean (SD)

All 0.83 (0.01) 0.74 (0.01) 0.74 (0.02) 0.75 (0.01)

Whites 0.82 (0.01) 0.73 (0.01) 0.72 (0.03) 0.75 (0.01)

Blacks 0.82 (0.01) 0.74 (0.01) 0.74 (0.01) 0.74 (0.01)
Model 3, mean (SD)

All 0.84 (0.01) 0.77 (0.01) 0.81 (0.01) 0.72 (0)

Whites 0.84 (0.01) 0.76 (0.01) 0.81 (0.02) 0.72 (0.01)

Blacks 0.84 (0.01) 0.76 (0.01) 0.81 (0.01) 0.71 (0.01)

aThe table presents comparative performance metrics of predictive models by race, derived from a retrospective cohort study of COVID-19 patients within the OneFlorida Clinical Research Network. The data encompasses adult patients (≥18 years old) diagnosed with COVID-19 between December 1, 2019, and April 28, 2021.

bAUC: the area under the receiver operating characteristic curve.