Figure 5. Performance of Question 2 Models in Postchallenge Analysis.

A, Performance of question 2 models for 21-day hospitalization prediction trained on all patients tested for COVID-19 vs only patients tested for COVID-19 in outpatient settings. B, Performance of question 2 models when trained on different lengths of electronic health record (EHR) history prior to the COVID-19 test. From left to right, the box indicates the 25th to 75th percentile; the error bars indicate the minimum and maximum, respectively, excluding the outliers; the diamonds indicate outliers; and the vertical line in each box is the median value. AUROC indicates area under the receiver operating characteristic curve.