Skip to main content
. 2021 Oct 4;23(10):e30697. doi: 10.2196/30697

Table 1.

Comparison of patient characteristics of available demographic and clinical variables: original vs synthetic data.


Original data (n=230,703) Synthetic data (n=230,650)
Age (years), mean (SD) 41.6 (20.4) 41.6 (20.4)
Gender (male), n (%) 108,194 (46.9) 107,892 (46.8)
Race, n (%)

White 121,706 (52.8) 121,564 (52.7)

Black 40,930 (17.7) 40,824 (17.7)

Asian 5203 (2.3) 5117 (2.2)

Other/unknown 62,864 (27.2) 62,733 (27.2)
Top 5 most prevalent states, n (%)

1 29,875 (12.9) 28,617 (12.4)

2 21,191 (9.2) 20,671 (9.0)

3 21,045 (9.1) 20,319 (9.0)

4 18,006 (7.8) 16,998 (7.4)

5 14,391 (6.2) 13,840 (6.0)
Top 5 most prevalent institutions, n (%)

1 33,413 (14.5) 32,743 (14.2)

2 24,533 (10.6) 23,986 (10.4)

3 15,578 (6.8) 15,065 (6.5)

4 11,870 (5.1) 11,255 (4.9)

5 11,354 (4.9) 10,850 (4.7)
Household income (US $), median (IQR) 56,738 (45,214, 71,250) 56,662 (45,223, 71,029)
BMI, mean (SD) 30.3 (8.4) 30.3 (8.2)
Admission start date (days from reference), mean (SD) 2.1 (3.3) 2.0 (3.2)
Minimum oxygen saturation, mean (SD) 90.9 (10.1) 91.0 (9.7)
Diabetes, n (%) 31,942 (13.8) 31,929 (13.8)
Dyspnea, n (%) 20,867 (9.0) 20,826 (9.0)
Chronic kidney disease, n (%) 11,225 (4.9) 11,194 (4.9)
Fever, n (%) 30,210 (13.1) 30,200 (13.1)
Cough, n (%) 39,703 (17.2) 39,689 (17.2)
Deceased, n (%) 1133 (0.5) 1008 (0.4)