Table 2 Performance of EXAM on independent datasets. Top, breakdown of patients by level of oxygen required across independent datasets from CDH, MVH and NCH. Bottom, AUC for prediction of the level of oxygen required at 24 and 72 h for the three independent datasets (95% confidence intervals)

From: Federated learning for predicting clinical outcomes in patients with COVID-19

Site

Cases (n)

Positive cases (n)

Prediction interval (h)

Patients at each level of oxygen requirement (n)

RA

LFO

HFO-NV

MV and death

CDH

840

244

24

608

162

48

22

72

575

173

62

30

MVH

399

30

24

356

36

3

4

72

351

39

3

6

NCH

264

29

24

237

23

4

0

72

235

22

4

3

Site

Prediction interval (h)

≥LFO

≥HFO-NV

≥MV

Average AUC

CDH

24

0.925 (0.903, 0.945)

0.950 (0.926, 0.971)

0.956 (0.918, 0.984)

0.944

72

0.902 (0.881, 0.924)

0.931 (0.905, 0.955)

0.938 (0.893, 0.927)

0.924

MVH

24

0.904 (0.844, 0.954)

0.836 (0.620, 0.978)

0.964 (0.925, 1.000)

0.901

72

0.887 (0.827, 0.940)

0.872 (0.663, 0.992)

0.988 (0.973, 0.997)

0.916

NCH

24

0.895 (0.833, 0.950)

0.984 (0.957, 1.000)

N/A

N/A

72

0.904 (0.850, 0.949)

0.947 (0.890, 0.991)

0.931 (0.897, 0.959)

0.927

  1. The AUC for the NCH dataset for MV at 24 h could not be calculated because there were no mechanically ventilated patients. Cases, number of patients included in the dataset; positive cases, number of patients with confirmed COVID-19 infection included in the dataset; N/A, not available.