Table 1 Performance on all test sites.

From: Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT

Test site ID

Institution

Train/Val. sites

Normals AUC

COVID− PNA AUC

COVID+ AUC

Accuracy

0

China-1

1,..,11

0.948

0.741

0.858

0.707

1

China-2

0,2,...,11

0.988

0.80

0.908

0.789

2

Kyungpook

0,1,3,..,11

N/A

N/A

N/A

0.921

3

Stanford

0,..,2,4,..,11

0.952

0.831

0.93

0.804

4

Unity Health

0,..,3,5,..,11

0.98

0.829

0.914

0.775

5

Koç

0,..,4,6,..,11

0.948

0.776

0.909

0.779

6

Rajaie

0,..,5,7,..,11

0.984

0.811

0.858

0.767

7

Einstein

0,..,6,8,..,11

N/A

N/A

N/A

0.915

8

UNIFESP

0,..,7,9,..,11

0.987

0.895

0.916

0.828

9

Henry Ford

0,..,8,10,..,11

0.986

0.830

0.889

0.76

10

TUMS-1

0,..,9,11

0.978

N/A

0.933

0.881

11

MosMedData

0,..,10

0.806

N/A

0.808

0.747

12

GUMS

0,..,11

N/A

N/A

N/A

0.944

13

TUMS-2

0,..,11

N/A

N/A

N/A

0.974

  1. Entries with N/A are due to class imbalance.
Back to article page