Skip to main content

Table 1 Demographic and clinical description of participants with AI abnormality scores among different groups

From: Comparing tuberculosis symptom screening to chest X-ray with artificial intelligence in an active case finding campaign in Northeast Nigeria

All participants

5297

n (%)

Median score (IQR)

Gender

 Male

2613 (49%)

0.037 (0.018–0.13)

 Female

2684 (51%)

0.042 (0.019–0.14)

Age, median (IQR)

37 (26–50)

 

 Male, median (IQR)

39 (26–53)

-

 Female, median (IQR)

36 (26–48)

-

 15–24

1054 (20%)

0.035 (0.018–0.086)

 25–50

2950 (56%)

0.039 (0.018–0.13)

  > 50

1293 (24%)

0.048 (0.020–0.196)

TB symptoms

 Any cough

1889 (36%)

0.05 (0.022–0.25)

 Cough ≥ 2 weeks

1056 (20%)

0.05 (0.022–0.265)

 Fever

425 (8%)

0.132 (0.028–0.51)

 Weight loss

1589 (30%)

0.048 (0.022–0.194)

 Night sweats

1403 (26%)

0.045 (0.021–0.178)

 Any TB symptoms

3083 (58%)

0.05 (0.021–0.21)

TB risk factors

 History of smoking

561 (11%)

0.052 (0.021–0.24)

 HIV positive (self-reported)

32 (0.6%)

0.134 (0.046–0.95)

Sputum collection

1021 (32% of 3205)

0.43 (0.24–0.74)

Any cough

639 (34% of 1889)

0.40 (0.096–0.68)

Cough ≥ 2 weeks

394 (37% of 1056)

0.36 (0.086–0.67)

Fever

212 (50% of 425)

0.49 (0.034–0.85)

Weight loss

515 (32% of 1589)

0.41 (0.013–0.71)

Night sweats

430 (31% of 1403)

0.38 (0.098–0.68)

Any TB symptoms

906 (29% of 3083)

0.43 (0.02–0.72)

History of smoking

174 (33% of 561)

0.44 (0.019–0.84)

AI score 30 and above

738 (96% of 769)

-

AI score 50 and above

424 (95% of 447)

-

AI score ≥ 30 AND any symptom

623 (96% of 647)

-

Xpert MTB/RIF results

 Test performed

1021 (19%)

 

 MTB detected

85 (8%)

0.91 (0.67–0.97)

 MTB not detected

936 (92%)

0.42 (0.21–0.65)

  1. IQR interquartile range, TB tuberculosis, HIV human immunodeficiency virus, AI artificial intelligence, MTB Mycobacterium tuberculosis, RIF rifampicin