Table 1 Baseline characteristics of the patients enrolled in the analysis.

From: Artificial intelligence-based radiographic extent analysis to predict tuberculosis treatment outcomes: a multicenter cohort study

Variable

Total

N = 230

Treatment success

n = 206

Unfavorable outcome

n = 24

P

Age (years)

61.0 (51.0–76. 0)

59. 0 (50.0–75.0)

75.0 (63.5–81.0)

0.002

Male sex

175 (76.1)

153 (74.3)

22 (91. 7)

0.059

BMI (kg/m2)*

21.5 (18.8–23.8)

21.8 (19.3–23.8)

17.9 (16.4–22.0)

0.002

Ever smoker

130 (56.5)

115 (55.8)

15 (62.5)

0.532

Drinking history

   

0.656

 Social drinker

105 (45.9)

94 (45.9)

11 (45.8)

 

 Binge drinker

26 (11.4)

22 (10.7)

4 (16.7)

 

 Unknown

98 (42.8)

89 (43.4)

9 (37.5)

 

History of tuberculosis

63 (27.4)

54 (26.2)

9 (37.5)

0.241

Comorbidities

 Hypertension

74 (32.2)

65 (31.6)

9 (37.5)

0.555

 Diabetes mellitus

64 (27.8)

58 (28.2)

6 (25.0)

0.744

 Solid organ malignancy within 5 years

32 (13.9)

26 (12.6)

6 (25.0)

0.097

 COPD

15 (6.5)

14 (6.8)

1 (4.2)

> 0.999

 Asthma

11 (4.8)

11 (5.3)

0 (0.0)

0.611

 Solid organ transplant

6 (2.6)

5 (2.4)

1 (4.2)

0.488

 Immune suppressants

4 (1.7)

3 (1.5)

1 (4.2)

0.358

 Hematologic malignancy within 5 years

4 (1.7)

2 (1.0)

2 (8.3)

0.055

  1. *A total of 211 patients were included in the analysis of BMI, including 187 for treatment success assessment and 24 for unfavorable outcome assessment. P-values were calculated using the independent-samples t-test, Wilcoxon rank-sum test, the chi square test, or Fisher’s exact test, as appropriate. Numbers are presented as count (percentage) or median (interquartile range). BMI, body mass index; COPD, chronic obstructive pulmonary disease.
Back to article page