Table 1 Baseline characteristics stratified by the train or test cohort.

From: Feasibility of the deep learning method for estimating the ventilatory threshold with electrocardiography data

 

All patients (n = 260)

Train cohort (n = 169)

Test cohort (n = 91)

P value*

Age, years

58.9 ± 14.6

58.6 ± 14.5

59.4 ± 14.9

0.720

Male sex

190 (73.1%)

122 (72.2%)

68 (74.7%)

0.660

Height, cm

165.6 ± 8.6

165.4 ± 8.5

165.8 ± 8.7

0.552

Weight, kg

64.7 ± 13.8

64.2 ± 14.0

65.7 ± 12.8

0.289

BMI, kg/m2

23.5 ± 3.9

23.3 ± 3.9

23.8 ± 3.8

0.272

Hypertension

121 (46.5%)

78 (46.2%)

43 (47.3%)

0.865

Diabetes mellitus

47 (18.1%)

33 (19.5%)

14 (15.4%)

0.532

Dyslipidemia

105 (40.4%)

75 (44.4%)

30 (33.3%)

0.074

Chronic heart failure

121 (46.5%)

78 (46.2%)

43 (47.3%)

0.865

Coronary artery disease

100 (38.4%)

70 (41.4%)

30 (33.0%)

0.181

Pulmonary hypertension

41 (15.8%)

22 (13.0%)

19 (20.9%)

0.097

Arrhythmias

37 (14.2%)

14 (15.4%)

23 (13.6%)

0.696

Prescription of a β-blocker

177 (68.1%)

122 (72.2%)

55 (60.4%)

0.142

AF rhythm during CPX

25 (9.6%)

17 (8.8%)

8 (10.1%)

0.741

  1. Values are presented as a mean ± standard deviation or number (percentage).
  2. *Difference between the train cohort and the test cohort for each item.
  3. BMI body mass index, AF atrial fibrillation, CPX cardiopulmonary exercise testing.
Back to article page