Skip to main content

Table 1 Characteristics of the training and validation datasets

From: Development and validation of explainable machine-learning models for carotid atherosclerosis early screening

Characteristics

Overall, N = 6315

Training set, N = 3264

Internal validation set (#), N = 817

External validation set (#), N = 2234

CAS proportion

3153 (50%)

1632 (50%)

407 (50%)

1114 (50%)

Age (years)

48 (38, 56)

48 (37, 55)

48 (37, 56)

49 (40, 57)***

Sex (n,%)

    

 Female

4196 (66%)

2137 (65%)

550 (67%)

1509 (68%)

 Male

2119 (34%)

1127 (35%)

267 (33%)

725 (32%)

BMI (kg/m2)

25.4 (23.2, 27.7)

25.4 (23.1, 27.7)

25.6 (23.3, 27.7)

25.4 (23.3, 27.8)

Waist circumference (cm)

85 (79, 91)

85 (78, 91)

85 (78, 91)

85 (79, 91)*

Height (cm)

169 (162, 175)

169 (162, 175)

170 (163, 175)

169 (163, 174)

Body weight (kg)

73 (63, 82)

72 (63, 82)

73 (64, 82)

73 (63, 82)

SBP (mmHg)

126 (115, 140)

126 (115, 140)

126 (115, 141)

126 (115, 141)

DBP (mmHg)

76 (68, 85)

76 (68, 85)

76 (67, 84)

76 (68, 85)

FPG (mmol/L)

5.18 (4.85, 5.61)

5.17 (4.84, 5.61)

5.16 (4.84, 5.59)

5.19 (4.87, 5.61)

TG (mmol/L)

1.38 (0.93, 2.10)

1.37 (0.92, 2.06)

1.38 (0.91, 2.18)

1.39 (0.94, 2.12)

TC (mmol/L)

4.87 (4.32, 5.49)

4.90 (4.33, 5.51)

4.84 (4.27, 5.48)

4.84 (4.32, 5.48)

HDL-C (mmol/L)

1.20 (1.02, 1.44)

1.21 (1.03, 1.46)

1.21 (1.01, 1.46)

1.20 (1.01, 1.42)**

LDL-C (mmol/L)

3.08 (2.58, 3.61)

3.09 (2.58, 3.62)

3.06 (2.50, 3.61)

3.09 (2.59, 3.61)

Non-HDL-C (mmol/L)

3.63 (3.04, 4.25)

3.65 (3.04, 4.28)

3.59 (3.00, 4.21)

3.62 (3.04, 4.21)

ALP (U/L)

65 (55, 77)

65 (54, 77)

66 (55, 78)

65 (55, 78)

GGT (U/L)

25 (17, 40)

25 (16, 39)

26 (17, 40)

25 (17, 40)

ALT (U/L)

20 (14, 30)

20 (14, 30)

21 (15, 31)

20 (14, 29)

AST (U/L)

20 (16, 24)

19 (16, 24)

20 (17, 24)*

20 (17, 24)

TP (g/L)

69.8 (67.4, 72.3)

70.2 (67.8, 72.6)

70.2 (67.6, 72.6)

69.1 (66.8, 71.6)***

ALB (g/L)

44.10 (42.60, 45.70)

44.30 (42.70, 45.90)

44.30 (42.70, 45.70)

43.80 (42.30, 45.40)***

TBIL (umol/L)

12.8 (10.0, 16.4)

12.7 (10.0, 16.3)

13.2 (10.1, 16.5)

12.8 (10.0, 16.4)

BUN (mmol/L)

5.07 (4.32, 5.92)

5.08 (4.31, 5.90)

5.05 (4.35, 5.88)

5.04 (4.31, 5.97)

Cr (μmol/L)

67 (56, 77)

67 (56, 77)

68 (56, 78)

68 (57, 77)

UA (μmol/L)

349 (285, 412)

348 (284, 409)

347 (281, 411)

350 (286, 417)

  1. Characteristics are presented as median (interquartile range) for continuous features and frequencies (%) for categorical features
  2. ALB  albumin; ALP alkaline phosphatase; ALT alanine aminotransferase; AST aspartate aminotransferase; BMI body mass index; BUN blood urea nitrogen; CAS carotid atherosclerosis; Cr creatine; DBP diastolic blood pressure; FPG fasting plasma glucose; GGT gamma-glutamyl transpeptidase; HDL-C high-density lipoprotein-C; LDL-C low-density lipoprotein-C; non-HDL-C non high-density lipoprotein cholesterol; SBP systolic blood pressure; TC total cholesterol; TG triglyceride; TP total protein; TBIL total bilirubin; UA uric acid
  3. #Comparing each validation set to the training set
  4. *P-value < 0.05; **P-value < 0.01; ***P-value < 0.001