Table 2 Odds ratios (95% confidence intervals) of being in the theoretically nonfasting status using the AContological sample in the training dataset (n = 277,822*).

From: Application of machine learning methods for the prediction of true fasting status in patients performing blood tests

Variables

Univariate analysis

Model 1

Model 2

OR (95% CI)

p-value

OR (95% CI)

p-value

OR (95% CI)

p-value

Glucose, per 5 mg/dL

1.20 (1.20–1.21)

< 0.001

1.16 (1.16–1.16)

< 0.001

1.23 (1.23–1.23)

< 0.001

Age, per 5 years

1.16 (1.16–1.17)

< 0.001

1.01 (1.00–1.01)

< 0.001

1.05 (1.04–1.05)

< 0.001

Male

1.05 (1.03–1.06)

< 0.001

1.09 (1.07–1.11)

< 0.001

1.16 (1.14–1.18)

< 0.001

Timing of the day

7:00–12:59

Ref

 

Ref

 

Ref

 

13:00–17:59

0.96 (0.93–1.00)

0.03

0.90 (0.86–0.94)

< 0.001

0.87 (0.83–0.91)

< 0.001

18:00–22:59

1.14 (1.07–1.22)

< 0.001

0.76 (0.70–0.84)

< 0.001

0.78 (0.70–0.86)

< 0.001

Interval between request and sampling, per 28 day

1.07 (1.05–1.08)

< 0.001

0.95 (0.94–0.96)

< 0.001

1.08 (1.07–1.08)

< 0.001

No. of outpatient visits, per 4 visits

1.03 (1.02–1.04)

< 0.001

0.99 (0.99–1.00)

< 0.001

1.02 (1.02–1.02)

< 0.001

Distance from home to hospital, per 10 km

0.998 (0.996–1.000)

0.04

0.998 (0.997–1.000)

0.03

0.998 (0.996–1.00)

0.01

Division

Health management center

Ref

 

Ref

 

Ref

–

General medicine

3.39 (3.27–3.52)

< 0.001

1.49 (1.43–1.56)

< 0.001

2.24 (2.14–2.35)

< 0.001

Metabolism/endocrinology

2.57 (2.49–2.65)

< 0.001

0.67 (0.65–0.70)

< 0.001

2.11 (2.02–2.21)

< 0.001

Nephrology

3.45 (3.32–3.58)

< 0.001

1.19 (1.13–1.25)

< 0.001

2.38 (2.25–2.51)

< 0.001

Cardiology

3.03 (2.93–3.13)

< 0.001

1.09 (1.04–1.14)

< 0.001

1.99 (1.89–2.08)

< 0.001

Family medicine

2.80 (2.69–2.91)

< 0.001

1.03 (0.98–1.08)

0.22

1.90 (1.81–2.00)

< 0.001

Surgery

2.57 (2.43–2.72)

< 0.001

1.30 (1.22–1.39)

< 0.001

1.74 (1.62–1.87)

< 0.001

Pediatrics

4.43 (4.13–4.77)

< 0.001

0.67 (0.60–0.75)

< 0.001

1.78 (1.59–1.99)

< 0.001

Chinese medicine

4.07 (3.87–4.28)

< 0.001

1.00 (0.94–1.06)

0.92

1.86 (1.74–1.99)

< 0.001

Other

3.98 (3.41–4.64)

< 0.001

1.30 (1.09–1.56)

0.004

1.95 (1.60–2.37)

< 0.001

Hypertension

1.04 (1.03–1.06)

< 0.001

  

1.02 (1.00–1.05)

0.03

Diabetes mellitus

0.70 (0.68–0.71)

< 0.001

  

0.09 (0.09–0.09)

< 0.001

Coronary artery disease

1.07 (1.05–1.09)

< 0.001

  

0.94 (0.91–0.96)

< 0.001

Stroke

1.02 (0.99–1.04)

0.12

  

0.99 (0.96–1.02)

0.64

Statin use

0.78 (0.77–0.80)

< 0.001

  

0.82 (0.80–0.83)

< 0.001

Concomitant lipid profile test

0.69 (0.68–0.70)

< 0.001

  

0.78 (0.76–0.80)

< 0.001

AIC

  

297,987

262,835

AUC

  

0.820 (0.819–0.822)

0.867 (0.866–0.869)

p-value for AUC difference

  

Ref

< 0.001

  1. *Sample were reduced because of missingness for the variable of "Distance from home to hospital".
  2. AIC Akaike information criterion, AUC area under the curve.
Back to article page