Skip to main content

Table 1 Characteristics of patients with diabetes by unplanned visit status

From: Predicting unplanned medical visits among patients with diabetes: translation from machine learning to clinical implementation

Predictor variable

No unplanned visits

(N = 18,771)

 ≥ 1 Unplanned visits

(N = 25,060)

p value

Age

65 (55–74)

66 (55–76)

< .0001

BMI

32.3 (28.3–37.0)

32.2 (28.0–37.3)

= .2454

Systolic BP

126.0 (118.0–134.0)

126.0 (116.0–136)

= .0089

Diastolic BP

72.0 (66.0–80.0)

72.0 (64.0–80.0)

< .0001

LDL cholesterol

85.0 (67.0–106.0)

84.0 (65.0–106.0)

= .0053

HDL cholesterol

44.0 (37.0–53.0)

42.0 (35.0–52.0)

< .0001

A1C

6.9 (6.3–7.8)

6.9 (6.3–7.9)

= .0001

Ranked smoking status

1.0 (0.0–2.0)

2.0 (0.0–2.0)

< .0001

Number of diagnoses on problem list

3.0 (2.0–4.0)

4.0 (3.0–6.0)

< .0001

Number of prescriptions

88.0 (40.0–179.0)

205.0 (96.0–408.0)

< .0001

  1. Variables are summarized as median (interquartile range). A1C glycohemoglobin. BMI body mass index. BP blood pressure. HDL high-density lipoprotein. LDL low-density lipoprotein. p values are based on t-tests of each variable across groups (any vs. no unplanned visits). Bold: p < .05