Skip to main content

Table 2 Implications of the DKD risk algorithm across baseline tertiles of UACR. The HR for the primary composite endpoint is expressed as a function of low or high DKD risk within tertiles of UACR. In the setting of a low-risk DKD algorithm result, the HR for the primary composite endpoint was low and without difference across UACR tertiles. Conversely, in the setting of high risk DKD algorithm result, risk for the primary composite endpoint was present even in lower UACR tertiles

From: A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney disease

 

CREDENCE derivation

CREDENCE validation

CANVAS validation

Category

HR

95% CI

P value

HR

95% CI

P value

HR

95% CI

P value

Low DKD risk result/UACR Tertile 1

0.38

0.15–0.95

0.04

0.16

0.05–0.55

0.004

0.33

0.21–0.52

 < 0.001

Low DKD risk result/UACR Tertile 2

0.12

0.03–0.50

0.004

0.16

0.04–0.69

0.01

0.35

0.09–1.37

0.13

Low DKD risk result/UACR Tertile 3

0.16

0.05–0.49

0.002

0.08

0.01–0.58

0.01

0.10

0.02–0.43

0.002

High DKD risk result/UACR Tertile 1

2.37

0.90–6.26

0.08

4.98

1.81–13.73

0.002

2.17

1.87–2.51

 < 0.001

High DKD risk result/UACR Tertile 2

4.30

2.26–8.21

 < 0.001

5.78

2.78–12.02

 < 0.001

3.10

0.66–14.58

0.15

High DKD risk result/UACR Tertile 3

3.18

2.20–4.59

 < 0.001

2.62

1.64–4.20

 < 0.001

4.40

2.17–8.91

 < 0.001

  1. DKD diabetic kidney disease; UACR urinary albumin-creatinine ratio; HR hazard ratio; CI confidence interval