Skip to main content

Table 6 Pearson correlation coefficients (PCC) and Shapiro–Wilk tests

From: Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone

Pearson correlation coefficient

Shapiro–Wilk test

Rank

Feature

abs(PCC)

Rank

Feature

p-value

1

Serum creatinine

0.294

1

Creatinine phosphokinase

7.05×10−28

2

Ejection fraction

0.269

2

Serum creatinine

5.39×10−27

3

Age

0.254

3

Smoking

4.58×10−26

4

Serum sodium

0.195

4

Death event

4.58×10−26

5

High blood pressure

0.079

5

Sex

1.17×10−25

6

Anaemia

0.066

6

High blood pressure

1.17×10−25

7

Creatinine phosphokinase

0.063

7

Diabetes

5.12×10−25

8

Platelets

0.049

8

Anaemia

6.21×10−25

9

Smoking

0.013

9

Platelets

2.89×10−12

10

Sex

0.004

10

Serum sodium

9.21×10−10

11

Diabetes

0.002

11

Ejection fraction

7.22×10−09

   

12

Age

5.34×10−05

  1. Results of the univariate application of the Pearson correlation coefficient between each feature and the target feature death event, absolute value (left), and the univariate application of the Shapiro–Wilk test on each feature (right)