Skip to main content

Table 1 Table of descriptive statistics for data features with P-Value Analysis: The table presents the descriptive statistics for each feature in the dataset, stratified by ‘Improved’ and ‘Not Improved’ sub-cohorts

From: Second opinion machine learning for fast-track pathway assignment in hip and knee replacement surgery: the use of patient-reported outcome measures

Feature

Mean (Not Impr.)

St.Dev (Not Impr.)

Mean (Impr.)

St.Dev. (Impr.)

Missing (Not Impr.)

Missing (Impr.)

P-value

Age

67.100

10.690

66.579

10.496

0%

0%

0.493

VAS (Preop)

6.856

2.333

7.226

2.031

0.4%

1.5%

0.069

SF12 Physical (Preop)

38.812

8.439

30.868

6.449

0%

0%

< 0.001*

SF12 Mental (Preop)

49.365

11.362

51.495

11.996

0%

0%

0.011*

EQ5D (Preop)

0.760

0.126

0.708

0.111

0%

0.3%

< 0.001*

Height

166.777

9.074

167.685

9.033

1.6%

0.7%

0.288

Weight

75.543

14.461

77.583

15.455

1.6%

0.7%

0.179

BMI

27.119

4.566

27.486

4.413

1.6%

0.7%

0.236

Hb (Preop)

13.922

1.352

14.066

1.399

0.8%

0.4%

0.248

Feature

Categories (Not Impr.)

Categories (Impr.)

P-value

Sex

Female (42.2%), Male (57.8%)

Female (48.4%), Male (51.6%)

0.229

Hip/Knee

Hip (42.2%), Knee (57.8%)

Hip (62.5%), Knee (37.5%)

< 0.001*

First Intervention

First Intervention (96%), Revision (4%)

First Intervention (96.3%), Revision (3.6%)

0.191

ASA

1 (11.6%), 2 (86.1%), 3 (2.3%)

1 (14.4%), 2 (81.6%), 3 (4%)

1 (0.443), 2 (0.162), 3 (0.159)

  1. For continuous and ordinal features, differences were assessed using the Mann-Whitney U test, while for categorical features, the Fisher’s exact test was utilized to determine statistical significance
  2. Asterisk denotes a significant difference between the two cohorts, at the 95% confidence level