Table 3 Variables included in the random survival forest MLR ranked based on their variable importance value (VIMP).

From: Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach

Variables

VIMP, mean (SD)

IR (%)

Age of RA diagnosis

0.110 (0.001)

100

Median ESR in the first 2 years after RA diagnosis

0.014 (9.8 × 10−4)

12.7

Hospital admissions in the first 2 years after RA diagnosis

0.012 (7.0 × 10−4)

10.5

Calendar year of RA diagnosis

0.009 (9.1 × 10−4)

8.4

Spaniard

0.005 (5.3 × 10−4)

4.5

Presence of Rheumatoid Factor

6.1 × 10−4 (5.7 × 10−4)

0.6

Any biological therapy in the first 2 years after RA diagnosis

3.5 × 10−4 (1.7 × 10−4)

0.3

Elapsed time from RA symptoms onset to diagnosis

2.8 × 10−4 (9.4 × 10−4)

0.2

Gender

0.5 × 10−4 (5.5 × 10−4)

0.1

  1. ACPA: Anti-citrullinated peptides antibodies; ESR: Erythrocyte sedimentation rate; HAQ: Health assessment questionnaire; RA: Rheumatoid Arthritis; SD: standard deviation; VIMP: Variable importance.
Back to article page