Skip to main content

Table 4 Performance parameters of ML models with primary outcome measure for LBP non-recovery (NRS > 2) (with final 3-item model in bold)

From: Development and internal validation of a machine learning prediction model for low back pain non-recovery in patients with an acute episode consulting a physiotherapist in primary care

 

AUC (95% CI)

Accuracy

1. 1-item model: resilience

0.61 (0.53–0.69)

58%

2. 2-item model: 1 + patient’s recovery expectation

0.65 (0.55–0.70)

62%

3. 3-item model: 2 + disability previous LBP episode

0.66 (0.56–0.70)

63%

4. 4-item model: 3 + bothersomeness (SBT item 9)

0.65 (0.55–0.70)

61%

5. 5-item model: 4 + physically demanding work

0.64 (0.55–0.69)

62%

6. 6-item model: 5 + work absenteeism

0.64 (0.56–0.70)

60%

7. 7-item model: 6 + frequency previous LBP episodes

0.64 (0.56–0.70)

59%

8. 8-item model: 7 + physical activity

0.63 (0.55–0.70)

60%

9. 9-item model: 8 + work ability

0.64 (0.54–0.69)

61%

10. 10-item model: 9 + pain severity

0.63 (0.55–0.69)

59%

  1. AUC Area under the curve, CI Confidence interval