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

Table 5 Performance parameters of model with (a) SBT risk profile or (b) physiotherapists’ expectation as predictor with primary outcome measure for LBP non-recovery (NRS > 2)

	OR (95% CI)	AUC (95% CI)	Accuracy	Hosmer & Lemeshow test p-value
Model (a) SBT risk profile
Low (reference) vs medium/high risk	1.25 (0.75–2.08)
Model summary		0.53 (0.45–0.60)	53%	n/a^a
Model (b) Physiotherapists’ expectation
Expectation of recovery (reference) vs. expectation of no recovery	2.27 (0.56–9.09)
Model summary		0.53 (0.46–0.61)	54%	n/a^a

OR Odds ratio, CI Confidence interval, AUC Area under the curve, n/a not applicable
^atest was not possible as model consisted of one dichotomous variable

ISSN: 1471-2474