A Return-to-Work Prognostic Model for Orthopaedic Trauma Patients (WORRK) Updated for Use at 3, 12 and 24 Months.
Chantal Plomb-Holmes, François Lüthi, Philippe Vuistiner and 2 others
PMID 28012065WHAT IT FOUND
The WORRK model can predict return-to-work status at 3 and 12 months after orthopaedic trauma if its intercept is updated.
It correctly identifies non-returners with moderate accuracy, helping clinicians tailor rehabilitation intensity earlier in the recovery process.
Key findings
01The original WORRK model showed significant miscalibration for 3- and 12-month predictions, but updating the intercept corrected this without changing the discrimination (AUC 0.73).
02At a 0.5 probability threshold, the updated model predicts non-return to work with a positive predictive value of 72% at 3 months and 69% at 12 months.
03The model was developed for 2-year prediction and was temporally externally validated for 3- and 12-month prediction in the same population by adjusting only the intercept.
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat it means for OTs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The study was a temporal external validation in a specific Swiss population with a unique insurance framework, so results may not generalise to other health systems. The model does not include key factors like self-efficacy or workplace environment details because they were not standardised in the data. The calibration at 3 months was noted to be slightly inaccurate, suggesting the model might benefit from further refinement with a larger sample size. The effectiveness of using this model to actually improve patient outcomes has not yet been tested in a randomised controlled trial.
Declared interests
The study used data from the Clinique Romande de Réadaptation, a medical centre of the Swiss National Accident Insurance Fund (Suva). The paper does not explicitly state funding sources or author conflicts of interest in the provided text, but the setting implies an institutional context focused on insurance-related rehabilitation.
The easy way to misread this
Do not assume this model proves that using it improves patient outcomes. The study validates the model's predictive accuracy for return-to-work status, but the authors explicitly state that the effectiveness of applying this tool in clinical practice to change decision-making and improve results has not yet been evaluated in a randomised controlled trial.