Predicting the time to get back to work using statistical models and machine learning approaches
Implementing a series of survival models with and without proportional hazards background provides a useful insight as well as better interpretation of the coefficients affected by non-linearities. However, that better fit does not translate to substantially higher predictive power and accuracy from using machine learning approaches. Further tuning of the machine learning algorithms may provide improved results.
Authors
- Martin Underwood (ORCID: https://orcid.org/0000-0002-0309-1708)
- Robert Froud (ORCID: https://orcid.org/0000-0002-9193-2297)
- George Bouliotis (ORCID: https://orcid.org/0000-0002-1287-8473)
Institutions
- Høyskolen Kristiania (NO)
- University of Warwick (GB)
Publication Details
- Journal
- BMC Medical Research Methodology
- Published
- 2024-11-29
- DOI
- https://doi.org/10.1186/s12874-024-02390-4
- Citations
- 1
- Primary Topic
- Retirement, Disability, and Employment
- Type
- article
- Field-Weighted Citation Impact
- 1.71
Funders
- Stryker
- National Institute for Health and Care Research
- University of Warwick
- University Hospitals Coventry and Warwickshire NHS Trust
- Medical Research Council
- National Health and Medical Research Council