Developing and evaluating prediction models in rehabilitation populations

Ronald T. Seel, Ewout W. Steyerberg, James F. Malec, Mark Sherer, Stephen N. MacCiocchi

Research output: Contribution to journalComment/debate

33 Scopus citations


This article presents a 3-part framework for developing and evaluating prediction models in rehabilitation populations. First, a process for developing and refining prognostic research questions and the scientific approach to prediction models is presented. Primary components of the scientific approach include the study design and sampling of patients, outcome measurement, selecting predictor variable(s), minimizing methodologic sources of bias, assuring a sufficient sample size for statistical power, and selecting an appropriate statistical model. Examples focus on prediction modeling using samples of rehabilitation patients. Second, a brief overview for statistically building and validating multivariable prediction models is provided, which includes the following 7 steps: data inspection, coding of predictors, model specification, model estimation, model performance, model validation, and model presentation. Third, we propose a set of primary considerations for evaluating prediction model studies using specific quality indicators as criteria to help stakeholders evaluate the quality of a prediction model study. Lastly, we offer perspectives on the future development and use of rehabilitation prediction models.

Original languageEnglish (US)
Pages (from-to)S138-S153
JournalArchives of physical medicine and rehabilitation
Issue number8 SUPPL.
StatePublished - Aug 2012


  • Biostatistics
  • Evidence-based medicine
  • Evidence-based practice
  • Models, statistical
  • Multivariate analysis
  • Prognosis
  • Rehabilitation
  • Review literature as topic
  • Statistics as topic

ASJC Scopus subject areas

  • Rehabilitation
  • Physical Therapy, Sports Therapy and Rehabilitation

Fingerprint Dive into the research topics of 'Developing and evaluating prediction models in rehabilitation populations'. Together they form a unique fingerprint.

  • Cite this

    Seel, R. T., Steyerberg, E. W., Malec, J. F., Sherer, M., & MacCiocchi, S. N. (2012). Developing and evaluating prediction models in rehabilitation populations. Archives of physical medicine and rehabilitation, 93(8 SUPPL.), S138-S153.