EUVIMEDEUVIMED entdecken
Crossref

When Is a Prognostic Prediction Model Ready for Clinical Use? A Primer for Clinicians

Daniel Feller, Alessandro Chiarotto

Journal of Orthopaedic & Sports Physical Therapy · 2026

DOI: 10.2519/jospt.2026.13868 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Orthopaedic & Sports Physical Therapy, 2026. Verfasst von Daniel Feller und 1 weiteren Autor:innen. Hauptthemen laut MEDLINE: Clinical Decision-Making. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 38 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: In clinical practice, accurately estimating a patient’s prognosis is essential for clinical decision making. Prognostic prediction models can support this process by combining multiple patients’ characteristics into individualized predictions. However, prognostic models require careful methodological evaluation before being applied in practice. CLINICAL QUESTION: How can clinicians determine whether a prognostic prediction model is ready for use in routine practice? KEY RESULTS: Prognostic prediction models are algorithms that combine multiple variables to estimate the likelihood of an outcome. They can be developed using regression-based methods or machine learning approaches. They are usually developed in a specific data set. However, good performance in the data set does not guarantee that the model will perform well when applied to new patient data in practice. Prognostic models must undergo validation (internal and/or external) and clinical impact evaluation before being implemented in practice. The performance of the model (at development and validation) should be evaluated across 3 key aspects: discrimination, calibration, and clinical utility. The risk of bias of a model should also be assessed, as weaknesses in study design or analysis can undermine the reliability of results. An effectiveness study should finally evaluate whether a model improves patients’ outcomes. CLINICAL APPLICATION: Clinicians should follow a structured process to review prognostic models before adopting them in practice. Clinicians should verify that the model has been validated in the target population, evaluate its performance metrics, and appraise its risk of bias. Only models that meet minimum standards across these domains should be considered suitable for clinical use. J Orthop Sports Phys Ther 2026;56(4):227-234. Epub 12 February 2026. doi:10.2519/jospt.2026.13868

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Clinical Decision-MakingHumansPrognosisPrediction AlgorithmsPredictive Learning ModelsReproducibility of ResultsAlgorithms

Stichwörter der Autor:innen

PROBAST+AIartificial intelligencemusculoskeletal disorderspredictive models

Zitieren

APA

Feller, D., & Chiarotto, A. (2026). When Is a Prognostic Prediction Model Ready for Clinical Use? A Primer for Clinicians. Journal of Orthopaedic & Sports Physical Therapy. https://doi.org/10.2519/jospt.2026.13868

Vancouver

Feller D, Chiarotto A. When Is a Prognostic Prediction Model Ready for Clinical Use? A Primer for Clinicians. Journal of Orthopaedic & Sports Physical Therapy. 2026. doi:10.2519/jospt.2026.13868

BibTeX
@article{Feller2026,
  author = {Feller, Daniel and Chiarotto, Alessandro},
  title = {When Is a Prognostic Prediction Model Ready for Clinical Use? A Primer for Clinicians},
  journal = {Journal of Orthopaedic & Sports Physical Therapy},
  year = {2026},
  doi = {10.2519/jospt.2026.13868}
}
Kostenlos starten →