Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2023 Apr;38(4):627-633.
doi: 10.1016/j.arth.2022.12.032. Epub 2022 Dec 24.

How to Develop and Validate Prediction Models for Orthopedic Outcomes

Isabella Zaniletti  1 , Dirk R Larson  2 , David G Lewallen  3 , Daniel J Berry  3 , Hilal Maradit Kremers  4
Affiliations
Review

How to Develop and Validate Prediction Models for Orthopedic Outcomes

Isabella Zaniletti et al. J Arthroplasty. 2023 Apr.

Abstract

Prediction models are common in medicine for predicting outcomes such as mortality, complications, or response to treatment. Despite the growing interest in these models in arthroplasty (and orthopaedics in general), few have been adopted in clinical practice. If robustly built and validated, prediction models can be excellent tools to support surgical decision making. In this paper, we provide an overview of the statistical concepts surrounding prediction models and outline practical steps for prediction model development and validation in arthroplasty research. Please visit the followinghttps://www.youtube.com/watch?v=9Yrit23Rkicfor a video that explains the highlights of the paper in practical terms.

Keywords: arthroplasty; machine learning; model validation; orthopedics; predictors; risk prediction.

PubMed Disclaimer

Conflict of interest statement

One or more of the authors of this paper have disclosed potential or pertinent conflicts of interest, which may include receipt of payment, either direct or indirect, institutional support, or association with an entity in the biomedical field which may be perceived to have potential conflict of interest with this work.

Figures

Fig. 1.
Fig. 1.
Steps of prediction model building
Fig. 2.
Fig. 2.
Internal validation methods: (A) Validation set (B) Cross-validation (C) Bootstrapping.
Fig. 3.
Fig. 3.
Calibration Slope and Calibration Intercepts. The bold 45-degree line indicates perfect agreement between the predicted risk probability (x-axis) and the observed risk probability (y-axis). Therefore, a curve that is closer to the diagonal 45-degree line indicates a better estimation of infection risk. The dashed lines represent the predicted versus observed risk from 2 hypothetical prediction models. The model over-estimates the actual risk where the dashed lines fall below the 45-degree line. The model under-estimates the actual risk where the dashed lines are above the 45-degree line.
See this image and copyright information in PMC

References

    1. Kuo RYL, et al., Artificial intelligence in fracture detection: a systematic review and metaanalysis. Radiology, 2022. 304(1): p. 50–62. - PMC - PubMed
    1. Leung K, et al., Prediction of total knee replacement and diagnosis of osteoarthritis by using deep learning on knee radiographs: data from the Osteoarthritis Initiative. Radiology, 2020. 296(3): p. 584–593. - PMC - PubMed
    1. Harris AHS, et al., Can machine learning methods produce accurate and easy-to-use prediction models of 30-day complications and mortality after knee or hip arthroplasty? Clin Orthop Relat Res, 2019. 477(2): p. 452–460. - PMC - PubMed
    1. Van Onsem S, et al., A new prediction model for patient satisfaction after total knee arthroplasty. J Arthroplasty, 2016. 31(12): p. 2660–2667 e1. - PubMed
    1. Ayers DC, et al., Using joint registry data from FORCE-TJR to improve the accuracy of riskadjustment prediction models for thirty-day readmission after total hip replacement and total knee replacement. J Bone Joint Surg Am, 2015. 97(8): p. 668–71. - PubMed

Publication types