Developing clinical prediction models: a step-by-step guide

Abstract

Predicting future outcomes of patients is essential to clinical practice, with many prediction models published each year. Empirical evidence suggests that published studies often have severe methodological limitations, which undermine their usefulness. This article presents a step-by-step guide to help researchers develop and evaluate a clinical prediction model. The guide covers best practices in defining the aim and users, selecting data sources, addressing missing data, exploring alternative modelling options, and assessing model performance. The steps are illustrated using an example from relapsing-remitting multiple sclerosis. Comprehensive R code is also provided. Clinical prediction models aim to forecast future health outcomes given a set of baseline predictors to facilitate medical decision making and improve people’s health outcomes.1 Prediction models are becoming increasingly popular, with many new ones published each year. For example, a review of prediction models identified 263 prediction models in obstetrics alone2; another review found 606 models related to covid-19.3 Interest in predicting health outcomes has been heightened by the increasing availability of big data,4 which has also led to the uptake of machine learning methods for prognostic research in medicine.56 Several resources are available to support prognostic research. The PROGRESS (prognosis research strategy) framework provides detailed guidance on different types of prognostic research.789 The TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) statement gives recommendations for reporting and has recently been extended to address prediction model research in clustered datasets.1011121314 PROBAST (prediction model risk-of-bias assessment tool) provides a structured way to assess the risk of bias in a prediction modelling study.15 Several papers further outline good practices and provide software code.161718 Despite these resources, published prediction modelling studies often have severe methodological limitations. For instance, …