February 5, 2013 | Ewout W. Steyerberg, Karel G. M. Moons, Danielle A. van der Windt, Jill A. Hayden, Pablo Perel, Sara Schroter, Richard D. Riley, Harry Hemingway, Douglas G. Altman, for the PROGRESS Group
The article "Prognosis Research Strategy (PROGRESS) 3: Prognostic Model Research" by Ewout W. Steyerberg et al. reviews the development, validation, and impact assessment of prognostic models in medical practice. Prognostic models are formal combinations of multiple predictors that estimate the risk of specific endpoints for individual patients. The authors highlight the importance of these models in stratified medicine, where treatment decisions are informed by an individual's profile of prognostic factors. They discuss the challenges in developing and validating models, emphasizing the need for external validation and clinical impact studies. The article also addresses the updating of models to incorporate new prognostic factors and biomarkers, and the importance of collaboration between research groups to enhance model development and validation. The authors recommend improving the reporting of prognostic model research to help clinicians identify robust models with potential clinical value.The article "Prognosis Research Strategy (PROGRESS) 3: Prognostic Model Research" by Ewout W. Steyerberg et al. reviews the development, validation, and impact assessment of prognostic models in medical practice. Prognostic models are formal combinations of multiple predictors that estimate the risk of specific endpoints for individual patients. The authors highlight the importance of these models in stratified medicine, where treatment decisions are informed by an individual's profile of prognostic factors. They discuss the challenges in developing and validating models, emphasizing the need for external validation and clinical impact studies. The article also addresses the updating of models to incorporate new prognostic factors and biomarkers, and the importance of collaboration between research groups to enhance model development and validation. The authors recommend improving the reporting of prognostic model research to help clinicians identify robust models with potential clinical value.