Quantifying the impact of different approaches for handling continuous predictors on the performance of a prognostic model

Collins, Gary, Ogundimu, Emmanuel, Cook, Jonathan, Le Manach, Yannick and Altman, Douglas (2016) Quantifying the impact of different approaches for handling continuous predictors on the performance of a prognostic model. Statistics in Medicine, 35 (23). pp. 4124-4135. ISSN 0277-6715

Preview	Text Collins_et_al-2016-Statistics_in_Medicine.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (852kB) | Preview
	Text Impact_of_categorisation_on_performance_1accepted copy.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy
	Text (Supplemental material for accepted version) sim6986-sup-0001-SI.pdf - Supplemental Material Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Continuous predictors are routinely encountered when developing a prognostic model. Investigators, who are often non-statisticians, must decide how to handle continuous predictors in their models. Categorising continuous measurements into two or more categories has been widely discredited, yet is still frequently done because of its simplicity, investigator ignorance of the potential impact and of suitable alternatives, or to facilitate model uptake. We examine three broad approaches for handling continuous predictors on the performance of a prognostic model, including various methods of categorising predictors, modelling a linear relationship between the predictor and outcome and modelling a nonlinear relationship using fractional polynomials or restricted cubic splines. We compare the performance (measured by the c-index, calibration and net benefit) of prognostic models built using each approach, evaluating them using separate data from that used to build them. We show that categorising continuous predictors produces models with poor predictive performance and poor clinical usefulness. Categorising continuous predictors is unnecessary, biologically implausible and inefficient and should not be used in prognostic model development.

Actions (login required)

View Item

Downloads