Uncertainty in using risk prediction models to drive clinical decision making'

This project will explore sources of uncertainty associated with using routinely collected health data for the prediction of major clinical endpoints. Risk prediction models have become embedded into the health system. They are used to guide clinical decision making in a variety of settings: risk of death following surgery (should we operate?), diagnostic models (should we screen?), or the probability of having a clinical event over a certain time period (should we take preventative measures?). However uncertainty is rarely evaluated beyond the statistical confidence interval, despite differences between databases, coding systems, or statistical methods used to develop most models. The purpose of this project is to develop transparent and reproducible methods for assessing uncertainty when using classical risk prediction techniques.
Despite there being clear guidelines on the development and reporting of models, features of models developed for the same purpose often differ. Furthermore, in the field of cardiovascular disease (CVD), risk thresholds for initiating statin therapy vary across England, Scotland, the US and Europe, despite a large body of evidence on when treatment becomes cost effectiveness. This highlights uncertainty when using these models to guide treatment for a patient, as using different models or clinical guidelines may result in a different decision for an individual. This PhD will focus on identifying and assessing the extent of sources of uncertainty associated with both parts of this process, generating risk predictions, and making decisions based on these risk predictions.