CMStatistics 2022: Start Registration
View Submission - CMStatistics
Title: Making predictions under hypothetical interventions in clinical prediction models Authors:  Niels Peek - The University of Manchester (United Kingdom) [presenting]
Abstract: The methods with which clinical prediction models are usually developed mean that neither the parameters nor the predictions should be interpreted causally. For many applications, this is perfectly acceptable. However, when these models are used to support clinical decision-making, there is often a need for predicting outcomes under hypothetical interventions. We aimed to compare methodological approaches for predicting individual-level cardiovascular risk under three hypothetical interventions: smoking cessation, reducing blood pressure, and reducing cholesterol. We used data from the PREDICT prospective cohort study in New Zealand to calculate cardiovascular risk in a primary care setting. We compared three strategies to estimate absolute risk under hypothetical interventions: (a) conditioning on hypothetical interventions in non-causal models; (b) integrating existing prediction models with causal effects estimated using observational causal inference methods; and (c) integrating existing prediction models with causal effects reported in published literature.