Standard clinical risk prediction models aim to predict a person’s risk of an outcome (e.g. mortality) given their observed characteristics. It is often of interest to use risk predictions to inform whether a person should initiate a particular treatment. However, when standard clinical prediction models are developed in a population in which patients follow a mix of treatment strategies, they are unsuitable for informing treatment decisions.
Counterfactual prediction models provide estimates of a person’s risk of an outcome if they were to follow a particular treatment pattern, and also taking into account other patient characteristics that are predictive of the outcome. There are a range of challenges in making counterfactual predictions to create decision support tools in the healthcare setting.
This workshop will bring together researchers from academia and industry to share knowledge about estimation and validation of counterfactual prediction models in healthcare using observational data, from the perspectives of both causal inference and AI. The workshop will consist of a combination of talks, round-table discussions, demos and practical data analysis activities, led by the co-organizers and workshop participants. Days 3 and 4 of the workshop will be dedicated to a practical analysis using synthetic case-study data from an example in type 2 diabetes.
One of the aims of the workshop will be to share the knowledge arising from our discussions and practical activities in one or more tutorial papers. We also hope the workshop will lead to new collaborations between participants and across disciplines.