Causal prediction models to support preventive clinical decision making

Clinical prediction models are mathematical models/algorithms that take a set of patient characteristics as inputs and provide their individual risk of an event of interest as output. The methods with which 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 prediction models are used to support decision making, there is often a need for predicting outcomes under hypothetical interventions. In my talk I will illustrate the need for causal prediction models using real-world clinical examples, and review the state-of-the-art and outstanding challenges in this emerging area of research.