Explicit causal reasoning is needed to prevent prognostic models being victims of their own success

The recent perspective by Lenert et al 1 provides an accessible and in-formative overview of the full life cycle of prognostic models, com-prising development, deployment, maintenance, and surveillance. The perspective focuses particularly on the fundamental issue that deployment of a prognostic model into clinical practice will lead to changes in decision making or interventions, and hence, changes in clinical outcomes. This has received little attention in the prognostic modeling literature but is important because this changes predictor-outcome associations, meaning that the performance of the model degrades over time; therefore, prognostic models become “victims of their own success.” More seriously, a prediction from such a model is challenging to interpret, as it implicitly reflects both the risk factors and the interventions that similar patients received, in the historical data used to develop the prognostic model. The authors rightly point out that “holistically modeling the outcome and interventions(s)” and “incorporat[ing] the intervention space” are required to overcome this concern. 1 However, the proposed so-lution of directly modeling interventions, or their surrogates, is not sufficient. An explicit causal inference framework is required. When the intended use of a prognostic model is to support deci-sions concerning intervention(s), the counterfactual causal framework provides a natural and powerful way to ensure that predictions issued by the prognostic model are useful, interpret-able, and less vulnerable to degradation over time. The framework allows predictions to be used to answer “what if” questions; for an introduction, see Hernan and Robbins. 2 However, challenging than pure