Active Learning to Understand Infectious Disease Models and Improve Policy Making

Modeling plays a major role in policy making, especially for infectious disease interventions but such models can be complex and computationally intensive. A more systematic exploration is needed to gain a thorough systems understanding. We present an active learning approach based on machine learning techniques as iterative surrogate modeling and model-guided experimentation to systematically analyze both common and edge manifestations of complex model runs. Symbolic regression is used for nonlinear response surface modeling with automatic feature selection. First, we illustrate our approach using an individual-based model for influenza vaccination. After optimizing the parameter space, we observe an inverse relationship between vaccination coverage and cumulative attack rate reinforced by herd immunity. Second, we demonstrate the use of surrogate modeling techniques on input-response data from a deterministic dynamic model, which was designed to explore the cost-effectiveness of varicella-zoster virus vaccination. We use symbolic regression to handle high dimensionality and correlated inputs and to identify the most influential variables. Provided insight is used to focus research, reduce dimensionality and decrease decision uncertainty. We conclude that active learning is needed to fully understand complex systems behavior. Surrogate models can be readily explored at no computational expense, and can also be used as emulator to improve rapid policy making in various settings.Author Summary: Mathematical models are used as pragmatic tools to inform policy makers on public health interventions and many non-health problems. Considerable efforts have been made to build realistic simulation models. Understanding the systems behavior and the effect of model assumptions and parameter values on the results before drawing conclusions for policy is crucial. Common and edge manifestations of complex model runs should be analyzed and therefore we present an active learning approach, also known as a sequential design of experiments, based on surrogate modeling and a model-guided experimentation process. First, we illustrate our approach with an individual-based model for influenza and demonstrate the benefits compared to current complex modeling practices. Second, we establish the power of our approach with a high dimensional model with correlated inputs to explore cost-effectiveness of varicella-zoster vaccination programs. The most influential variables are identified with the aim to reduce dimensionality and decrease decision uncertainty. We also elaborate on the use of surrogate models as an emulator to improve rapid policy making in various settings. To this purpose we provide an interactive platform through which the reader can explore instantaneously the sensitivity of the surrogate models to parameter changes for both our applications.