Supporting COVID-19 policy response with large-scale mobility-based modeling

Social distancing measures, such as restricting occupancy at venues, have been a primary intervention for controlling the spread of COVID-19. However, these mobility restrictions place a significant economic burden on individuals and businesses. To balance these competing demands, policymakers need analytical tools to assess the costs and benefits of different mobility reduction measures.In this paper, we present our work motivated by our interactions with the Virginia Department of Health on a decision-support tool that utilizes large-scale data and epidemiological modeling to quantify the impact of changes in mobility on infection rates. Our model captures the spread of COVID-19 by using a fine-grained, dynamic mobility network that encodes the hourly movements of people from neighborhoods to individual places, with over 3 billion hourly edges. By perturbing the mobility network, we can simulate a wide variety of reopening plans and forecast their impact in terms of new infections and the loss in visits per sector. To deploy this model in practice, we built a robust computational infrastructure to support running millions of model realizations, and we worked with policymakers to develop an intuitive dashboard interface that communicates our models predictions for thousands of potential policies, tailored to their jurisdiction. The resulting decision-support environment provides policymakers with much-needed analytical machinery to assess the tradeoffs between future infections and mobility restrictions.

Mobility network modeling explains higher SARS-CoV-2 infection rates among disadvantaged groups and informs reopening strategies

Fine-grained epidemiological modeling of the spread of SARS-CoV-2--capturing who is infected at which locations--can aid the development of policy responses that account for heterogeneous risks of different locations as well as the disparities in infections among different demographic groups. Here, we develop a metapopulation SEIR disease model that uses dynamic mobility networks, derived from US cell phone data, to capture the hourly movements of millions of people from local neighborhoods (census block groups, or CBGs) to points of interest (POIs) such as restaurants, grocery stores, or religious establishments. We simulate the spread of SARS-CoV-2 from March 1-May 2, 2020 among a population of 98 million people in 10 of the largest US metropolitan statistical areas. We show that by integrating these mobility networks, which connect 57k CBGs to 553k POIs with a total of 5.4 billion hourly edges, even a relatively simple epidemiological model can accurately capture the case trajectory despite dramatic changes in population behavior due to the virus. Furthermore, by modeling detailed information about each POI, like visitor density and visit length, we can estimate the impacts of fine-grained reopening plans: we predict that a small minority of "superspreader" POIs account for a large majority of infections, that reopening some POI categories (like full-service restaurants) poses especially large risks, and that strategies restricting maximum occupancy at each POI are more effective than uniformly reducing mobility. Our models also predict higher infection rates among disadvantaged racial and socio-economic groups solely from differences in mobility: disadvantaged groups have not been able to reduce mobility as sharply, and the POIs they visit (even within the same category) tend to be smaller, more crowded, and therefore more dangerous. By modeling who is infected at which locations, our model supports fine-grained analyses that can inform more effective and equitable policy responses to SARS-CoV-2.

Interpretable Decision Sets: A Joint Framework for Description and Prediction.

One of the most important obstacles to deploying predictive models is the fact that humans do not understand and trust them. Knowing which variables are important in a model's prediction and how they are combined can be very powerful in helping people understand and trust automatic decision making systems. Here we propose interpretable decision sets, a framework for building predictive models that are highly accurate, yet also highly interpretable. Decision sets are sets of independent if-then rules. Because each rule can be applied independently, decision sets are simple, concise, and easily interpretable. We formalize decision set learning through an objective function that simultaneously optimizes accuracy and interpretability of the rules. In particular, our approach learns short, accurate, and non-overlapping rules that cover the whole feature space and pay attention to small but important classes. Moreover, we prove that our objective is a non-monotone submodular function, which we efficiently optimize to find a near-optimal set of rules. Experiments show that interpretable decision sets are as accurate at classification as state-of-the-art machine learning techniques. They are also three times smaller on average than rule-based models learned by other methods. Finally, results of a user study show that people are able to answer multiple-choice questions about the decision boundaries of interpretable decision sets and write descriptions of classes based on them faster and more accurately than with other rule-based models that were designed for interpretability. Overall, our framework provides a new approach to interpretable machine learning that balances accuracy, interpretability, and computational efficiency.