How AI Makes Intervention Recommendations

This demo illustrates social distancing recommendations (NPIs) that Evolutionary AI generates for different countries at different stages of the pandemic. You first select the country from the map at right, and then select the degree to which you'd like to minimize the number of cases vs. minimize the stringency of NPIs from the slider on the left. Among the ~10161 possible NPI schedules for the next 180 days, the AI will then recommend one that implements that tradeoff with as few cases and NPIs as possible. The predicted number of cases and the recommended NPIs will be shown over time in the charts below. See Optimizing COVID-19 Interventions for the general context, in-depth technical paper, and a summary video, and ESP Introduction for a description of the Evolutionary AI technology and its other applications.

What is going on?

The ESP system learned to make recommendations based on historical data, in this case publicly available COVID-19 data provided by Oxford University (Hale, Webster, Petherick, Phillips, Kira, 2020, Oxford COVID-19 Government Response Tracker, Blavatnik School of Government, Oxford University) and COVID-19 Data Repository by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University. As described in this paper, ESP consists of two learning tasks: learning to predict, and using the predictor as a surrogate for the real world, to prescribe actions that lead to desirable outcomes.

The Predictor was first trained with historical data. It is an LSTM recurrent neural network. Given number of cases and NPIs in the past two weeks, its task is to predict the cases the next day. This prediction and any changes to NPIs were then fed back into the LSTM as input data to predict the next day, cascading predictions upto 180 days into the future.

Using the Predictor as a surrogate, a Prescriptor neural network was then created through population-based search. Initially a population of random Prescriptor neural networks was created. During each generation, each network was evaluated in turn, based on how well their NPI recommendations fared in two dimensions: the number of cases, and the sum of NPI stringency levels, both averaged over the following 180 days and over the 20 countries with the most deaths. As usual in evolution, those networks that performed well along one or both objectives were crossed over and mutated to form offspring networks, replacing those that performed poorly. The population thus discovered a Pareto front of tradeoffs between these two objectives (for an animation, see Demo 2.2).

Twenty different Prescriptors from Demo 2.2 are used in this demo. The selected one is initialized with data for a selected country, and it recommends NPIs over time. The same initial sequence and the recommended NPIs are given to the Predictor, and it generates the plot of cases over time (you can zoom in with the mouse by dragging). Uncertainty in the predictions is estimated through RIO, a Gaussian process approach for estimating residuals (RIO). The gray area represents the upper and lower quartiles of the distribution for each day. It is formed by rolling out uncertainties stochastically day by day for 180 days, thus resulting in jagged boundaries.

Explore especially the intermediate prescriptors that try to balance the two objectives by combining and alternating various NPI recommendations. Given the amount and quality of available data, these recommendations should not yet be taken literally, but it is possible to see certain informative trends to emerge: for example schools and workplace restrictions, i.e. those where people spend a lot of time with the same people mostly indoors, have the largest impact. Also, the model suggests that there may be creative ways to implement these restrictions gradually, for instance by alternating them on and off over time. These insights also change depending on the stage in the pandemic. For example, in June there appeared to be a shift where NPIs were no longer as effective as they had been (possibly because people were eager to emerge from lockdowns). Also, schools were closed for the summer in many countries, and travel restrictions become more important. The data is updated frequently, and the Predictors and Prescriptors trained with it, and thus the system is continuously adjusting to the changing face of the pandemic.