Machine learning assisted calibration of stochastic agent-based models for pandemic outbreak analysis (preprint)

Mathematical modelling with agent-based models (ABMs) has gained popularity during the COVID-19 pandemic, but their complexity makes efficient and robust calibration to data challenging. We propose an improved method for calibrating ABMs that combines a machine-learning step with Approximate Bayesian Computation (ML-ABC). We showcase its application to Covasim - a stochastic ABM that has been timely and responsively used to model the English COVID-19 epidemic and inform policy at important junctions. We illustrate the advantage of ML-ABC application in calibrating Covasim during the first and the second COVID-19 epidemic waves of 2020 and early 2021, demonstrating that the use of an ML screening step allows us to derive faster and more efficient estimates of the posterior distribution of the Covasim optimal parameters without compromising on accuracy. This is important for generating timely responsive modelling results during an emerging epidemic.

Fusing Low-Latency Data Feeds with Death Data to Accurately Nowcast COVID-19 Related Deaths (preprint)

The emergence of the novel coronavirus (COVID-19) has generated a need to quickly and accurately assemble up-to-date information related to its spread. While it is possible to use deaths to provide a reliable information feed, the latency of data derived from deaths is significant. Confirmed cases derived from positive test results potentially provide a lower latency data feed. However, the sampling of those tested varies with time and the reason for testing is often not recorded. Hospital admissions typically occur around 1-2 weeks after infection and can be considered out of date in relation to the time of initial infection. The extent to which these issues are problematic is likely to vary over time and between countries. We use a machine learning algorithm for natural language processing, trained in multiple languages, to identify symptomatic individuals derived from social media and, in particular Twitter, in real-time. We then use an extended SEIRD epidemiological model to fuse combinations of low-latency feeds, including the symptomatic counts from Twitter, with death data to estimate parameters of the model and nowcast the number of people in each compartment. The model is implemented in the probabilistic programming language Stan and uses a bespoke numerical integrator. We present results showing that using specific low-latency data feeds along with death data provides more consistent and accurate forecasts of COVID-19 related deaths than using death data alone.