When Do We Need Massive Computations to Perform Detailed COVID‐19 Simulations?

Abstract

The COVID‐19 pandemic has infected over 250 million people worldwide and killed more than 5 million as of November 2021. Many intervention strategies are utilized (e.g., masks, social distancing, vaccinations), but officials making decisions have a limited time to act. Computer simulations can aid them by predicting future disease outcomes, but they also require significant processing power or time. It is examined whether a machine learning model can be trained on a small subset of simulation runs to inexpensively predict future disease trajectories resembling the original simulation results. Using four previously published agent‐based models (ABMs) for COVID‐19, a decision tree regression for each ABM is built and its predictions are compared to the corresponding ABM. Accurate machine learning meta‐models are generated from ABMs without strong interventions (e.g., vaccines, lockdowns) using small amounts of simulation data: the root‐mean‐square error (RMSE) with 25% of the data is close to the RMSE for the full dataset (0.15 vs 0.14 in one model; 0.07 vs 0.06 in another). However, meta‐models for ABMs employing strong interventions require much more training data (at least 60%) to achieve a similar accuracy. In conclusion, machine learning meta‐models can be used in some scenarios to assist in faster decision‐making.

Assessing the impact of architectural and behavioral interventions for controlling indoor COVID-19 infection risk: An agent-based approach

“…However, the problem of high time cost can be resolved by the use of hybrid models. For instance, Lutz and Giabbanelli [ 96 ] have developed machine leaning regression models for 4 COVID-19 ABMs to assist in fast decision-making. With the continuous improvement of hardware computing power and supervised learning algorithms, time cost will become less of a problem.…”

Innovations in integrating machine learning and agent-based modeling of biomedical systems

“…This DNN-based surrogate model was then used for parameter calibration (Pereira et al, 2021). Other studies have taken similar approaches, for example, by using regression algorithms to train surrogate meta-models of an ABM of interest (Tong et al, 2015;Li et al, 2017;Sai et al, 2019;Lutz and Giabbanelli, 2022).…”

A Scoping Review of Three Dimensions for Long-Term COVID-19 Vaccination Models: Hybrid Immunity, Individual Drivers of Vaccinal Choice, and Human Errors

“…In the simulated timespans of these models, it was adequate to consider that individuals would have a constant level of immunity once recovered or vaccinated, and that the dominant strain at the time was the only one . As we transition into a more long-term perspective, we need to account for changes in the level of immunity, including the cumulative effect of vaccination and recovery (particularly since most Americans have had COVID-19 [ 54 ]), as well as the ongoing emergence of variants.…”