The COVID-19 pandemic emphasized the essential role of timely, effective modeling and analytic tools during health crises. Advances in machine learning, increased access to epidemiological and digital data streams, and enhanced computational capacity have significantly improved epidemic modeling and mechanistic transmission models. These advancements have significantly enhanced forecasting data and analytical capabilities, empowering public health decision-makers, particularly at state and local levels. Modeling, forecasting, and analytics have moved from academic exercises to key public health decision-making tools, as demonstrated in the Ebola and Zika outbreaks, the CDC's influenza challenge and COVID-19 response. Constantly innovating and improving analytical capacities is crucial for enabling informed decision-making, and facilitating effective actions during outbreak responses.
Our ABMP features three validated approaches: LANL's EpiCast simulates the entire U.S. population with extensive geographical and demographic data; the Multiplex Agent-Based (MAB) model by IU and NEU replicates the US population's from socio-demographic data; and UF hosts a model using synthetic populations derived from various datasets. This suite allows for comparisons of different models output against real outbreak data and to assess the impact of behavior change, vaccines, and therapeutics to guide intervention policies.
This platform uses the metapopulation approach of the Global Epidemic and Mobility model. It covers over 3,200 census areas across nearly 190 countries, incorporating comprehensive mobility data. The model's unique capabilities allow adaptable precision in describing disease dynamics within each subpopulation and have been validated during major outbreaks. The platform allows to model and track epidemic across international boundaries and simulate explicitly cases dissemination and the introduction emerging infectious diseases through port of entry and traveling hubs.
Our consortium hosts multiple forecasting platforms. LANL houses Covid-19 and influenza forecasting models; the MOBS-NEU model contributes to the Flusight initiative, and the COVID-19 Forecast hub; and the ARGO platform at NEU integrates historical local case counts with various external data sources. These platforms amalgamate both mechanistic and machine learning approaches.
Our proposed application will develop innovative methodologies to integrate advanced statistical and analytical frameworks and machine intelligence with mechanistic modeling techniques, identifying new approaches that improve local, state, and regional forecasting and modeling capabilities and analytics tools. The proposed activities involve integrating novel data sources—including high-resolution mobility, airline travel, genomic and wastewater surveillance data—with agent-based, statistical, and deep learning forecasting models to increase the accuracy of outbreak analytic products. Importantly, our approach will consider population heterogeneities/disparities and will deliver outbreak analytic tools for rural/underserved populations and for diseases/locations with low prevalence. Finally, we will identify best practices for how to transfer and maintain the needed methodology, technical expertise, and data sources, and establish a comprehensive training program for public health workforce and emergency response decision makers (which includes embedding co-op students into public health/healthcare delivery agencies and developing collabathons).
.png)
