skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Agent-Based Markov Modeling for Improved COVID-19 Mitigation Policies
The year 2020 saw the covid-19 virus lead to one of the worst global pandemics in history. As a result, governments around the world have been faced with the challenge of protecting public health while keeping the economy running to the greatest extent possible. Epidemiological models provide insight into the spread of these types of diseases and predict the effects of possible intervention policies. However, to date, even the most data-driven intervention policies rely on heuristics. In this paper, we study how reinforcement learning (RL) and Bayesian inference can be used to optimize mitigation policies that minimize economic impact without overwhelming hospital capacity. Our main contributions are (1) a novel agent-based pandemic simulator which, unlike traditional models, is able to model fine-grained interactions among people at specific locations in a community; (2) an RLbased methodology for optimizing fine-grained mitigation policies within this simulator; and (3) a Hidden Markov Model for predicting infected individuals based on partial observations regarding test results, presence of symptoms, and past physical contacts. This article is part of the special track on AI and COVID-19.  more » « less
Award ID(s):
2019844
PAR ID:
10334852
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Journal of Artificial Intelligence Research
Volume:
71
ISSN:
1076-9757
Page Range / eLocation ID:
953 to 992
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, BIBM'20, IEEE Int. Conf. on Bioinformatics and Biomedicine, Dec 2020)
    null (Ed.)
    Biomedical named entity recognition (BioNER) is a fundamental step for mining COVID-19 literature. Existing BioNER datasets cover a few common coarse-grained entity types (e.g., genes, chemicals, and diseases), which cannot be used to recognize highly domain-specific entity types (e.g., animal models of diseases) or emerging ones (e.g., coronaviruses) for COVID-19 studies. We present CORD-NER, a fine-grained named entity recognized dataset of COVID-19 literature (up until May 19, 2020). CORD-NER contains over 12 million sentences annotated via distant supervision. Also included in CORD-NER are 2,000 manually-curated sentences as a test set for performance evaluation. CORD-NER covers 75 fine-grained entity types. In addition to the common biomedical entity types, it covers new entity types specifically related to COVID-19 studies, such as coronaviruses, viral proteins, evolution, and immune responses. The dictionaries of these fine-grained entity types are collected from existing knowledge bases and human-input seed sets. We further present DISTNER, a distantly supervised NER model that relies on a massive unlabeled corpus and a collection of dictionaries to annotate the COVID-19 corpus. DISTNER provides a benchmark performance on the CORD-NER test set for future research. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining)
    null (Ed.)
    Mobility restrictions have been a primary intervention for controlling the spread of COVID-19, but they also 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 interactive dashboard that communicates our model's predictions for thousands of potential policies. 
    more » « less
  3. ; ; ; ; (, PLOS Computational Biology)
    Britton, Tom (Ed.)
    During pandemics, countries, regions, and communities develop various epidemic models to evaluate spread and guide mitigation policies. However, model uncertainties caused by complex transmission behaviors, contact-tracing networks, time-varying parameters, human factors, and limited data present significant challenges to model-based approaches. To address these issues, we propose a novel framework that centers around reproduction number estimates to perform counterfactual analysis, strategy evaluation, and feedback control of epidemics. The framework 1) introduces a mechanism to quantify the impact of the testing-for-isolation intervention strategy on the basic reproduction number. Building on this mechanism, the framework 2) proposes a method to reverse engineer the effective reproduction number under different strengths of the intervention strategy. In addition, based on the method that quantifies the impact of the testing-for-isolation strategy on the basic reproduction number, the framework 3) proposes a closed-loop control algorithm that uses the effective reproduction number both as feedback to indicate the severity of the spread and as the control goal to guide adjustments in the intensity of the intervention. We illustrate the framework, along with its three core methods, by addressing three key questions and validating its effectiveness using data collected during the COVID-19 pandemic at the University of Illinois Urbana-Champaign (UIUC) and Purdue University: 1) How severe would an outbreak have been without the implemented intervention strategies? 2) What impact would varying the intervention strength have had on an outbreak? 3) How can we adjust the intervention intensity based on the current state of an outbreak? 
    more » « less
  4. ; ; (, PLOS ONE)
    Alam, Mumtaz (Ed.)
    When COVID-19 was first introduced to the United States, state and local governments enacted a variety of policies intended to mitigate the virulence of the epidemic. At the time, the most effective measures to prevent the spread of COVID-19 included stay-at-home orders, closing of nonessential businesses, and mask mandates. Although it was well known that regions with high population density and cold climates were at the highest risk for disease spread, rural counties that are economically reliant on tourism were incentivized to enact fewer precautions against COVID-19. The uncertainty of the COVID-19 pandemic, the multiple policies to reduce transmission, and the changes in outdoor recreation behavior had a significant impact on rural tourism destinations and management of protected spaces. We utilize fine-scale incidence and demographic data to study the relationship between local economic and political concerns, COVID-19 mitigation measures, and the subsequent severity of outbreaks throughout the continental United States. We also present results from an online survey that measured travel behavior, health risk perceptions, knowledge and experience with COVID-19, and evaluation of destination attributes by 407 out-of-state visitors who traveled to Maine from 2020 to 2021. We synthesize this research to present a narrative on how perceptions of COVID-19 risk and public perceptions of rural tourism put certain communities at greater risk of illness throughout 2020. This research could inform future rural destination management and public health policies to help reduce negative socioeconomic, health and environmental impacts of pandemic-derived changes in travel and outdoor recreation behavior. 
    more » « less
  5. ; ; (, Networks and Heterogeneous Media)
    The COVID-19 pandemic highlighted the need to quickly respond, via public policy, to the onset of an infectious disease breakout. Deciding the type and level of interventions a population must consider to mitigate risk and keep the disease under control could mean saving thousands of lives. Many models were quickly introduced highlighting lockdowns, testing, contact tracing, travel policies, later on vaccination, and other intervention strategies along with costs of implementation. Here, we provided a framework for capturing population heterogeneity whose consideration may be crucial when developing a mitigation strategy based on non-pharmaceutical interventions. Precisely, we used age-stratified data to segment our population into groups with unique interactions that policy can affect such as school children or the oldest of the population, and formulated a corresponding optimal control problem considering the economic cost of lockdowns and deaths. We applied our model and numerical methods to census data for the state of New Jersey and determined the most important factors contributing to the cost and the optimal strategies to contained the pandemic impact. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email