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: Artificial Neural Network Prediction of COVID-19 Daily Infection Count
This study addresses COVID-19 testing as a nonlinear sampling problem, aiming to uncover the dependence of the true infection count in the population on COVID-19 testing metrics such as testing volume and positivity rates. Employing an artificial neural network, we explore the relationship among daily confirmed case counts, testing data, population statistics, and the actual daily case count. The trained artificial neural network undergoes testing in in-sample, out-of-sample, and several hypothetical scenarios. A substantial focus of this paper lies in the estimation of the daily true case count, which serves as the output set of our training process. To achieve this, we implement a regularized backcasting technique that utilizes death counts and the infection fatality ratio (IFR), as the death statistics and serological surveys (providing the IFR) as more reliable COVID-19 data sources. Addressing the impact of factors such as age distribution, vaccination, and emerging variants on the IFR time series is a pivotal aspect of our analysis. We expect our study to enhance our understanding of the genuine implications of the COVID-19 pandemic, subsequently benefiting mitigation strategies.  more » « less
Award ID(s):
2108628
PAR ID:
10532549
Author(s) / Creator(s):
; ;
Publisher / Repository:
Springer Nature
Date Published:
Journal Name:
Bulletin of Mathematical Biology
Volume:
86
Issue:
5
ISSN:
0092-8240
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, Journal of Infection and Public Health)
    Background: Estimating the infection fatality rate (IFR) for emerging diseases is elusive due to the presence of asymptomatic or mildly symptomatic infections and variable testing capacity. IFR estimates are also affected by region-specific differences in sampling regimes, demographics, and healthcare resources. Methods: Here we present a novel regression approach using population testing and readily available case fatality rates (CFR) to estimate the IFR during an outbreak. The approach is based on few assumptions and can be used for a wide range of emerging diseases. We validate the use of the method using commonly reported COVID-19 testing data. Results: Our new statistical approach reveals a conservative global IFR of 0.90 % (CI: 0.70 %, 1.16 %) for COVID-19 across the 139 countries affected before May 2020. Deviation of countries’ reported CFR from the estimator did not correlate with demography, per capita GDP, or healthcare access and quality, suggesting variation is due to differing testing regimes or reporting guidelines by country. Conclusions: This method can be used retrospectively or for future disease outbreaks when other data are limited. 
    more » « less
  2. ; ; ; (, 2020 International Conference on Computational Science and Computational Intelligence (CSCI))
    There is growing concern that racial and ethnic minority communities around the United States are experiencing a disproportionate burden of infection rate and mortality from the coronavirus disease 2019 (Covid-19). While most research, media newspapers, websites, and television networks are providing statistical numbers of daily infection and death rate across US by state, these numbers fail to study the actual impact of COVID-19 to each race. Our approach has taken the top five races by population count in the US and has calculated the impact index by race for each state for COVID-19 infections and death rate. We also examine the rise in the utilization of hospitals as a result of the rise in cases of COVID-19 in the United states. We conclude that the African American race and Hispanic race is disproportionately impacted more than the white population for infection rate. 
    more » « less
  3. ; ; (, Royal Society Open Science)
    Each state in the USA exhibited a unique response to the COVID-19 outbreak, along with variable levels of testing, leading to different actual case burdens in the country. In this study, via per capita testing dependent ascertainment rates, along with case and death data, we fit a minimal epidemic model for each state. We estimate infection-level responsive lockdown/self-quarantine entry and exit rates (representing government and behavioural reaction), along with the true number of cases as of 31 May 2020. Ultimately, we provide error-corrected estimates for commonly used metrics such as infection fatality ratio and overall case ascertainment for all 55 states and territories considered, along with the USA in aggregate, in order to correlate outbreak severity with first wave intervention attributes and suggest potential management strategies for future outbreaks. We observe a theoretically predicted inverse proportionality relation between outbreak size and lockdown rate, with scale dependent on the underlying reproduction number and simulations suggesting a critical population quarantine ‘half-life’ of 30 days independent of other model parameters. 
    more » « less
  4. ; ; (, Proceedings of the International AAAI Conference on Web and Social Media)
    During the COVID-19 pandemic, local news organizations have played an important role in keeping communities informed about the spread and impact of the virus. We explore how political, social media, and economic factors impacted the way local media reported on COVID-19 developments at a national scale between January 2020 and July 2021. We construct and make available a dataset of over 10,000 local news organizations and their social media handles across the U.S. We use social media data to estimate the population reach of outlets (their “localness”), and capture underlying content relationships between them. Building on this data, we analyze how local and national media covered four key COVID-19 news topics: Statistics and Case Counts, Vaccines and Testing, Public Health Guidelines, and Economic Effects. Our results show that news outlets with higher population reach reported proportionally more on COVID-19 than more local outlets. Separating the analysis by topic, we expose more nuanced trends, for example that outlets with a smaller population reach covered the Statistics and Case Counts topic proportionally more, and the Economic Effects topic proportionally less. Our analysis further shows that people engaged proportionally more and used stronger reactions when COVID-19 news were posted by outlets with a smaller population reach. Finally, we demonstrate that COVID-19 posts in Republican-leaning counties generally received more comments and fewer likes than in Democratic counties, perhaps indicating controversy. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; (, COVID)
    The strategy of relying solely on current SARS-CoV-2 vaccines to halt SARS-CoV-2 transmission has proven infeasible. In response, many public-health authorities have advocated for using vaccines to limit mortality while permitting unchecked SARS-CoV-2 spread (“learning to live with the disease”). The feasibility of this strategy critically depends on the infection fatality rate (IFR) of SARS-CoV-2. An expectation exists that the IFR will decrease due to selection against virulence. In this work, we perform a viral fitness estimation to examine the basis for this expectation. Our findings suggest large increases in virulence for SARS-CoV-2 would result in minimal loss of transmissibility, implying that the IFR may vary freely under neutral evolutionary drift. We use an SEIRS model framework to examine the effect of hypothetical changes in the IFR on steady-state death tolls under COVID-19 endemicity. Our modeling suggests that endemic SARS-CoV-2 implies vast transmission resulting in yearly US COVID-19 death tolls numbering in the hundreds of thousands under many plausible scenarios, with even modest increases in the IFR leading to unsustainable mortality burdens. Our findings highlight the importance of enacting a concerted strategy and continued development of biomedical interventions to suppress SARS-CoV-2 transmission and slow its evolution. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email