A Time Series Analysis and Predictive Modeling of COVID-19 Impacts in the African American Community

  1. Timothy Oladunni
  2. Sourou Tossou
  3. Max Denis
  4. Esther Ososanya
  5. Joseph Adesina

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Background

Sometimes in 2019, there was an outbreak of coronavirus pandemic. Data shows that the virus has infected millions of people and claimed thousands of lives. Vaccination and other non-pharmacological interventions have brought a relief; however, COVID-19 left some indelible marks. This work focuses on a time series analysis and prediction of COVID-19 fatality rates in the Black community. Decision makers will find the work useful in building a robust architecture for a resilient pandemic preparedness and responsiveness against the next pandemic. Method: Our analysis of COVID-19 cases and deaths spans March 2020 to December 2020. Assuming there was no vaccine and other factors remained the same, we hypothesized that COVID-19 disproportionality would have continued. To test our hypothesis, COVID-19 forecasting cases and deaths models were built for the total population as well as the Black population. Holt and Holt-Winters exponential smoothing forecast methodologies were used for the forecast modeling. Forecasting accuracy was based on Mean Absolute Percentage Error (MAPE). Furthermore, we designed, developed, and evaluated a fatality rate predictive model for a Black county. Considering the number of ethnic groups in the USA, a Black county was defined as any county in the USA that at least 45% of its population are Blacks. Five learning algorithms were trained and evaluated. Dataset was a merger of datasets obtained from John Hopkins COVID-19 repository, US Census Bureau and US Center for Disease Control and Prevention.

Results and Conclusion

Time series analysis shows that there exists a strong evidence of COVID-19 disproportionate impacts in the states investigated. Using 9 different criteria for performance comparison, our predictive modeling showed that decision tree model has a slight edge over other models. Our experiment suggests that Blacks and senior citizens with pre-existing condition living in Georgia State are the most vulnerable to COVID-19.

Article activity feed

  1. Version published to 10.1101/2021.05.13.21257189v3 on medRxiv
  2. Version published to 10.1101/2021.05.13.21257189v2 on medRxiv
  3. ScreenIT

    SciScore for 10.1101/2021.05.13.21257189: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    Ethicsnot detected.
    Sex as a biological variablenot detected.
    Randomizationnot detected.
    Blindingnot detected.
    Power Analysisnot detected.

    Table 2: Resources

    No key resources detected.

    Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    Results from scite Reference Check: We found no unreliable references.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  4. Version published to 10.1101/2021.05.13.21257189v1 on medRxiv