Predicting increases in COVID-19 incidence to identify locations for targeted testing in West Virginia: A machine learning enhanced approach

Factors Associated With Surveillance Testing in Individuals With COVID-19 Symptoms During the Last Leg of the Pandemic: Multivariable Regression Analysis

Background

Rural underserved areas facing health disparities have unequal access to health resources. By the third and fourth waves of SARS-CoV-2 infections in the United States, COVID-19 testing had reduced, with more reliance on home testing, and those seeking testing were mostly symptomatic.

Objective

This study identifies factors associated with COVID-19 testing among individuals who were symptomatic versus asymptomatic seen at a Rapid Acceleration of Diagnostics for Underserved Populations phase 2 (RADx-UP2) testing site in West Virginia.

Methods

Demographic, clinical, and behavioral factors were collected via survey from tested individuals. Logistic regression was used to identify factors associated with the presence of individuals who were symptomatic seen at testing sites. Global tests for spatial autocorrelation were conducted to examine clustering in the proportion of symptomatic to total individuals tested by zip code. Bivariate maps were created to display geographic distributions between higher proportions of tested individuals who were symptomatic and social determinants of health.

Results

Among predictors, the presence of a physical (adjusted odds ratio [aOR] 1.85, 95% CI 1.3-2.65) or mental (aOR 1.53, 95% CI 0.96-2.48) comorbid condition, challenges related to a place to stay/live (aOR 307.13, 95% CI 1.46-10,6372), no community socioeconomic distress (aOR 0.99, 95% CI 0.98-1.00), no challenges in getting needed medicine (aOR 0.01, 95% CI 0.00-0.82) or transportation (aOR 0.23, 95% CI 0.05-0.64), an interaction between community socioeconomic distress and not getting needed medicine (aOR 1.06, 95% CI 1.00-1.13), and having no community socioeconomic distress while not facing challenges related to a place to stay/live (aOR 0.93, 95% CI 0.87-0.99) were statistically associated with an individual being symptomatic at the first test visit.

Conclusions

This study addresses critical limitations to the current COVID-19 testing literature, which almost exclusively uses population-level disease screening data to inform public health responses.

Enhanced SARS-CoV-2 case prediction using public health data and machine learning models

Objectives

The goal of this study is to propose and test a scalable framework for machine learning (ML) algorithms to predict near-term severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) cases by incorporating and evaluating the impact of real-time dynamic public health data.

Materials and Methods

Data used in this study include patient-level results, procurement, and location information of all SARS-CoV-2 tests reported in West Virginia as part of their mandatory reporting system from January 2021 to March 2022. We propose a method for incorporating and comparing widely available public health metrics inside of a ML framework, specifically a long-short-term memory network, to forecast SARS-CoV-2 cases across various feature sets.

Results

Our approach provides better prediction of localized case counts and indicates the impact of the dynamic elements of the pandemic on predictions, such as the influence of the mixture of viral variants in the population and variable testing and vaccination rates during various eras of the pandemic.

Discussion

Utilizing real-time public health metrics, including estimated Rt from multiple SARS-CoV-2 variants, vaccination rates, and testing information, provided a significant increase in the accuracy of the model during the Omicron and Delta period, thus providing more precise forecasting of daily case counts at the county level. This work provides insights on the influence of various features on predictive performance in rural and non-rural areas.

Conclusion

Our proposed framework incorporates available public health metrics with operational data on the impact of testing, vaccination, and current viral variant mixtures in the population to provide a foundation for combining dynamic public health metrics and ML models to deliver forecasting and insights in healthcare domains. It also shows the importance of developing and deploying ML frameworks in rural settings.

If you build it, will they come? Is test site availability a root cause of geographic disparities in COVID-19 testing?

OBJECTIVES

The purpose of this study was to examine the relationship between test site availability and testing rate within the context of social determinants of health.

STUDY DESIGN

A retrospective ecological investigation was conducted using statewide COVID-19 testing data between March 2020 and December 2021.

METHODS

Ordinary least squares and geographically weighted regression were used to estimate state and ZIP code level associations between testing rate and testing sites per capita, adjusting for neighbourhood-level confounders.

RESULTS

The findings indicate that site availability is positively associated with the ZIP code level testing rate and that this association is amplified in communities of greater economic deprivation. In addition, economic deprivation is a key factor for consideration when examining ethnic differences in testing in medically underserved states.

CONCLUSION

The study findings could be used to guide the delivery of testing facilities in resource-constrained states.

Novel Strategies to Increase COVID-19 Testing Among Underserved and Vulnerable Populations in West Virginia

This project addressed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) testing barriers in rural West Virginia by providing testing enhancements that included (1) a flexible testing staff, (2) mobile testing, (3) essential supplies, and (4) specialized testing in communities of color. A total of 142 775 polymerase chain reaction tests were performed from December 2021 through February 2022; positivity rates were 21% and 17% in clinics and mobile testing venues, respectively. The project results showed that, within a statewide network of health care clinics, administrators quickly identified and distributed enhancements and thus reduced testing barriers. (Am J Public Health. 2022;112(S9):S892-S895. https://doi.org/10.2105/AJPH.2022.307004).