Abstract
COVID-19 remains a global threat in the face of emerging SARS-CoV-2 variants and gaps in vaccine administration and availability. In this study, we analyze a data-driven COVID-19 testing program implemented at a mid-sized university, which utilized two simple, diverse, and easily interpretable machine learning models to predict which students were at elevated risk and should be tested. The program produced a positivity rate of 0.53% (95% CI 0.34–0.77%) from 20,862 tests, with 1.49% (95% CI 1.15–1.89%) of students testing positive within five days of the initial test—a significant increase from the general surveillance baseline, which produced a positivity rate of 0.37% (95% CI 0.28–0.47%) with 0.67% (95% CI 0.55–0.81%) testing positive within five days. Close contacts who were predicted by the data-driven models were tested much more quickly on average (0.94 days from reported exposure; 95% CI 0.78–1.11) than those who were manually contact traced (1.92 days; 95% CI 1.81–2.02). We further discuss how other universities, business, and organizations could adopt similar strategies to help quickly identify positive cases and reduce community transmission.
Highlights
COVID-19 remains a global threat in the face of emerging SARS-CoV-2 variants and gaps in vaccine administration and availability
The adaptive testing program utilized two different, data-driven network models to quickly and accurately predict which students had an elevated risk of contracting COVID-19 and should be called proactively for testing
The adaptive testing program was one of many COVID-19 mitigation strategies implemented throughout the 2020–21 academic year at the University of Notre Dame[7]
Summary
COVID-19 remains a global threat in the face of emerging SARS-CoV-2 variants and gaps in vaccine administration and availability. The key difference between the two lies in the problem formulation: the first model was trained for a node-level task (classifying students as high-risk or low-risk using prior COVID-19 test results as training data), while the second was trained for an edgelevel task (predicting contact tracing relationships between students using contact tracing records from the previous semester as training data) While both models operated within the same social network, the difference in model inputs and optimization strategy resulted in models that were diverse and complementary, able to identify highrisk individuals within the campus network while reducing the overhead of manual contact tracing. A targeted and data-driven adaptive testing program was initiated on March 3, 2021 to supplement general surveillance testing, manual contact tracing, quarantine/isolation protocols, and self-reported health checks with more targeted and data-driven testing
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.