Data-driven testing program improves detection of COVID-19 cases and reduces community transmission

Steven J. Krieg, Carolina Avendano, Evan Grantham-Brown, Aaron Lilienfeld Asbun, Jennifer J. Schnur, Marie Lynn Miranda, Nitesh V. Chawla

Introduction

During the COVID-19 pandemic, institutions like universities faced a critical challenge: identifying infected individuals before they could drive community transmission. Traditional methods, such as random surveillance testing, are resource-intensive and often miss asymptomatic cases. Conversely, manual contact tracing is frequently hampered by delays and the limitations of human memory. Researchers at the University of Notre Dame addressed this "needle in a haystack" problem by developing an "adaptive" testing program that leverages social network analysis and machine learning to proactively identify high-risk individuals.

Methodology

The researchers modeled the university population as a heterogeneous social network. In this model, students are nodes and edges represent administrative connections, including shared dorm rooms, floors, classes, and athletic teams. To predict risk, the team deployed an ensemble of two machine learning models:

  1. Node Risk (NR) Model: This model uses a risk propagation approach. When a student tests positive, their risk score is transmitted to neighbors in the social network. The weights for different connection types (e.g., roommate vs. classmate) were optimized using an evolutionary strategy.
  2. Link Prediction (LP) Model: This model estimates the probability of unobserved contact tracing relationships. By analyzing historical data and metrics like Katz centrality, it identifies likely close contacts that manual tracing might overlook.

These models were trained on a massive dataset from the 2020–2021 academic year, including over 145,000 test results and comprehensive administrative records.

Results

The adaptive testing program significantly outperformed random surveillance. The adaptive cohort demonstrated a positivity rate of 0.53%, compared to 0.37% in the general surveillance group. This advantage became even more pronounced over time; within a five-day window, the adaptive program's detection rate rose to 1.49%, a 122% increase over the 0.67% found via random testing.

Figure 5: Comparison of cumulative positivity rates between the adaptive cohort and general surveillance over a 14-day window.

Speed of intervention was another major benefit. The models identified close contacts in an average of 0.94 days from exposure, effectively halving the 1.92-day average required for manual contact tracing. This rapid identification allowed for earlier testing and isolation of potentially infectious individuals.

Figure 4: Cumulative percentage of close contacts tested over time, comparing those identified by the adaptive model versus those who were not.

Discussion and Insights

A key finding was the effectiveness of administrative data as a proxy for viral transmission paths. Even without direct biological or location data, class schedules and housing assignments provided a robust framework for predicting risk. Furthermore, the program benefited from a "nudge" effect: students flagged as high-risk had a 95% testing response rate, significantly higher than the 78% seen in general surveillance.

While the study was conducted in a specific university setting with a relatively homogeneous demographic, the results suggest that these models could be adapted for other infectious diseases or corporate environments using Enterprise Social Networks (ESNs). Future work will focus on accounting for inter-community transmission and refining the social graph to capture interactions not documented in administrative records.

Summary updated

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.
BibTeX
@article{krieg2022data,
  author = {Steven J. Krieg and Carolina Avendano and Evan Grantham-Brown and Aaron Lilienfeld Asbun and Jennifer J. Schnur and Marie Lynn Miranda and Nitesh V. Chawla},
  title = {{Data-driven testing program improves detection of COVID-19 cases and reduces community transmission}},
  journal = {Npj Digit. Medicine},
  year = {2022},
  doi = {10.1038/s41746-022-00562-4},
}
Figure