Precision recruitment for high-risk participants in a COVID-19 cohort study

Abstract

Background: Studies for developing diagnostics and treatments for infectious diseases usually require observing the onset of infection during the study period. However, when the infection base rate incidence is low, the cohort size required to measure an effect becomes large, and recruitment becomes costly and prolonged. We developed a model for reducing recruiting time and resources in a COVID-19 detection study by targeting recruitment to high-risk individuals.

Methods: We conducted an observational longitudinal cohort study at individual sites throughout the U.S., enrolling adults who were members of an online health and research platform. Through direct and longitudinal connection with research participants, we applied machine learning techniques to compute individual risk scores from individually permissioned data about socioeconomic and behavioral data, in combination with predicted local prevalence data. The modeled risk scores were then used to target candidates for enrollment in a hypothetical COVID-19 detection study. The main outcome measure was the incidence rate of COVID-19 according to the risk model compared with incidence rates in actual vaccine trials.

Results: When we used risk scores from 66,040 participants to recruit a balanced cohort of participants for a COVID-19 detection study, we obtained a 4- to 7-fold greater COVID-19 infection incidence rate compared with similar real-world study cohorts.

Conclusion: This risk model offers the possibility of reducing costs, increasing the power of analyses, and shortening study periods by targeting for recruitment participants at higher risk.

Keywords: CDC, Centers for Disease Control and Prevention; COVID-19; Clinical trials; GAMs, generalized additive models; Risk modeling.

Fig. 1

Covid-19 incidence rate in each cohort normalized by US incidence rate matched for time, age, and sex.

Fig. 2

The 20 Most Important Groups of Predictors of Risk Ranked by Random Forest Feature Importance. Sub-predictors from the same group (e.g., Healthcare occupation) have been separated and rearranged for visual clarity. Positive coefficients that are statistically significant (risk increasing) are in blue, and negative ones are in orange. More detailed descriptions of each factor and variable are available in the Appendix. (For interpretation of the references to colour in this figure legend, the reader is referred to the Web version of this article.)