A method for intelligent allocation of diagnostic testing by leveraging data from commercial wearable devices: a case study on COVID-19

Mass surveillance testing can help control outbreaks of infectious diseases such as COVID-19. However, diagnostic test shortages are prevalent globally and continue to occur in the US with the onset of new COVID-19 variants and emerging diseases like monkeypox, demonstrating an unprecedented need for improving our current methods for mass surveillance testing. By targeting surveillance testing toward individuals who are most likely to be infected and, thus, increasing the testing positivity rate (i.e., percent positive in the surveillance group), fewer tests are needed to capture the same number of positive cases. Here, we developed an Intelligent Testing Allocation (ITA) method by leveraging data from the CovIdentify study (6765 participants) and the MyPHD study (8580 participants), including smartwatch data from 1265 individuals of whom 126 tested positive for COVID-19. Our rigorous model and parameter search uncovered the optimal time periods and aggregate metrics for monitoring continuous digital biomarkers to increase the positivity rate of COVID-19 diagnostic testing. We found that resting heart rate (RHR) features distinguished between COVID-19-positive and -negative cases earlier in the course of the infection than steps features, as early as 10 and 5 days prior to the diagnostic test, respectively. We also found that including steps features increased the area under the receiver operating characteristic curve (AUC-ROC) by 7–11% when compared with RHR features alone, while including RHR features improved the AUC of the ITA model’s precision-recall curve (AUC-PR) by 38–50% when compared with steps features alone. The best AUC-ROC (0.73 ± 0.14 and 0.77 on the cross-validated training set and independent test set, respectively) and AUC-PR (0.55 ± 0.21 and 0.24) were achieved by using data from a single device type (Fitbit) with high-resolution (minute-level) data. Finally, we show that ITA generates up to a 6.5-fold increase in the positivity rate in the cross-validated training set and up to a 4.5-fold increase in the positivity rate in the independent test set, including both symptomatic and asymptomatic (up to 27%) individuals. Our findings suggest that, if deployed on a large scale and without needing self-reported symptoms, the ITA method could improve the allocation of diagnostic testing resources and reduce the burden of test shortages.

For Apple users, see https://www.apple.com/privacy/For Fitbit users, see https://www.fitbit.com/legal/privacy-policyFor Garmin users, see https://www.garmin.com/en-US/privacy/connect/For Fitbit, Garmin, and Android users, we will ask you to provide an email address and cell phone number associated with these devices which we will store securely.
We do not collect GPS data or real-time location data.You have the option of telling us your address, and this information will be used by Duke researchers to understand the spread of COVID-19 over time, and how location corresponds to risk of infection.

VOLUNTARY NATURE OF PARTICIPATION
Participation in this study is voluntary.You can choose not to participate at any point and may withdraw at any time.Please opt-out from communications or delete the CovIdentify app and notify the study staff if you wish to withdraw.After withdrawal, Covidentify will no longer obtain further information from you, but still has permission to use the information collected previously.

CONTACT FOR FUTURE STUDIES
The information we obtain in this study may be used again in future research related to Covidentify.Please check the box if you wish to be re-contacted for future research opportunities.{[consent7] radio} {1} Please re-contact me about future research opportunities such as the impact of the pandemic on autoimmune disease, risk factors such as diabetes or hypertension, or the use of wearable devices.

WHOM DO I CALL IF I HAVE QUESTIONS OR PROBLEMS?
For questions about the study, please contact the study team at covidentify@duke.edu or Dr. Jessilyn Dunn at 919-668-9798 during regular business hours.For questions about your rights as a participant in this research study, contact the Duke Campus IRB at 919-684-3030 or campusirb@duke.edu.

STATEMENT OF CONSENT
If you live in or are traveling in specific regions of Europe (the European Economic Area, or EEA), you are subject to additional data protection laws called "General Data Protection Regulations" (GDPR).To participate in our study, you must check the box below.By checking the box, you give us permission to collect and process your sensitive personal data while you are in the EEA, as well as transfer your data to the United States.
If you are in or travel to the EEA during this study, we are required to inform you that sensitive personal data about you, including racial or ethnic origin, genetic or biometric information, and health information, will be collected.

{
read the consent form and I wish to participate in the study AND I consent to the collection and transfer of my personal data, including my sensitive personal data, if I am traveling to or living in the EEA during the course of this study If you agree to take part in the study, please sign and date below.{Branching logic (show if):

Did you have any symptoms that you believe were caused by the first dose?
03/18/2022 11:11am projectredcap.org

Did you have any symptoms that you believe were caused by the second dose?
What was the date of the second dose?{[covid_second_shot_date] text date_mdy} __________________________________ {Branching logic (show if): [covid_second_shot] = '1'}