A method for intelligent allocation of diagnostic testing by leveraging data from commercial wearable devices: a case study on COVID-19
Md Mobashir Hasan Shandhi, Peter J Cho, Ali R Roghanizad, Karnika Singh, Will Wang, Oana M Enache, Amanda Stern, Rami Sbahi, Bilge Tatar, Sean Fiscus, Qi Xuan Khoo, Yvonne Kuo, Xiao Lu, Joseph Hsieh, Alena Kalodzitsa, Amir Bahmani, Arash Alavi, Utsab Ray, Michael P Snyder, Geoffrey S Ginsburg, Dana K Pasquale, Christopher W Woods, Ryan J Shaw, Jessilyn P Dunn, Md Mobashir Hasan Shandhi, Peter J Cho, Ali R Roghanizad, Karnika Singh, Will Wang, Oana M Enache, Amanda Stern, Rami Sbahi, Bilge Tatar, Sean Fiscus, Qi Xuan Khoo, Yvonne Kuo, Xiao Lu, Joseph Hsieh, Alena Kalodzitsa, Amir Bahmani, Arash Alavi, Utsab Ray, Michael P Snyder, Geoffrey S Ginsburg, Dana K Pasquale, Christopher W Woods, Ryan J Shaw, Jessilyn P Dunn
Abstract
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.
Conflict of interest statement
J.P.D. is an Associate Editor of npj Digital Medicine. M.M.H.S is an Editorial Board Member of npj Digital Medicine. J.P.D. is on the scientific advisory board of Human Engineering Health Oy and is a consultant for ACI Gold Track. C.W.W. is a founder of Predigen that is merged with Biomeme. He is also on the scientific advisory board of Biomeme/Predigen, FHI Clinical, IDbyDNA, Regeneron, and Roche Molecular Sciences. He is also a consultant for bioMerieux/Biofire, Domus, Karius, Steradian, and SeLux Diagnostics. He is also on the data and safety monitoring board of Bavarian Nordic and Janssen. M.P.S. is a co-founder and member of the scientific advisory board of Personalis, Qbio, January, SensOmics, Protos, Mirvie, NiMo, Onza, and Oralome. He is also on the scientific advisory board of Danaher, Genapsys, and Jupiter. Other authors declare no competing interests.
© 2022. The Author(s).
Figures
References
- COVID Live. Coronavirus Statistics – Worldometer. (2022).
- United States COVID. Coronavirus Statistics – Worldometer. (2022).
- Moghadas SM, et al. The implications of silent transmission for the control of COVID-19 outbreaks. Proc. Natl Acad. Sci. USA. 2020;117:17513–17515. doi: 10.1073/pnas.2008373117.
- Why pretest and posttest probability matter in the time of COVID-19. (2020).
- Stolberg, S. G. & LaFraniere, S. With Omicron, U.S. testing capacity faces intense pressure. The New York Times (2021).
- Reports of price gouging amid shortages of COVID-19 tests. (2022).
- O’donnell, C. U.S. COVID-19 tests again in short supply as infections soar, schools reopen. Reuters (2021).
- Omicron testing shortages and delays are making results useless—and deepening COVID inequality. Fortune (2022).
- Heilweil, R. How omicron broke COVID-19 testing. Vox (2021).
- More coronavirus tests will be available next month, Fauci says, as U.S. struggles with shortage. Washington Post (2021).
- Huang, P. There has been a shortage of testing and vaccines for Monkeypox. NPR (2022).
- Perspective | Testing failures helped covid spread. We must do better with monkeypox. Washington Post (2022).
- Rader B, et al. Geographic access to United States SARS-CoV-2 testing sites highlights healthcare disparities and may bias transmission estimates. J. Travel Med. 2020;27:taaa076. doi: 10.1093/jtm/taaa076.
- Souch JM, Cossman JS. A commentary on rural-urban disparities in COVID-19 testing rates per 100,000 and risk factors. J. Rural Health. 2021;37:188–190. doi: 10.1111/jrh.12450.
- New surgo analysis identifies highly vulnerable rural communities as COVID-19 testing deserts. Surgo Ventures (2022).
- Kannoth S, Kandula S, Shaman J. The association between early country-level COVID-19 testing capacity and later COVID-19 mortality outcomes. Influenza Other Respir. Viruses. 2022;16:56–62. doi: 10.1111/irv.12906.
- CDC. Community, work, and school. Centers for Disease Control and Prevention (2020).
- Meirom, E., Maron, H., Mannor, S. & Chechik, G. Controlling graph dynamics with reinforcement learning and graph neural networks. in Proceedings of the 38th International Conference on Machine Learning 7565–7577 (PMLR, 2021).
- Du J, et al. Optimal diagnostic test allocation strategy during the COVID-19 pandemic and beyond. Stat. Med. 2022;41:310–327. doi: 10.1002/sim.9238.
- Radin JM, Wineinger NE, Topol EJ, Steinhubl SR. Harnessing wearable device data to improve state-level real-time surveillance of influenza-like illness in the USA: a population-based study. Lancet Digit. Health. 2020;2:e85–e93. doi: 10.1016/S2589-7500(19)30222-5.
- Li X, et al. Digital health: tracking physiomes and activity using wearable biosensors reveals useful health-related information. PLoS Biol. 2017;15:e2001402. doi: 10.1371/journal.pbio.2001402.
- Shapiro A, et al. Characterizing COVID-19 and influenza illnesses in the real world via person-generated health data. Patterns. 2021;2:100188. doi: 10.1016/j.patter.2020.100188.
- Mishra T, et al. Pre-symptomatic detection of COVID-19 from smartwatch data. Nat. Biomed. Eng. 2020;4:1208–1220. doi: 10.1038/s41551-020-00640-6.
- Quer G, et al. Wearable sensor data and self-reported symptoms for COVID-19 detection. Nat. Med. 2021;27:73–77. doi: 10.1038/s41591-020-1123-x.
- Miller DJ, et al. Analyzing changes in respiratory rate to predict the risk of COVID-19 infection. PloS One. 2020;15:e0243693. doi: 10.1371/journal.pone.0243693.
- Grzesiak E, et al. Assessment of the feasibility of using noninvasive wearable biometric monitoring sensors to detect influenza and the common cold before symptom onset. JAMA Netw. Open. 2021;4:e2128534. doi: 10.1001/jamanetworkopen.2021.28534.
- Alavi, A. et al. Real-time alerting system for COVID-19 and other stress events using wearable data. Nat. Med. 28, 175–184. 10.1038/s41591-021-01593-2 (2022).
- Harris PA, et al. Research Electronic Data Capture (REDCap) – a metadata-driven methodology and workflow process for providing translational research informatics support. J. Biomed. Inform. 2009;42:377–381. doi: 10.1016/j.jbi.2008.08.010.
- Rapeport G, et al. SARS-CoV-2 human challenge studies—establishing the model during an evolving pandemic. N. Engl. J. Med. 2021;385:961–964. doi: 10.1056/NEJMp2106970.
- CDC. COVID-19 and your health. Centers for Disease Control and Prevention (2020).
- Radin JM, et al. Assessment of prolonged physiological and behavioral changes associated with COVID-19 infection. JAMA Netw. Open. 2021;4:e2115959. doi: 10.1001/jamanetworkopen.2021.15959.
- Krzywinski M, Altman N. Error bars. Nat. Methods. 2013;10:921–922. doi: 10.1038/nmeth.2659.
- Bradley AP. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 1997;30:1145–1159. doi: 10.1016/S0031-3203(96)00142-2.
- Gadaleta M, et al. Passive detection of COVID-19 with wearable sensors and explainable machine learning algorithms. Npj Digit. Med. 2021;4:1–10. doi: 10.1038/s41746-021-00533-1.
- Mason AE, et al. Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study. Sci. Rep. 2022;12:3463. doi: 10.1038/s41598-022-07314-0.
- Conroy B, et al. Real-time infection prediction with wearable physiological monitoring and AI to aid military workforce readiness during COVID-19. Sci. Rep. 2022;12:3797. doi: 10.1038/s41598-022-07764-6.
- Natarajan A, Su H-W, Heneghan C. Assessment of physiological signs associated with COVID-19 measured using wearable devices. Npj Digit. Med. 2020;3:1–8. doi: 10.1038/s41746-020-00363-7.
- Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One. 2015;10:e0118432. doi: 10.1371/journal.pone.0118432.
- Davis, J. & Goadrich, M. The relationship between precision-recall and ROC curves. in Proceedings of the 23rd international conference on Machine learning – ICML ’06 233–240 (ACM Press, 2006). 10.1145/1143844.1143874.
- Lever J, Krzywinski M, Altman N. Model selection and overfitting. Nat. Methods. 2016;13:703–704. doi: 10.1038/nmeth.3968.
- Institute of Medicine (US) Council on Health Care Technology; Sox, H., Stern, S., Owens, D. & Abrams, H. L. in The Use of Diagnostic Tests: A Probabilistic Approach. Assessment of Diagnostic Technology in Health Care: Rationale, Methods, Problems, and Directions: Monograph of the Council on Health Care Technology (National Academies Press (US), 1989).
- Frequently Asked Questions (FAQs). . (2020).
- Watson J, Whiting PF, Brush JE. Interpreting a COVID-19 test result. BMJ. 2020;369:m1808. doi: 10.1136/bmj.m1808.
- Gubbay, J. B. et al. Impact of coronavirus disease 2019 (COVID-19) pre-test probability on positive predictive value of high cycle threshold severe acute respiratory coronavirus virus 2 (SARS-CoV-2) real-time reverse transcription polymerase chain reaction (RT-PCR) test results. Infect. Control Hosp. Epidemiol. 1–5 10.1017/ice.2021.369 (2021).
- Cho, P. J. et al. Demographic Imbalances Resulting From the Bring-Your-Own-Device Study Design. JMIR Mhealth Uhealth10, e29510 (2022).
- Vogels, E. A. Digital divide persists even as Americans with lower incomes make gains in tech adoption. Pew Research Center (2021).
- Vogels, E. A. Some digital divides persist between rural, urban and suburban America. Pew Research Center (2021).
- Macridis S, Johnston N, Johnson S, Vallance JK. Consumer physical activity tracking device ownership and use among a population-based sample of adults. PLoS One. 2018;13:e0189298. doi: 10.1371/journal.pone.0189298.
- Guk K, et al. Evolution of wearable devices with real-time disease monitoring for personalized healthcare. Nanomaterials. 2019;9:813. doi: 10.3390/nano9060813.
- Demographics of mobile device ownership and adoption in the United States. Pew Research Center: Internet, Science & Tech (2021).
- Silver, L. Smartphone ownership is growing rapidly around the world, but not always equally. Pew Research Center’s Global Attitudes Project (2019).
- U.S. Census Bureau QuickFacts: United States. (2020).
- CDC. COVIDView, Key Updates for Week 23. Centers for Disease Control and Prevention (2020).
- Uddin S, Khan A, Hossain ME, Moni MA. Comparing different supervised machine learning algorithms for disease prediction. BMC Med. Inform. Decis. Mak. 2019;19:281. doi: 10.1186/s12911-019-1004-8.
- Deo RC. Machine learning in medicine. Circulation. 2015;132:1920–1930. doi: 10.1161/CIRCULATIONAHA.115.001593.
- Cawley, G. C. & Talbot, N. L. C. On over-fitting in model selection and subsequent selection bias in performance evaluation. J Mach Learn Res.11, 2079–2107 (2010).
- Varma S, Simon R. Bias in error estimation when using cross-validation for model selection. BMC Bioinforma. 2006;7:91. doi: 10.1186/1471-2105-7-91.
Source: PubMed