Cargando…

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, demonstrating an unprecedented need for improving our current methods for m...

Descripción completa

Detalles Bibliográficos
Autores principales: Dunn, Jessilyn, Shandhi, Mobashir Hasan, Cho, Peter, Roghanizad, Ali, Singh, Karnika, Wang, Will, Enache, Oana, Stern, Amanda, Sbahi, Rami, Tatar, Bilge, Fiscus, Sean, Khoo, Qi Xuan, Kuo, Yvonne, Lu, Xiao, Hsieh, Joseph, Kalodzitsa, Alena, Bahmani, Amir, Alavi, Arash, Ray, Utsab, Snyder, Michael, Ginsburg, Geoffrey, Pasquale, Dana, Woods, Christopher, Shaw, Ryan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Journal Experts 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8978951/
https://www.ncbi.nlm.nih.gov/pubmed/35378754
http://dx.doi.org/10.21203/rs.3.rs-1490524/v1
_version_ 1784681067321491456
author Dunn, Jessilyn
Shandhi, Mobashir Hasan
Cho, Peter
Roghanizad, Ali
Singh, Karnika
Wang, Will
Enache, Oana
Stern, Amanda
Sbahi, Rami
Tatar, Bilge
Fiscus, Sean
Khoo, Qi Xuan
Kuo, Yvonne
Lu, Xiao
Hsieh, Joseph
Kalodzitsa, Alena
Bahmani, Amir
Alavi, Arash
Ray, Utsab
Snyder, Michael
Ginsburg, Geoffrey
Pasquale, Dana
Woods, Christopher
Shaw, Ryan
author_facet Dunn, Jessilyn
Shandhi, Mobashir Hasan
Cho, Peter
Roghanizad, Ali
Singh, Karnika
Wang, Will
Enache, Oana
Stern, Amanda
Sbahi, Rami
Tatar, Bilge
Fiscus, Sean
Khoo, Qi Xuan
Kuo, Yvonne
Lu, Xiao
Hsieh, Joseph
Kalodzitsa, Alena
Bahmani, Amir
Alavi, Arash
Ray, Utsab
Snyder, Michael
Ginsburg, Geoffrey
Pasquale, Dana
Woods, Christopher
Shaw, Ryan
author_sort Dunn, Jessilyn
collection PubMed
description 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, demonstrating an unprecedented need for improving our current methods for mass surveillance testing. By targeting surveillance testing towards individuals who are most likely to be infected and, thus, increasing 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 (6,765 participants) and the MyPHD study (8,580 participants), including smartwatch data from 1,265 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 features distinguished between COVID-19 positive and negative cases earlier in the course of the infection than steps features, as early as ten and five 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 3-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 allocation of diagnostic testing resources and reduce the burden of test shortages.
format Online
Article
Text
id pubmed-8978951
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher American Journal Experts
record_format MEDLINE/PubMed
spelling pubmed-89789512022-04-05 A Method for Intelligent Allocation of Diagnostic Testing by Leveraging Data from Commercial Wearable Devices: A Case Study on COVID-19 Dunn, Jessilyn Shandhi, Mobashir Hasan Cho, Peter Roghanizad, Ali Singh, Karnika Wang, Will Enache, Oana Stern, Amanda Sbahi, Rami Tatar, Bilge Fiscus, Sean Khoo, Qi Xuan Kuo, Yvonne Lu, Xiao Hsieh, Joseph Kalodzitsa, Alena Bahmani, Amir Alavi, Arash Ray, Utsab Snyder, Michael Ginsburg, Geoffrey Pasquale, Dana Woods, Christopher Shaw, Ryan Res Sq Article 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, demonstrating an unprecedented need for improving our current methods for mass surveillance testing. By targeting surveillance testing towards individuals who are most likely to be infected and, thus, increasing 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 (6,765 participants) and the MyPHD study (8,580 participants), including smartwatch data from 1,265 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 features distinguished between COVID-19 positive and negative cases earlier in the course of the infection than steps features, as early as ten and five 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 3-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 allocation of diagnostic testing resources and reduce the burden of test shortages. American Journal Experts 2022-04-01 /pmc/articles/PMC8978951/ /pubmed/35378754 http://dx.doi.org/10.21203/rs.3.rs-1490524/v1 Text en https://creativecommons.org/licenses/by/4.0/This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/) , which allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator. The license allows for commercial use.
spellingShingle Article
Dunn, Jessilyn
Shandhi, Mobashir Hasan
Cho, Peter
Roghanizad, Ali
Singh, Karnika
Wang, Will
Enache, Oana
Stern, Amanda
Sbahi, Rami
Tatar, Bilge
Fiscus, Sean
Khoo, Qi Xuan
Kuo, Yvonne
Lu, Xiao
Hsieh, Joseph
Kalodzitsa, Alena
Bahmani, Amir
Alavi, Arash
Ray, Utsab
Snyder, Michael
Ginsburg, Geoffrey
Pasquale, Dana
Woods, Christopher
Shaw, Ryan
A Method for Intelligent Allocation of Diagnostic Testing by Leveraging Data from Commercial Wearable Devices: A Case Study on COVID-19
title A Method for Intelligent Allocation of Diagnostic Testing by Leveraging Data from Commercial Wearable Devices: A Case Study on COVID-19
title_full A Method for Intelligent Allocation of Diagnostic Testing by Leveraging Data from Commercial Wearable Devices: A Case Study on COVID-19
title_fullStr A Method for Intelligent Allocation of Diagnostic Testing by Leveraging Data from Commercial Wearable Devices: A Case Study on COVID-19
title_full_unstemmed A Method for Intelligent Allocation of Diagnostic Testing by Leveraging Data from Commercial Wearable Devices: A Case Study on COVID-19
title_short A Method for Intelligent Allocation of Diagnostic Testing by Leveraging Data from Commercial Wearable Devices: A Case Study on COVID-19
title_sort method for intelligent allocation of diagnostic testing by leveraging data from commercial wearable devices: a case study on covid-19
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8978951/
https://www.ncbi.nlm.nih.gov/pubmed/35378754
http://dx.doi.org/10.21203/rs.3.rs-1490524/v1
work_keys_str_mv AT dunnjessilyn amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT shandhimobashirhasan amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT chopeter amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT roghanizadali amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT singhkarnika amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT wangwill amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT enacheoana amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT sternamanda amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT sbahirami amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT tatarbilge amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT fiscussean amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT khooqixuan amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT kuoyvonne amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT luxiao amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT hsiehjoseph amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT kalodzitsaalena amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT bahmaniamir amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT alaviarash amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT rayutsab amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT snydermichael amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT ginsburggeoffrey amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT pasqualedana amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT woodschristopher amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT shawryan amethodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT dunnjessilyn methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT shandhimobashirhasan methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT chopeter methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT roghanizadali methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT singhkarnika methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT wangwill methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT enacheoana methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT sternamanda methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT sbahirami methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT tatarbilge methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT fiscussean methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT khooqixuan methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT kuoyvonne methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT luxiao methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT hsiehjoseph methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT kalodzitsaalena methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT bahmaniamir methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT alaviarash methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT rayutsab methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT snydermichael methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT ginsburggeoffrey methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT pasqualedana methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT woodschristopher methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19
AT shawryan methodforintelligentallocationofdiagnostictestingbyleveragingdatafromcommercialwearabledevicesacasestudyoncovid19