Real-time infection prediction with wearable physiological monitoring and AI to aid military workforce readiness during COVID-19. Conroy, B., Silva, I., Mehraei, G., Damiano, R., Gross, B., Salvati, E., Feng, T., Schneider, J., Olson, N., Rizzo, A. G., Curtin, C. M., Frassica, J., & McFarlane, D. C. Scientific Reports, 12(1):3797, March, 2022. Number: 1 Publisher: Nature Publishing Group![Real-time infection prediction with wearable physiological monitoring and AI to aid military workforce readiness during COVID-19 [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Infectious threats, like the COVID-19 pandemic, hinder maintenance of a productive and healthy workforce. If subtle physiological changes precede overt illness, then proactive isolation and testing can reduce labor force impacts. This study hypothesized that an early infection warning service based on wearable physiological monitoring and predictive models created with machine learning could be developed and deployed. We developed a prototype tool, first deployed June 23, 2020, that delivered continuously updated scores of infection risk for SARS-CoV-2 through April 8, 2021. Data were acquired from 9381 United States Department of Defense (US DoD) personnel wearing Garmin and Oura devices, totaling 599,174 user-days of service and 201 million hours of data. There were 491 COVID-19 positive cases. A predictive algorithm identified infection before diagnostic testing with an AUC of 0.82. Barriers to implementation included adequate data capture (at least 48% data was needed) and delays in data transmission. We observe increased risk scores as early as 6 days prior to diagnostic testing (2.3 days average). This study showed feasibility of a real-time risk prediction score to minimize workforce impacts of infection.
@article{conroy_real-time_2022,
title = {Real-time infection prediction with wearable physiological monitoring and {AI} to aid military workforce readiness during {COVID}-19},
volume = {12},
copyright = {2022 The Author(s)},
issn = {2045-2322},
url = {https://www.nature.com/articles/s41598-022-07764-6},
doi = {10.1038/s41598-022-07764-6},
abstract = {Infectious threats, like the COVID-19 pandemic, hinder maintenance of a productive and healthy workforce. If subtle physiological changes precede overt illness, then proactive isolation and testing can reduce labor force impacts. This study hypothesized that an early infection warning service based on wearable physiological monitoring and predictive models created with machine learning could be developed and deployed. We developed a prototype tool, first deployed June 23, 2020, that delivered continuously updated scores of infection risk for SARS-CoV-2 through April 8, 2021. Data were acquired from 9381 United States Department of Defense (US DoD) personnel wearing Garmin and Oura devices, totaling 599,174 user-days of service and 201 million hours of data. There were 491 COVID-19 positive cases. A predictive algorithm identified infection before diagnostic testing with an AUC of 0.82. Barriers to implementation included adequate data capture (at least 48\% data was needed) and delays in data transmission. We observe increased risk scores as early as 6 days prior to diagnostic testing (2.3 days average). This study showed feasibility of a real-time risk prediction score to minimize workforce impacts of infection.},
language = {en},
number = {1},
urldate = {2023-06-04},
journal = {Scientific Reports},
author = {Conroy, Bryan and Silva, Ikaro and Mehraei, Golbarg and Damiano, Robert and Gross, Brian and Salvati, Emmanuele and Feng, Ting and Schneider, Jeffrey and Olson, Niels and Rizzo, Anne G. and Curtin, Catherine M. and Frassica, Joseph and McFarlane, Daniel C.},
month = mar,
year = {2022},
note = {Number: 1
Publisher: Nature Publishing Group},
keywords = {Infectious diseases, Machine learning},
pages = {3797},
}
Downloads: 0
{"_id":"2rxkN5PWWkAQT5SeT","bibbaseid":"conroy-silva-mehraei-damiano-gross-salvati-feng-schneider-etal-realtimeinfectionpredictionwithwearablephysiologicalmonitoringandaitoaidmilitaryworkforcereadinessduringcovid19-2022","author_short":["Conroy, B.","Silva, I.","Mehraei, G.","Damiano, R.","Gross, B.","Salvati, E.","Feng, T.","Schneider, J.","Olson, N.","Rizzo, A. G.","Curtin, C. M.","Frassica, J.","McFarlane, D. C."],"bibdata":{"bibtype":"article","type":"article","title":"Real-time infection prediction with wearable physiological monitoring and AI to aid military workforce readiness during COVID-19","volume":"12","copyright":"2022 The Author(s)","issn":"2045-2322","url":"https://www.nature.com/articles/s41598-022-07764-6","doi":"10.1038/s41598-022-07764-6","abstract":"Infectious threats, like the COVID-19 pandemic, hinder maintenance of a productive and healthy workforce. If subtle physiological changes precede overt illness, then proactive isolation and testing can reduce labor force impacts. This study hypothesized that an early infection warning service based on wearable physiological monitoring and predictive models created with machine learning could be developed and deployed. We developed a prototype tool, first deployed June 23, 2020, that delivered continuously updated scores of infection risk for SARS-CoV-2 through April 8, 2021. Data were acquired from 9381 United States Department of Defense (US DoD) personnel wearing Garmin and Oura devices, totaling 599,174 user-days of service and 201 million hours of data. There were 491 COVID-19 positive cases. A predictive algorithm identified infection before diagnostic testing with an AUC of 0.82. Barriers to implementation included adequate data capture (at least 48% data was needed) and delays in data transmission. We observe increased risk scores as early as 6 days prior to diagnostic testing (2.3 days average). This study showed feasibility of a real-time risk prediction score to minimize workforce impacts of infection.","language":"en","number":"1","urldate":"2023-06-04","journal":"Scientific Reports","author":[{"propositions":[],"lastnames":["Conroy"],"firstnames":["Bryan"],"suffixes":[]},{"propositions":[],"lastnames":["Silva"],"firstnames":["Ikaro"],"suffixes":[]},{"propositions":[],"lastnames":["Mehraei"],"firstnames":["Golbarg"],"suffixes":[]},{"propositions":[],"lastnames":["Damiano"],"firstnames":["Robert"],"suffixes":[]},{"propositions":[],"lastnames":["Gross"],"firstnames":["Brian"],"suffixes":[]},{"propositions":[],"lastnames":["Salvati"],"firstnames":["Emmanuele"],"suffixes":[]},{"propositions":[],"lastnames":["Feng"],"firstnames":["Ting"],"suffixes":[]},{"propositions":[],"lastnames":["Schneider"],"firstnames":["Jeffrey"],"suffixes":[]},{"propositions":[],"lastnames":["Olson"],"firstnames":["Niels"],"suffixes":[]},{"propositions":[],"lastnames":["Rizzo"],"firstnames":["Anne","G."],"suffixes":[]},{"propositions":[],"lastnames":["Curtin"],"firstnames":["Catherine","M."],"suffixes":[]},{"propositions":[],"lastnames":["Frassica"],"firstnames":["Joseph"],"suffixes":[]},{"propositions":[],"lastnames":["McFarlane"],"firstnames":["Daniel","C."],"suffixes":[]}],"month":"March","year":"2022","note":"Number: 1 Publisher: Nature Publishing Group","keywords":"Infectious diseases, Machine learning","pages":"3797","bibtex":"@article{conroy_real-time_2022,\n\ttitle = {Real-time infection prediction with wearable physiological monitoring and {AI} to aid military workforce readiness during {COVID}-19},\n\tvolume = {12},\n\tcopyright = {2022 The Author(s)},\n\tissn = {2045-2322},\n\turl = {https://www.nature.com/articles/s41598-022-07764-6},\n\tdoi = {10.1038/s41598-022-07764-6},\n\tabstract = {Infectious threats, like the COVID-19 pandemic, hinder maintenance of a productive and healthy workforce. If subtle physiological changes precede overt illness, then proactive isolation and testing can reduce labor force impacts. This study hypothesized that an early infection warning service based on wearable physiological monitoring and predictive models created with machine learning could be developed and deployed. We developed a prototype tool, first deployed June 23, 2020, that delivered continuously updated scores of infection risk for SARS-CoV-2 through April 8, 2021. Data were acquired from 9381 United States Department of Defense (US DoD) personnel wearing Garmin and Oura devices, totaling 599,174 user-days of service and 201 million hours of data. There were 491 COVID-19 positive cases. A predictive algorithm identified infection before diagnostic testing with an AUC of 0.82. Barriers to implementation included adequate data capture (at least 48\\% data was needed) and delays in data transmission. We observe increased risk scores as early as 6 days prior to diagnostic testing (2.3 days average). This study showed feasibility of a real-time risk prediction score to minimize workforce impacts of infection.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2023-06-04},\n\tjournal = {Scientific Reports},\n\tauthor = {Conroy, Bryan and Silva, Ikaro and Mehraei, Golbarg and Damiano, Robert and Gross, Brian and Salvati, Emmanuele and Feng, Ting and Schneider, Jeffrey and Olson, Niels and Rizzo, Anne G. and Curtin, Catherine M. and Frassica, Joseph and McFarlane, Daniel C.},\n\tmonth = mar,\n\tyear = {2022},\n\tnote = {Number: 1\nPublisher: Nature Publishing Group},\n\tkeywords = {Infectious diseases, Machine learning},\n\tpages = {3797},\n}\n\n","author_short":["Conroy, B.","Silva, I.","Mehraei, G.","Damiano, R.","Gross, B.","Salvati, E.","Feng, T.","Schneider, J.","Olson, N.","Rizzo, A. G.","Curtin, C. M.","Frassica, J.","McFarlane, D. C."],"key":"conroy_real-time_2022","id":"conroy_real-time_2022","bibbaseid":"conroy-silva-mehraei-damiano-gross-salvati-feng-schneider-etal-realtimeinfectionpredictionwithwearablephysiologicalmonitoringandaitoaidmilitaryworkforcereadinessduringcovid19-2022","role":"author","urls":{"Paper":"https://www.nature.com/articles/s41598-022-07764-6"},"keyword":["Infectious diseases","Machine learning"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"article","biburl":"https://api.zotero.org/users/1528358/collections/VYQBMSWJ/items?key=ZpFELJbRRRzw7HareFKZ4Uix&format=bibtex&limit=100","dataSources":["ZX4taNS949XiyXgAT"],"keywords":["infectious diseases","machine learning"],"search_terms":["real","time","infection","prediction","wearable","physiological","monitoring","aid","military","workforce","readiness","during","covid","conroy","silva","mehraei","damiano","gross","salvati","feng","schneider","olson","rizzo","curtin","frassica","mcfarlane"],"title":"Real-time infection prediction with wearable physiological monitoring and AI to aid military workforce readiness during COVID-19","year":2022}