TY - JOUR
T1 - Augmented curation of clinical notes from a massive ehr system reveals symptoms of impending covid-19 diagnosis
AU - Wagner, Tyler
AU - Shweta, F. N.U.
AU - Murugadoss, Karthik
AU - Awasthi, Samir
AU - Venkatakrishnan, A. J.
AU - Bade, Sairam
AU - Puranik, Arjun
AU - Kang, Martin
AU - Pickering, Brian W.
AU - O’horo, John C.
AU - Bauer, Philippe R.
AU - Razonable, Raymund R.
AU - Vergidis, Paschalis
AU - Temesgen, Zelalem
AU - Rizza, Stacey
AU - Mahmood, Maryam
AU - Wilson, Walter R.
AU - Challener, Douglas
AU - Anand, Praveen
AU - Liebers, Matt
AU - Doctor, Zainab
AU - Silvert, Eli
AU - Solomon, Hugo
AU - Anand, Akash
AU - Barve, Rakesh
AU - Gores, Gregory
AU - Williams, Amy W.
AU - Morice, William G.
AU - Halamka, John
AU - Badley, Andrew
AU - Soundararajan, Venky
N1 - Publisher Copyright:
© Wagner et al.
PY - 2020/7
Y1 - 2020/7
N2 - Understanding temporal dynamics of COVID-19 symptoms could provide fine-grained resolution to guide clinical decision-making. Here, we use deep neural networks over an institution-wide platform for the augmented curation of clinical notes from 77,167 patients subjected to COVID-19 PCR testing. By contrasting Electronic Health Record (EHR)-derived symptoms of COVID-19-positive (COVIDpos; n = 2,317) versus COVID-19-negative (COVIDneg; n = 74,850) patients for the week preceding the PCR testing date, we identify anosmia/dysgeusia (27.1-fold), fever/chills (2.6-fold), respiratory difficulty (2.2-fold), cough (2.2-fold), myalgia/arthralgia (2-fold), and diarrhea (1.4-fold) as significantly amplified in COVIDpos over COVIDneg patients. The combination of cough and fever/chills has 4.2-fold amplification in COVIDpos patients during the week prior to PCR testing, in addition to anosmia/dysgeusia, constitutes the earliest EHR-derived signature of COVID-19. This study introduces an Augmented Intelligence platform for the real-time synthesis of institutional biomedical knowledge. The platform holds tremendous potential for scaling up curation throughput, thus enabling EHR-powered early disease diagnosis.
AB - Understanding temporal dynamics of COVID-19 symptoms could provide fine-grained resolution to guide clinical decision-making. Here, we use deep neural networks over an institution-wide platform for the augmented curation of clinical notes from 77,167 patients subjected to COVID-19 PCR testing. By contrasting Electronic Health Record (EHR)-derived symptoms of COVID-19-positive (COVIDpos; n = 2,317) versus COVID-19-negative (COVIDneg; n = 74,850) patients for the week preceding the PCR testing date, we identify anosmia/dysgeusia (27.1-fold), fever/chills (2.6-fold), respiratory difficulty (2.2-fold), cough (2.2-fold), myalgia/arthralgia (2-fold), and diarrhea (1.4-fold) as significantly amplified in COVIDpos over COVIDneg patients. The combination of cough and fever/chills has 4.2-fold amplification in COVIDpos patients during the week prior to PCR testing, in addition to anosmia/dysgeusia, constitutes the earliest EHR-derived signature of COVID-19. This study introduces an Augmented Intelligence platform for the real-time synthesis of institutional biomedical knowledge. The platform holds tremendous potential for scaling up curation throughput, thus enabling EHR-powered early disease diagnosis.
UR - http://www.scopus.com/inward/record.url?scp=85089204568&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089204568&partnerID=8YFLogxK
U2 - 10.7554/eLife.58227
DO - 10.7554/eLife.58227
M3 - Article
C2 - 32633720
AN - SCOPUS:85089204568
SN - 2050-084X
VL - 9
SP - 1
EP - 12
JO - eLife
JF - eLife
M1 - e58227
ER -