TY - JOUR TI - Augmented curation of clinical notes from a massive EHR system reveals symptoms of impending COVID-19 diagnosis AU - Wagner, Tyler AU - Shweta, FNU AU - Murugadoss, Karthik AU - Awasthi, Samir AU - Venkatakrishnan, AJ 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, II AU - Halamka, John AU - Badley, Andrew AU - Soundararajan, Venky A2 - van de Veerdonk, Frank L A2 - van der Meer, Jos WM VL - 9 PY - 2020 DA - 2020/07/07 SP - e58227 C1 - eLife 2020;9:e58227 DO - 10.7554/eLife.58227 UR - https://doi.org/10.7554/eLife.58227 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. KW - electronic health record KW - neural networks KW - machine learning KW - artificial intelligence KW - COVID-19 KW - SARS-CoV-2 JF - eLife SN - 2050-084X PB - eLife Sciences Publications, Ltd ER -