Augmented curation of clinical notes from a massive EHR system reveals symptoms of impending COVID-19 diagnosis

July 7 2020

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.

Authors:

Tyler Wagner, FNU Shweta, Karthik Murugadoss, Samir Awasthi, AJ Venkatakrishnan, Sairam Bade, Arjun Puranik, Martin Kang, Brian W Pickering, John C O’Horo, Philippe R Bauer, Raymund R Razonable, Paschalis Vergidis, Zelalem Temesgen, Stacey Rizza, Maryam Mahmood, Walter R Wilson, Douglas Challener, Praveen Anand, Matt Liebers, Zainab Doctor, Eli Silvert, Hugo Solomon, Akash Anand, Rakesh Barve, Gregory Gores, Amy W Williams, William G Morice II, John Halamka, Andrew Badley, Venky Soundararajan

nference Cambridge, United States nference Labs Bangalore, India Mayo Clinic Rochester, United States Mayo Clinic Laboratories Rochester, United States

Mayo Clinic

nference

Correspondence to:

Andrew Badley (badley.andrew@mayo.edu), Venky Soundararajan (venky@nference.net)