Natural Language Processing for Improved Characterization of COVID-19 Symptoms: Observational Study of 350,000 Patients in a Large Integrated Health Care System

Deborah E Malden   ^{1, 2 *} , MSc, DPhil ;   Sara Y Tartof   ^{2, 3 *} , MPH, PhD ;   Bradley K Ackerson   ⁴ , MD ;   Vennis Hong   ² , MPH ;   Jacek Skarbinski   ^{5, 6} , MD ;   Vincent Yau   ⁷ , MA, PhD ;   Lei Qian   ² , MS, PhD ;   Heidi Fischer   ² , MS, PhD ;   Sally F Shaw   ² , MPH, DrPH ;   Susan Caparosa   ² , MA ;   Fagen Xie   ² , PhD

¹ Epidemic Intelligence Service, Centers for Disease Control and Prevention, Atlanta, GA, United States

² Department of Research & Evaluation, Kaiser Permanente Southern California, Pasadena, CA, United States

³ Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, CA, United States

⁴ Southern California Permanente Medical Group, Harbor City, CA, United States

⁵ The Permanente Medical Group, Kaiser Permanente Northern California, Oakland, CA, United States

⁶ Division of Research, Kaiser Permanente Northern California, Oakland, CA, United States

⁷ Genentech, a Member of the Roche Group, San Francisco, CA, United States

*these authors contributed equally