COVID-19 is caused by the SARS-CoV-2 virus and was first detected in Wuhan, China, and reported to the World Health Organization Country Office in China on December 31, 2019. It was declared a public health emergency of international concern on January 30, 2020, and a pandemic on March 11, 2020. The first COVID-19 case in the United States was confirmed on January 21, 2020. A rapid expansion to all 50 US states was observed, with approximately 47 500 000 confirmed cases and almost 770 000 deaths as of November 15, 2021. Detailed clinical information is needed to help assess the extent of the pandemic, characterize the virus and the disease it causes, discover and compare supportive or therapeutic approaches, and apply population health measures at the patient level. This detailed information is typically found in unstructured text notes from electronic health record (EHR) systems or other ancillary systems. Extracting such information manually is costly, not scalable, and far too slow to address current needs.
