JMIR Publications

ABSTRACT

Background:

Natural language processing (NLP) of unstructured text from EMR can improve characterization of COVID-19 symptoms, but large-scale studies assessing the real world application of NLP for this purpose are limited.

Objective:

To assess the contribution of NLP when identifying COVID-19 symptoms from EMR.

Methods:

This was a retrospective cohort study conducted in Kaiser Permanente Southern California (KPSC), a large integrated health care system using data from patients with positive SARS-CoV-2 laboratory tests from March 2020 to May 2021. An NLP algorithm was developed to extract free text from EMR on 12 established COVID-19 symptoms. Proportions of patients reporting each symptom were described before and after supplementing structured EMR data with NLP-extracted symptoms.

Results:

Among 359,938 patients with confirmed SARS-CoV-2 infection, NLP-supplemented analysis identified an additional 55,568 (15%) symptomatic cases that were previously defined as asymptomatic using structured data alone. The most common symptoms identified through NLP-supplemented analyses were cough (61%), fever (52%), myalgia (43%), and headache (40%). The proportion of additional cases with each selected symptom identified in NLP-supplemented analysis varied across symptoms, from 29% of all complaints for cough, to 61% of all records with nausea or vomiting. Of 295,305 symptomatic patients, the median time from symptom onset to testing was 3 days using structured data alone, whereas NLP-supplemented analyses resulted in the identification of COVID-19 symptoms approximately one day earlier.

Conclusions:

These findings demonstrate the value of NLP to facilitate enhanced characterization of COVID-19 by identifying additional signs and symptoms from EMR compared to traditional surveillance systems.