Chief Complaints: Can They Predict COVID-19 Positive Patients?

Abstract

Background: The COVID-19 pandemic has overwhelmed emergent and nonemergent medical facilities with patients often presenting with a vast array of clinical symptoms. We aim to evaluate the chief complaints of patients presenting to Urgent Care and Emergency facilities to better understand which chief complaints are more likely to be associated with these patients being confirmed COVID-19 positive. It is hypothesized that patients who have more commonly associated COVID-19 presenting symptoms will have a greater likelihood of positive test results. Methods: The study was a retrospective computational analysis that investigated the chief complaints of all confirmed and suspected COVID-19 cases presenting to Banner Health facilities within the state of Arizona from March through October 2020. The chief complaint and demographic data were extracted from Cerner’s underlying database. For each of these visits, the full list of chief complaints and patient demographics were extracted from the electronic health record. To more meaningfully characterize the chief complaint list, semantically and clinically similar chief complaints were aggregated. An example of aggregated complaints includes “SOB” and “Dyspnea”. Results: During the study period there were 70,884 unique encounters of COVID-19 suspected patients with 59,225 unique patients identified and 17,408 (29%) being confirmed COVID-19 positive. The twenty unique chief complaints were then correlated by patient encounter. Among the entire study population, “fever” was the most common chief complaint followed by “cough”. “Cough” (48%) and “fever” (41%) were the most common chief complaint for COVID-19 positive patients. Patients who presented with “loss of taste” or “loss of smell” were most likely to test positive with an OR of 5.53, 95% CI 5.12-5.97 and 7.64, 95% CI 6.96-8.39 respectively. Conclusion: Our research highlights an important aspect of the initial evaluation of COVID-19 patients within the clinical setting. Our study identified chief complaints that commonly are associated with the diagnosis of COVID-19 along with those that are less likely to be associated. This effort provides healthcare providers with data to that can better predict and identify patients that have an increased likelihood of being infected with COVID-19 based on their initial chief complaint.