Duke Health Joins with nference to Advance Medical Research and Patient Care
< Back to All Publications
Pre-existing conditions are associated with COVID-19 patients' hospitalization, despite confirmed clearance of SARS-CoV-2 virus
March 23 2021
The current diagnostic gold-standard for SARS-CoV-2 clearance from infected patients is two consecutive negative PCR test results. However, there are anecdotal reports of hospitalization from protracted COVID complications (long-COVID) despite such confirmed viral clearance, presenting a clinical conundrum. We conducted a retrospective analysis of 266 COVID patients to compare those that were admitted/re-admitted post-viral clearance (hospitalized post-clearance cohort, n=93) with those that were hospitalized pre-clearance but were not re-admitted post-viral clearance (non-hospitalized post-clearance cohort, n=173). In order to differentiate these two cohorts, we used neural network models for the augmented curation of comorbidities and complications with positive sentiment in the EHR physician notes. In the year preceding COVID onset, acute kidney injury (n=15 (16.1%), p-value: 0.03), anemia (n=20 (21.5%), p-value: 0.02), and cardiac arrhythmia (n=21 (22.6%), p-value: 0.05) were significantly enriched in the physician notes of the hospitalized post-clearance cohort. This study highlights that these specific pre-existing conditions are associated with amplified hospitalization risk in long-COVID patients, despite their successful SARS-CoV-2 viral clearance. Our findings motivate follow-up prospective research into specific risk factors that predispose some patients towards the long-COVID syndrome.
Colin Pawlowski, AJ Venkatakrishnan, Eshwan Ramudu, Christian Kirkup, Arjun Puranik, Nikhil Kayal, Gabriela Berner, Akash Anand, Rakesh Barve, John C. O’Horo, Andrew D. Badley, Venky Soundararajan
nference, Cambridge, MA 02142, USA Mayo Clinic, Rochester, MN 55905, USA
Venky Soundararajan (firstname.lastname@example.org)
Let’s talk about how we can work together.
Fill out the form and we’ll get right back to you.