Mapping each pre-existing condition\u2019s association to short-term and long-term COVID-19 complications

A J Venkatakrishnan,John C O‘Horo,Ian Conrad,Arjun Puranik,Purushottam Sinha,Travis Hughes,Nikhil Kayal,Colin Pawlowski,Akash Anand,Andrew D Badley,Venky Soundararajan,Rakesh Barve,Gabriela Berner,John Halamka,Sairam Bade,David Zemmour

doi:10.1038/s41746-021-00484-7

A J Venkatakrishnan, John C O‘Horo + Show 14 more

Open Access

https://doi.org/10.1038/s41746-021-00484-7

Copy DOI

Abstract

Understanding the relationships between pre-existing conditions and complications of COVID-19 infection is critical to identifying which patients will develop severe disease. Here, we leverage ~1.1 million clinical notes from 1803 hospitalized COVID-19 patients and deep neural network models to characterize associations between 21 pre-existing conditions and the development of 20 complications (e.g. respiratory, cardiovascular, renal, and hematologic) of COVID-19 infection throughout the course of infection (i.e. 0–30 days, 31–60 days, and 61–90 days). Pleural effusion was the most frequent complication of early COVID-19 infection (89/1803 patients, 4.9%) followed by cardiac arrhythmia (45/1803 patients, 2.5%). Notably, hypertension was the most significant risk factor associated with 10 different complications including acute respiratory distress syndrome, cardiac arrhythmia, and anemia. The onset of new complications after 30 days is rare and most commonly involves pleural effusion (31–60 days: 11 patients, 61–90 days: 9 patients). Lastly, comparing the rates of complications with a propensity-matched COVID-negative hospitalized population confirmed the importance of hypertension as a risk factor for early-onset complications. Overall, the associations between pre-COVID conditions and COVID-associated complications presented here may form the basis for the development of risk assessment scores to guide clinical care pathways.

Highlights

The COVID-19 pandemic remains an ongoing public health crisis[1], and it is critically important to understand the full spectrum of complications that arise throughout the course of SARS-CoV-2 infection
Using deep language models (Fig. 1B), we extracted the 20 risk factors for COVID-19 severe illness reported by the CDC (Fig. 1C) and the 18 COVID-associated complications (Fig. 1D) in order to analyze their association in our cohort (Figs. 2–4)
We identify hypertension (RR: 9.4, p-value: 2.9e−64) as the most significant risk factor followed by other cardiovascular chronic diseases, anemia (RR: 3.2, p-value: 9.8e−14), and chronic kidney disease (RR: 4.4, p-value: 1.5e−22), as the most significant predictors of clinical complication in early COVID-19 infection

Summary

Introduction

The COVID-19 pandemic remains an ongoing public health crisis[1], and it is critically important to understand the full spectrum of complications that arise throughout the course of SARS-CoV-2 infection. There is an incomplete understanding of the relationship between preexisting comorbidities and post-COVID complications. Automated curation of clinical notes affords the ability to rapidly perform epidemiologic studies from unstructured text found in electronic health records (EHRs). Previous efforts have leveraged various models for natural language processing to extract information regarding diagnoses, treatments, and clinical courses from unstructured data[3]. We have previously benchmarked different natural language processing models and transformer architectures[4] and developed BERT-based models to curate unstructured clinical data from EHRs to uncover associations with COVID-19 infection[4,5]

Methods

Results

Conclusion