Identification of risk factors of Long COVID and predictive modeling in the RECOVER EHR cohorts

Zang, C; Hou, Y; Schenck, EJ; et al., Communications Medicine, July 2024

View Publication on PubMed

July 2024
Communications Medicine

Short Summary

Some people develop new conditions or symptoms after having COVID-19, called Long COVID. This can lead to ongoing health problems. Researchers still don’t fully understand why some people get Long COVID while others do not. In this RECOVER study, researchers wanted to learn what increases someone’s risk of developing Long COVID after getting COVID-19. Researchers studied the electronic health records of 2.1 million people from New York and Florida who either had or had not had COVID-19 between March 2020 and November 2021. Using this data, they created a new computational model (a computer program that imitates how something works in real life) to help identify the things that Long COVID patients had in common. The researchers looked at whether these shared factors increased their risk of developing Long COVID. The model found that the people who were more likely to develop Long COVID if they had severe COVID-19 the first time they got the virus, were underweight, or had other health problems, like cancer or liver disease. The results also show that computational models can help identify people who have a higher chance of developing different symptoms and types of Long COVID. This information is important because it can be used to help researchers find new ways to prevent, diagnose, and treat Long COVID.

This summary was prepared by the RECOVER Initiative.

Publication Details

DOI: 10.1038/s43856-024-00549-0

Abstract

Background: SARS-CoV-2-infected patients may develop new conditions in the period after the acute infection. These conditions, the post-acute sequelae of SARS-CoV-2 infection (PASC, or Long COVID), involve a diverse set of organ systems. Limited studies have investigated the predictability of Long COVID development and its associated risk factors.

Methods: In this retrospective cohort study, we used electronic healthcare records from two large-scale PCORnet clinical research networks, INSIGHT (~1.4 million patients from New York) and OneFlorida+ (~0.7 million patients from Florida), to identify factors associated with having Long COVID, and to develop machine learning-based models for predicting Long COVID development. Both SARS-CoV-2-infected and non-infected adults were analysed during the period of March 2020 to November 2021. Factors associated with Long COVID risk were identified by removing background associations and correcting for multiple tests.

Results: We observed complex association patterns between baseline factors and a variety of Long COVID conditions, and we highlight that severe acute SARS-CoV-2 infection, being underweight, and having baseline comorbidities (e.g., cancer and cirrhosis) are likely associated with increased risk of developing Long COVID. Several Long COVID conditions, e.g., dementia, malnutrition, chronic obstructive pulmonary disease, heart failure, PASC diagnosis U099, and acute kidney failure are well predicted (C-index > 0.8). Moderately predictable conditions include atelectasis, pulmonary embolism, diabetes, pulmonary fibrosis, and thromboembolic disease (C-index 0.7-0.8). Less predictable conditions include fatigue, anxiety, sleep disorders, and depression (C-index around 0.6).

Conclusions: This observational study suggests that association patterns between investigated factors and Long COVID are complex, and the predictability of different Long COVID conditions varies. However, machine learning-based predictive models can help in identifying patients who are at risk of developing a variety of Long COVID conditions.

Authors

Chengxi Zang, Yu Hou, Edward J Schenck, Zhenxing Xu, Yongkang Zhang, Jie Xu, Jiang Bian, Dmitry Morozyuk, Dhruv Khullar, Anna S Nordvig, Elizabeth A Shenkman, Russell L Rothman, Jason P Block, Kristin Lyman, Yiye Zhang, Jay Varma, Mark G Weiner, Thomas W Carton, Fei Wang, Rainu Kaushal

Keywords

Not available