Vital measurements of hospitalized COVID-19 patients as a predictor of Long COVID: An EHR-based cohort study from the RECOVER Program in N3C
Jiang, S; Loomba, J; Sharma, S; et al., Proceedings (IEEE International Conference on Bioinformatics and Biomedicine), December 2022
View Publication on PubMed
Short Summary
In this RECOVER study, researchers looked at the electronic health records (EHRs) of 85,196 people in the hospital with COVID to identify possible risk factors for Long COVID. Researchers wanted to see if health measurements called vital signs—which include how well a person breathes, how fast their heart beats, and their blood pressure—could show which people with COVID might be more likely to get Long COVID. Researchers used computer tools and special techniques to look at these vital signs. They found that changes in a person’s breathing and heartbeat during the first week they were hospitalized with COVID were better at predicting who might get Long COVID than other information like a person’s age, sex, or other health conditions. When researchers used these vital signs and other information together, they could make even better predictions. These findings show that looking at a person’s vital signs during the first week that they’re hospitalized with COVID can help doctors figure out, and better care for, people who might get Long COVID.
This summary was prepared by the RECOVER Initiative.
Publication Details
DOI: 10.1109/bibm55620.2022.9995311
Abstract
It is shown that various symptoms could remain in the stage of post-acute sequelae of SARS-CoV-2 infection (PASC), otherwise known as Long COVID. A number of COVID patients suffer from heterogeneous symptoms, which severely impact recovery from the pandemic. While scientists are trying to give an unambiguous definition of Long COVID, efforts in prediction of Long COVID could play an important role in understanding the characteristics of this new disease. Vital measurements (e.g., oxygen saturation, heart rate, blood pressure) could reflect the body's most basic functions and are measured regularly during hospitalization. Among patients diagnosed COVID-positive and hospitalized, we analyze the vital measurements of first 7 days since the hospitalization start date to study the pattern of the vital measurements and predict Long COVID with the information from vital measurements.
Authors
Sihang Jiang, Johanna Loomba, Suchetha Sharma, Donald Brown
Keywords
Long COVID; classification; machine learning; summary statistics; time series; vital measurements