Identifying who has long COVID in the USA: a machine learning approach using N3C data

Pfaff, Emily R.; Girvin, Andrew T.; Bennett, Tellen D.; Bhatia, Abhishek; Brooks, Ian M.; Deer, Rachel; Dekermanjian, Jonathan; Jolley, Sarah E.; Kahn, Michael G.; Kostka, Kristin; McMurry, Julie A.; Moffitt, Richard A.; Walden, Anita; Chute, Christopher G.; Haendel, Melissa; Bramante, Carolyn T.; Dorr, David A.; Morris, Michele; Parker, Ann M.; Sidky, Hythem; Gersing, Ken; Hong, Stephanie; Niehaus, Emily

doi:10.1016/s2589-7500(22)00048-6

Cited by 154 publications

(176 citation statements)

References 21 publications

Supporting

Mentioning

131

Contrasting

Unclassified

Order By: Relevance

“…These differences in sex distribution could be explained by the variations in the immune response between males and females, and the fact that female patients have more robust inflammatory, antiviral, and humoral immune responses, biological differences on sex hormones, and expression and regulation of angiotensin-converting enzyme 2 (ACE2)(18, 20). Our study cohort, similar to other PASC studies, the subjects were predominantly white females, with obesity(17, 21, 22) characteristics associated with lower likelihood for full recovery(23). In contrast, some racial and ethnic minority groups, such as Native American Indians, Alaska Natives, Hispanic and Black, have been shown to have a disproportionately higher risk for infection, severity of illness, hospitalization, and deaths.…”

Section: Discussionsupporting

confidence: 78%

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is common in post-acute sequelae of SARS-CoV-2 infection (PASC): Results from a post-COVID-19 multidisciplinary clinic

Bonilla

Quach

Tiwari

et al. 2022

Preprint

View full text Add to dashboard Cite

Background The global prevalence of PASC is estimated to be present in 0.43 and based on the WHO estimation of 470 million worldwide COVID-19 infections, corresponds to around 200 million people experiencing long COVID symptoms. Despite this, its clinical features are not well defined. Methods We collected retrospective data from 140 patients with PASC in a post-COVID-19 clinic on demographics, risk factors, illness severity (graded as one-mild to five-severe), functional status, and 29 symptoms and principal component symptoms cluster analysis. The Institute of Medicine (IOM) 2015 criteria were used to determine the ME/CFS phenotype. Findings The median age was 47 years, 59.0% were female; 49.3% White, 17.2% Hispanic, 14.9% Asian, and 6.7% Black. Only 12.7% required hospitalization. Seventy-two (53.5%) patients had no known comorbid conditions. Forty-five (33.9%) were significantly debilitated. The median duration of symptoms was 285.5 days, and the number of symptoms was 12. The most common symptoms were fatigue (86.5%), post-exertional malaise (82.8%), brain fog (81.2%), unrefreshing sleep (76.7%), and lethargy (74.6%). Forty-three percent fit the criteria for ME/CFS. Interpretations Most PASC patients evaluated at our clinic had no comorbid condition and were not hospitalized for acute COVID-19. One-third of patients experienced a severe decline in their functional status. About 43% had the ME/CFS subtype.

show abstract

Section: Discussionsupporting

confidence: 78%

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is common in post-acute sequelae of SARS-CoV-2 infection (PASC): Results from a post-COVID-19 multidisciplinary clinic

Bonilla

Quach

Tiwari

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Second, because identification of individuals without PASC (controls) is not straightforward without clear definitions or biomarkers, we used three approaches to identify controls. Two of those leveraged our CP classification model for long-COVID [23]. Some pre-existing conditions can carry forward from the acute phase and appear later as features in the PASC phase.…”

Section: Discussionmentioning

confidence: 99%

Risk Factors Associated with Post-Acute Sequelae of SARS-CoV-2 in an EHR Cohort: A National COVID Cohort Collaborative (N3C) Analysis as part of the NIH RECOVER program

Hill

Mehta

Sharma

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background: More than one-third of individuals experience post-acute sequelae of SARS-CoV-2 infection (PASC, which includes long-COVID). Objective: To identify risk factors associated with PASC/long-COVID. Design: Retrospective case-control study. Setting: 31 health systems in the United States from the National COVID Cohort Collaborative (N3C). Patients: 8,325 individuals with PASC (defined by the presence of the International Classification of Diseases, version 10 code U09.9 or a long-COVID clinic visit) matched to 41,625 controls within the same health system. Measurements: Risk factors included demographics, comorbidities, and treatment and acute characteristics related to COVID-19. Multivariable logistic regression, random forest, and XGBoost were used to determine the associations between risk factors and PASC. Results: Among 8,325 individuals with PASC, the majority were >50 years of age (56.6%), female (62.8%), and non-Hispanic White (68.6%). In logistic regression, middle-age categories (40 to 69 years; OR ranging from 2.32 to 2.58), female sex (OR 1.4, 95% CI 1.33-1.48), hospitalization associated with COVID-19 (OR 3.8, 95% CI 3.05-4.73), long (8-30 days, OR 1.69, 95% CI 1.31-2.17) or extended hospital stay (30+ days, OR 3.38, 95% CI 2.45-4.67), receipt of mechanical ventilation (OR 1.44, 95% CI 1.18-1.74), and several comorbidities including depression (OR 1.50, 95% CI 1.40-1.60), chronic lung disease (OR 1.63, 95% CI 1.53-1.74), and obesity (OR 1.23, 95% CI 1.16-1.3) were associated with increased likelihood of PASC diagnosis or care at a long-COVID clinic. Characteristics associated with a lower likelihood of PASC diagnosis or care at a long-COVID clinic included younger age (18 to 29 years), male sex, non-Hispanic Black race, and comorbidities such as substance abuse, cardiomyopathy, psychosis, and dementia. More doctors per capita in the county of residence was associated with an increased likelihood of PASC diagnosis or care at a long-COVID clinic. Our findings were consistent in sensitivity analyses using a variety of analytic techniques and approaches to select controls. Conclusions: This national study identified important risk factors for PASC such as middle age, severe COVID-19 disease, and specific comorbidities. Further clinical and epidemiological research is needed to better understand underlying mechanisms and the potential role of vaccines and therapeutics in altering PASC course.

show abstract

“…Studies to date estimate that 30-50% of people who had COVID-19 still experience at least one post-COVID symptom 4 weeks after infection and 10-30% even after 12 weeks of acute infection 2, 3 . While the definition and scope of PASC remains to be determined, it is currently defined as new or persistent symptoms of COVID-19 beyond 4 weeks of acute infection that cannot be explained by other underlying etiologies 4, 5 . With the huge toll of acute infections that have and continue to occur worldwide, even if only a small fraction of patients goes on to develop PASC, it will have an enormous impact on society and the healthcare system for years to come.…”

Section: Introductionmentioning

confidence: 99%

Persistent Presence of Spike protein and Viral RNA in the Circulation of Individuals with Post-Acute Sequelae of COVID-19

Craddock

Mahajan

Krishnamachary

et al. 2022

Preprint

View full text Add to dashboard Cite

SARS-CoV-2, the causative agent of COVID-19 disease has resulted in the death of millions worldwide since the beginning of the pandemic in December 2019. While much progress has been made to understand acute manifestations of SARS-CoV-2 infection, less is known about post-acute sequelae of COVID-19 (PASC). We investigated the levels of circulating SARS-CoV-2 components, Spike protein and viral RNA, in patients hospitalized with acute COVID-19 and in patients with and without PASC. In hospitalized patients with acute COVID-19 (n=116), we observed a positive correlation of Spike protein with D-dimer, length of hospitalization, and peak WHO score while viral RNA correlated with a tissue injury marker, lactate dehydrogenase (LDH). When comparing patients with post-COVID symptoms (n=33) and patients without (n=14), we found that Spike protein and viral RNA were more likely to be present in patients with PASC and in some cases at higher levels compared to acute COVID-19 patients. We also observed that the percent positivity of circulating viral RNA increased in the PASC positive individuals compared to acute COVID-19 group while Spike protein positivity remained the same. Additionally, we report that part of the circulating Spike protein is linked to extracellular vesicles without any presence of viral RNA in these vesicles. Our findings suggest that Spike protein and/or viral RNA fragments persist in the recovered COVID-19 patients with PASC, independent of their presence or absence during the acute COVID-19 phase.

show abstract

Identifying who has long COVID in the USA: a machine learning approach using N3C data

Cited by 154 publications

References 21 publications

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is common in post-acute sequelae of SARS-CoV-2 infection (PASC): Results from a post-COVID-19 multidisciplinary clinic

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is common in post-acute sequelae of SARS-CoV-2 infection (PASC): Results from a post-COVID-19 multidisciplinary clinic

Risk Factors Associated with Post-Acute Sequelae of SARS-CoV-2 in an EHR Cohort: A National COVID Cohort Collaborative (N3C) Analysis as part of the NIH RECOVER program

Persistent Presence of Spike protein and Viral RNA in the Circulation of Individuals with Post-Acute Sequelae of COVID-19

Contact Info

Product

Resources

About