Publications

@article{nokey,

title = {HIV Infection and Long COVID: A RECOVER Program, Electronic Health Record-Based Cohort Study},

author = {Kellie L. Hawkins and Dima Dandachi and Zoe Verzani and M. Daniel Brannock and Colby Lewis and Sajjad Abedian and Sohrab Jaferian and Shannon Wuller and Jennifer Truong and Margot Gage Witvliet and Gretchen Dymond and Hemalkumar B. Mehta and Payal B. Patel and Elaine Hill and Mark G. Weiner and Thomas W. Carton and Rainu Kaushal and Elen Feuerriegel and Huong G. Tran and Kristen Marks and Carlos R. Oliveira and Edward M. Gardner and Igho Ofotokun and Roy M. Gulick and Kristine M. Erlandson},

doi = {10.1093/cid/ciaf242},

year  = {2025},

date = {2025-10-06},

urldate = {2025-10-06},

journal = {Clinical Infectious Diseases},

volume = {81},

issue = {3},

pages = {427-438},

abstract = {Background: People with human immunodeficiency virus (HIV) may be at increased risk for long COVID after acute severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. We investigated the association between HIV and long COVID in 2 large electronic health record databases.



Methods: Using data from the Patient-Centered Clinical Research Network (PCORnet) and the National Clinical Cohort Collaborative (N3C) from 1 January 2018 to 30 April 2024, our analytic sample included individuals aged ≥21 years with SARS-CoV-2. All individuals were classified as having HIV or not. We estimated the adjusted odds ratio (aOR) of long COVID by HIV status using logistic regression. Multivariable models controlled for potential associated factors and used 2 cohort definitions: a computed phenotype definition or ICD-10 code-based definition.



Results: We included 1 369 896 patients from PCORnet (11 964 with and 1 357 932 without HIV) and 3 312 355 patients from N3C (23 931 with and 3 288 424 without HIV). Using the computed phenotype definition of long COVID, we noted a small, but significant, increase in odds of developing long COVID among people with compared to those without HIV (PCORnet: aOR, 1.09 [95% confidence interval {CI}, 1.04-1.14]; N3C: aOR, 1.18 [95% CI, 1.13-1.23]). Using the ICD-10 definition of long COVID, there was no association between HIV and long COVID (PCORnet: aOR, 1.01 [95% CI, .88-1.16]; N3C: aOR, 1.07 [95% CI, .97-1.18]).



Conclusions: In this large multicenter study, people with HIV had a modestly increased risk of long COVID when defined by a computed phenotype, but not when using ICD-10 codes. These findings suggest that long COVID may be underrecognized in people with HIV and underscore challenges in diagnosing long COVID in populations with baseline chronic conditions.},

keywords = {chronic diseases, COVID-19, health disparities, HIV, long COVID},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Schizophrenia, Bipolar, or Major Depressive Disorder and Postacute Sequelae of COVID-19},

author = {Veer Vekaria and Rohith Kumar Thiruvalluru and Zoe Verzani and Sajjad Abedian and Mark Olfson and Braja Gopal Patra and Yunyu Xiao and Katherine S. Salamon and Karin Hoth and Frank Blancero and Maxwell M. Hornig-Rohan and Teresa Akintonwa and Mahfuza Sabiha and Mark G. Weiner and Thomas W. Carton and Rainu Kaushal and Jyotishman Pathak},

doi = {10.1001/jamanetworkopen.2025.40242},

year  = {2025},

date = {2025-10-01},

urldate = {2025-10-01},

journal = {JAMA Network Open},

volume = {8},

issue = {10},

pages = {e2540242},

abstract = {Importance: Given the increased vulnerability to COVID-19 among those with a serious mental illness (SMI), it remains unclear whether these individuals face a higher risk of developing postacute sequelae of SARS-CoV-2 (PASC). Understanding this association could inform secondary prevention efforts.



Objective: To identify the risk of developing PASC in patients with an SMI.



Design, setting, and participants: This longitudinal cohort study used data derived from large-scale electronic health records (EHRs) between March 2020 and April 2023, inclusive of 180-day follow-up. Patients included adults aged 21 years or older with a confirmed COVID-19 infection evidenced by a relevant laboratory result, diagnosis, or prescription order.



Exposures: Evidence of an SMI diagnosis (schizophrenia, bipolar disorder, or recurrent major depressive disorder) recorded before COVID-19 infection.



Main outcomes and measures: Evidence of PASC symptoms within 30 to 180 days' follow-up after COVID-19 infection reported as odds ratios (OR) mutually adjusted for age, sex, race and ethnicity, insurance type, Charlson Comorbidity Index (CCI) score, and COVID-19 severity.



Results: A total of 1 625 857 patients with a COVID-19 infection were included (mean [SD] age, 52 [17] years; 998 237 [61.4%] female, 204 237 [12.6%] non-Hispanic Black, 219 220 [13.5%] Hispanic, 833 411 [51.3%] non-Hispanic White, and 1 228 664 [75.6%] urban patients), of whom 258 523 (15.9%) had an SMI and 403 641 (24.8%) developed PASC. Individuals with an SMI had increased adjusted odds of developing PASC (OR, 1.10; 95% CI, 1.08-1.11; P < .001). Variables associated with greater odds of PASC among the study population included older age compared with age 22 to 34 years (35 to 44 years: OR, 1.04; 95% CI, 1.03-1.06; 45 to 64 years: OR, 1.11; 95% CI, 1.10-1.12; ≥65 years: OR, 1.18; 95% CI, 1.17-1.20), non-Hispanic Black and Hispanic compared with non-Hispanic White race and ethnicity (non-Hispanic Black: OR, 1.08; 95% CI, 1.07-1.10; Hispanic: OR, 1.12; 95% CI, 1.11-1.13), higher chronic disease burden vs no chronic disease (CCI 1 to 3: OR, 1.13; 95% CI, 1.12-1.14; CCI ≥4: OR, 1.23; 95% CI, 1.22-1.25), and hospitalization with initial COVID-19 infection vs no hospitalization (hospitalized: OR, 1.80; 95% CI, 1.77-1.82; hospitalized with ventilation: OR, 2.17; 95% CI, 2.12-2.22; P < .001). Compared with public insurance, commercial health insurance was associated with lower odds of PASC (OR, 0.85; 95% CI, 0.84-0.86).



Conclusions and relevance: In this cohort study of patients infected with COVID-19, patients with SMI compared with those without SMI were at increased risk of PASC, underscoring the need for coordinated mental health and COVID-19 care strategies.},

keywords = {COVID-19, long COVID, mental health},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Extracting post-acute sequelae of SARS-CoV-2 infection symptoms from clinical notes via hybrid natural language processing},

author = {Zilong Bai and Zihan Xu and Cong Sun and Chengxi Zang and H. Timothy Bunnell and Catherine Sinfield and Jacqueline Rutter and Aaron Thomas Martinez and L. Charles Bailey and Mark G. Weiner and Thomas T. Campion and Thomas W. Carton and Christopher B. Forrest and Rainu Kaushal and Fei Wang and Yifan Peng},

doi = {10.1038/s44401-025-00033-4},

year  = {2025},

date = {2025-08-21},

journal = {npj Health System},

volume = {21},

issue = {2},

abstract = {Accurately and efficiently diagnosing Post-Acute Sequelae of COVID-19 (PASC) remains challenging due to its myriad symptoms that evolve over long- and variable-time intervals. To address this issue, we developed a hybrid natural language processing pipeline that integrates rule-based named entity recognition with BERT-based assertion detection modules for PASC-symptom extraction and assertion detection from clinical notes. We developed a comprehensive PASC lexicon with clinical specialists. From 11 health systems of the RECOVER initiative network across the U.S., we curated 160 intake progress notes for model development and evaluation, and collected 47,654 progress notes for a population-level prevalence study. We achieved an average F1 score of 0.82 in one-site internal validation and 0.76 in 10-site external validation for assertion detection. Our pipeline processed each note at 2.448 ± 0.812 seconds on average. Spearman correlation tests showed ρ > 0.83 for positive mentions and ρ > 0.72 for negative ones, both with P < 0.0001. These demonstrate the effectiveness and efficiency of our models and its potential for improving PASC diagnosis.},

keywords = {COVID-19, long COVID, natural language processing},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Long-COVID incidence proportion in adults and children between 2020 and 2024},

author = {Hannah L. Mandel and Yun J. Yoo and Andrea J. Allen and Sajjad Abedian and Zoe Verzani and Elizabeth W. Karlson and Lawrence C. Kleinman and Praveen C. Mudumbi and Carlos R. Oliveira and Jennifer A. Muszynski and Rachel S. Gross and Thomas W. Carton and C. Kim and Emily Taylor and Heekyong Park and Jasmin Divers and J. Daniel Kelly and Jonathan Arnold and Carol Reynolds Geary and Chengxi Zang and Kelan G. Tantisira and Kyung E. Rhee and Michael Koropsak and Sindhu Mohandas and Andrew Vasey and Abu S. M. Mosa and Melissa Haendel and Christopher G. Chute and Shawn N. Murphy and Lisa O'Brien and Jacqueline Szmuszkovicz and Nicholas Guthe and Jorge L. Santana and Aliva De and Amanda L. Bogie and Katia C. Halabi and Lathika Mohanraj and Patricia A Kinser and Samuel E. Packard and Katherine R. Tuttle and Kathryn Hirabayashi and Rainu Kaushal and Emily Pfaff and Mark G. Weiner and Lorna E. Thorpe and Richard A. Moffitt},

doi = {10.1093/cid/ciaf046},

year  = {2025},

date = {2025-07-18},

urldate = {2025-07-18},

journal = {Clinical Infectious Diseases},

volume = {80},

issue = {6},

pages = {1247-1261},

abstract = {Background: Incidence estimates of post-acute sequelae of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, also known as long COVID, have varied across studies and changed over time. We estimated long COVID incidence among adult and pediatric populations in 3 nationwide research networks of electronic health records (EHRs) participating in the RECOVER (Researching COVID to Enhance Recovery) Initiative using different classification algorithms (computable phenotypes).



Methods: This EHR-based retrospective cohort study included adult and pediatric patients with documented acute SARS-CoV-2 infection and 2 control groups: contemporary coronavirus disease 2019 (COVID-19)-negative and historical patients (2019). We examined the proportion of individuals identified as having symptoms or conditions consistent with probable long COVID within 30-180 days after COVID-19 infection (incidence proportion). Each network (the National COVID Cohort Collaborative [N3C], National Patient-Centered Clinical Research Network [PCORnet], and PEDSnet) implemented its own long COVID definition. We introduced a harmonized definition for adults in a supplementary analysis.



Results: Overall, 4% of children and 10%-26% of adults developed long COVID, depending on computable phenotype used. Excess incidence among SARS-CoV-2 patients was 1.5% in children and ranged from 5% to 6% among adults, representing a lower-bound incidence estimation based on our control groups. Temporal patterns were consistent across networks, with peaks associated with introduction of new viral variants.



Conclusions: Our findings indicate that preventing and mitigating long COVID remains a public health priority. Examining temporal patterns and risk factors for long COVID incidence informs our understanding of etiology and can improve prevention and management.},

keywords = {COVID-19, electronic health records, long COVID, public health surveillance},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Long COVID after SARS-CoV-2 during pregnancy in the United States},

author = {Chengxi Zang and Daniel Guth and Ann M. Bruno and Zhenxing Xu and Haoyang Li and Nariman Ammar and Robert Chew and Nick Guthe and Emily Hadley and Rainu Kaushal and Tanzy Love and Brenda M. McGrath and Rena C. Patel and Elizabeth C. Seibert and Yalini Senathirajah and Sharad Kumar Singh and Fei Wang and Mark G. Weiner and Kenneth J. Wilkins and Yiye Zhang and Torri D. Metz and Elaine Hill and Thomas W. Carton},

doi = {10.1038/s41467-025-57849-9},

year  = {2025},

date = {2025-04-01},

urldate = {2025-04-01},

journal = {Nature Communications},

volume = {16},

issue = {1},

pages = {3005},

abstract = {Pregnancy alters immune responses and clinical manifestations of COVID-19, but its impact on Long COVID remains uncertain. This study investigated Long COVID risk in individuals with SARS-CoV-2 infection during pregnancy compared to reproductive-age females infected outside of pregnancy. A retrospective analysis of two U.S. databases, the National Patient-Centered Clinical Research Network (PCORnet) and the National COVID Cohort Collaborative (N3C), identified 29,975 pregnant individuals (aged 18-50) with SARS-CoV-2 infection in pregnancy from PCORnet and 42,176 from N3C between March 2020 and June 2023. At 180 days after infection, estimated Long COVID risks for those infected during pregnancy were 16.47 per 100 persons (95% CI, 16.00-16.95) in PCORnet using the PCORnet computational phenotype (CP) model and 4.37 per 100 persons (95% CI, 4.18-4.57) in N3C using the N3C CP model. Compared to matched non-pregnant individuals, the adjusted hazard ratios for Long COVID were 0.86 (95% CI, 0.83-0.90) in PCORnet and 0.70 (95% CI, 0.66-0.74) in N3C. The observed risk factors for Long COVID included Black race/ethnicity, advanced maternal age, first- and second-trimester infection, obesity, and comorbid conditions. While the findings suggest a high incidence of Long COVID among pregnant individuals, their risk was lower than that of matched non-pregnant females.},

keywords = {COVID-19, long COVID, maternal health},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Opportunities and Challenges in Using Electronic Health Record Systems to Study Postacute Sequelae of SARS-CoV-2 Infection: Insights From the NIH RECOVER Initiative},

author = {Hannah L. Mandel and Shruti N. Shah and L. Charles Bailey and Thomas W. Carton and Yu Chen and Shari Esquenazi-Karonika and Melissa Haendel and Mady Hornig and Rainu Kaushal and Carlos R. Oliveira and Alice A. Perlowski and Emily Pfaff and Suchitra Rao and Hanieh Razzaghi and Elle Seibert and Gelise L. Thomas and Mark G. Weiner and Lorna E. Thorpe and Jasmin Divers},

doi = {10.2196/59217},

year  = {2025},

date = {2025-03-05},

urldate = {2025-03-05},

journal = {Journal of Medical Internet Research},

volume = {27},

pages = {e59217},

abstract = {The benefits and challenges of electronic health records (EHRs) as data sources for clinical and epidemiologic research have been well described. However, several factors are important to consider when using EHR data to study novel, emerging, and multifaceted conditions such as postacute sequelae of SARS-CoV-2 infection or long COVID. In this article, we present opportunities and challenges of using EHR data to improve our understanding of long COVID, based on lessons learned from the National Institutes of Health (NIH)-funded RECOVER (REsearching COVID to Enhance Recovery) Initiative, and suggest steps to maximize the usefulness of EHR data when performing long COVID research.},

keywords = {COVID-19, electronic health records, long COVID},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = { Ethnic and racial differences in children and young people with respiratory and neurological post-acute sequelae of SARS-CoV-2: an electronic health record-based cohort study from the RECOVER Initiative},

author = {Suchitra Rao and Rodrigo Azuero-Dajud and Vital Lorman and Jeremy Landeo-Gutierrez and Kyung E. Rhee and Julie Ryu and C. Kim and Megan Carmilani and Rachel S. Gross and Sindhu Mohandas and Srinivasan Suresh and L. Charles Bailey and Victor Castro and Yalini Senathirajah and Shari Esquenazi-Karonika and Shawn N. Murphy and Steve Caddle and Lawrence C. Kleinman and Leah Castro-Baucom and Carlos R. Oliveira and Jonathan D. Klein and Alicia Chung and Lindsay G. Cowell and Charisse Madlock-Brown and Carol Reynolds Geary and Marion R. Sills and Lorna E. Thorpe and Jacqueline Szmuszkovicz and Kelan G. Tantisira},

doi = {10.1016/j.eclinm.2024.103042},

year  = {2025},

date = {2025-01-02},

urldate = {2025-01-02},

journal = {eClinical Medicine},

volume = {80},

pages = {103042},

abstract = {Background: Children from racial and ethnic minority groups are at greater risk for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, but it is unclear whether they have increased risk for post-acute sequelae of SARS-CoV-2 (PASC). Our objectives were to assess whether the risk of respiratory and neurologic PASC differs by race/ethnicity and social drivers of health.



Methods: We conducted a retrospective cohort study of individuals <21 years seeking care at 24 health systems across the U.S, using electronic health record (EHR) data. Our cohort included those with a positive SARS-CoV-2 molecular, serology or antigen test, or with a COVID-19, multisystem inflammatory disease in children, or PASC diagnosis from February 29, 2020 to August 1, 2022. We identified children/youth with at least 2 codes associated with respiratory and neurologic PASC. We measured associations between sociodemographic and clinical characteristics and respiratory and neurologic PASC using odds ratios and 95% confidence intervals estimated from multivariable logistic regression models adjusted for other sociodemographic characteristics, social vulnerability index or area deprivation index, time period of cohort entry, presence and complexity of chronic respiratory (respectively, neurologic) condition and healthcare utilization.



Findings: Among 771,725 children in the cohort, 203,365 (26.3%) had SARS-CoV-2 infection. Among children with documented infection, 3217 children had respiratory PASC and 2009 children/youth had neurologic PASC. In logistic regression models, children <5 years (Odds Ratio [OR] 1.78, 95% CI 1.62-1.97), and of Hispanic White descent (OR 1.19, 95% CI 1.05-1.35) had higher odds of having respiratory PASC. Children/youth living in regions with higher area deprivation indices (OR 1.25, 95% CI 1.10-1.420 for 60-79th percentile) and with chronic complex respiratory conditions (OR 3.28, 95% CI 2.91-3.70) also had higher odds of respiratory PASC. In contrast, older (OR 1.57, 95% CI 1.40-1.77 for those aged 12-17 years), non-Hispanic White individuals and those with chronic pre-existing neurologic conditions (OR 2.04, 95% CI 1.78-2.35) were more likely to have a neurologic PASC diagnosis.



Interpretation: Racial and ethnic differences in healthcare utilization for neurologic and respiratory PASC may reflect social drivers of health and inequities in access to care.},

keywords = {COVID-19, long COVID, pediatrics, social determinants of health},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Prevalent Metformin Use in Adults With Diabetes and the Incidence of Long COVID: An EHR-Based Cohort Study From the RECOVER Program},

author = {Steven G. Johnson and Sajjad Abedian and Til Sturmer and Jared D. Huling and Colby Lewis and John B. Buse and Shari B. Brosnahan and Praveen C. Mudumbi and Kristine M. Erlandson and Grace A. McComsey and Jonathan Arnold and Talia D. Wiggen and Rachel Wong and Shawn N. Murphy and Clifford Rosen and Rainu Kaushal and Mark G. Weiner and Carolyn T. Bramante },

doi = {10.2337/DCa24-0032},

year  = {2024},

date = {2024-11-01},

urldate = {2024-11-01},

journal = {Diabetes Care},

volume = {47},

issue = {11},

pages = {1930-1940},

abstract = {Objective: Studies show metformin use before and during SARS-CoV-2 infection reduces severe COVID-19 and postacute sequelae of SARS-CoV-2 (PASC) in adults. Our objective was to describe the incidence of PASC and possible associations with prevalent metformin use in adults with type 2 diabetes mellitus (T2DM).



Research design and methods: This is a retrospective cohort analysis using the National COVID Cohort Collaborative (N3C) and Patient-Centered Clinical Research Network (PCORnet) electronic health record (EHR) databases with an active comparator design that examined metformin-exposed individuals versus nonmetformin-exposed individuals who were taking other diabetes medications. T2DM was defined by HbA1c ≥6.5 or T2DM EHR diagnosis code. The outcome was death or PASC within 6 months, defined by EHR code or computable phenotype.



Results: In the N3C, the hazard ratio (HR) for death or PASC with a U09.9 diagnosis code (PASC-U09.0) was 0.79 (95% CI 0.71-0.88; P < 0.001), and for death or N3C computable phenotype PASC (PASC-N3C) was 0.85 (95% CI 0.78-0.92; P < 0.001). In PCORnet, the HR for death or PASC-U09.9 was 0.87 (95% CI 0.66-1.14; P = 0.08), and for death or PCORnet computable phenotype PASC (PASC-PCORnet) was 1.04 (95% CI 0.97-1.11; P = 0.58). Incident PASC by diagnosis code was 1.6% metformin vs. 2.0% comparator in the N3C, and 2.1% metformin vs. 2.5% comparator in PCORnet. By computable phenotype, incidence was 4.8% metformin and 5.2% comparator in the N3C and 24.7% metformin vs. 26.1% comparator in PCORnet.



Conclusions: Prevalent metformin use is associated with a slightly lower incidence of death or PASC after SARS-CoV-2 infection. PASC incidence by computable phenotype is higher than by EHR code, especially in PCORnet. These data are consistent with other observational analyses showing prevalent metformin is associated with favorable outcomes after SARS-CoV-2 infection in adults with T2DM.},

keywords = {COVID-19, diabetes mellitus, long COVID},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Long COVID incidence in adults and children between 2020 and 2023: a real-world data study from the RECOVER Initiative},

author = {Hannah L. Mandel and Yun J. Yoo and Andrea J. Allen and Sajjad Abedian and Zoe Verzani and Elizabeth W. Karlson and Lawrence C. Kleinman and Praveen C. Mudumbi and Carlos R. Oliveira and Jennifer A. Muszynski and Rachel S. Gross and Thomas W. Carton and C. Kim and Emily Taylor and Heekyong Park and Jasmin Divers and J. Daniel Kelly and Jonathan Arnold and Carol Reynolds Geary and Chengxi Zang and Kelan G. Tantisira and Kyung E. Rhee and Michael Koropsak and Sindhu Mohandas and Andrew Vasey and Mark G. Weiner and Abu S. M. Mosa and Melissa Haendel and Christopher G. Chute and Shawn N. Murphy and Lisa O'Brien and Jacqueline Szmuszkovicz and Nicholas Guthe and Jorge L. Santana and Aliva De and Amanda L. Bogie and Katia C. Halabi and Lathika Mohanraj and Patricia A Kinser and Samuel E. Packard and Katherine R. Tuttle and Lorna E. Thorpe and Richard A. Moffitt},

doi = {10.21203/rs.3.rs-4124710/v1},

year  = {2024},

date = {2024-04-26},

journal = {Research Square},

pages = {rs.3.rs-4124710},

abstract = {Estimates of post-acute sequelae of SARS-CoV-2 infection (PASC) incidence, also known as Long COVID, have varied across studies and changed over time. We estimated PASC incidence among adult and pediatric populations in three nationwide research networks of electronic health records (EHR) participating in the RECOVER Initiative using different classification algorithms (computable phenotypes). Overall, 7% of children and 8.5%-26.4% of adults developed PASC, depending on computable phenotype used. Excess incidence among SARS-CoV-2 patients was 4% in children and ranged from 4-7% among adults, representing a lower-bound incidence estimation based on two control groups - contemporary COVID-19 negative and historical patients (2019). Temporal patterns were consistent across networks, with peaks associated with introduction of new viral variants. Our findings indicate that preventing and mitigating Long COVID remains a public health priority. Examining temporal patterns and risk factors of PASC incidence informs our understanding of etiology and can improve prevention and management.},

keywords = {COVID-19, long COVID},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Data-driven analysis to understand long COVID using electronic health records from the RECOVER initiative},

author = {Chengxi Zang and Yongkang Zhang and Jie Xu and Jiang Bian and Dmitry Morozyuk and Edward J. Schenck and Dhruv Khullar and Anna Starikovsky Nordvig and Elizabeth A. Shenkman and Russell L. Rothman and Jason P. Block and Kristin Lyman and Mark G. Weiner and Thomas W. Carton and Fei Wang and Rainu Kaushal },

doi = {10.1038/s41467-023-37653-z},

year  = {2023},

date = {2023-04-07},

urldate = {2023-04-07},

journal = {Nature Communications},

volume = {14},

number = {1948},

issue = {1},

abstract = {Recent studies have investigated post-acute sequelae of SARS-CoV-2 infection (PASC, or long COVID) using real-world patient data such as electronic health records (EHR). Prior studies have typically been conducted on patient cohorts with specific patient populations which makes their generalizability unclear. This study aims to characterize PASC using the EHR data warehouses from two large Patient-Centered Clinical Research Networks (PCORnet), INSIGHT and OneFlorida+, which include 11 million patients in New York City (NYC) area and 16.8 million patients in Florida respectively. With a high-throughput screening pipeline based on propensity score and inverse probability of treatment weighting, we identified a broad list of diagnoses and medications which exhibited significantly higher incidence risk for patients 30-180 days after the laboratory-confirmed SARS-CoV-2 infection compared to non-infected patients. We identified more PASC diagnoses in NYC than in Florida regarding our screening criteria, and conditions including dementia, hair loss, pressure ulcers, pulmonary fibrosis, dyspnea, pulmonary embolism, chest pain, abnormal heartbeat, malaise, and fatigue, were replicated across both cohorts. Our analyses highlight potentially heterogeneous risks of PASC in different populations.},

keywords = {COVID-19, long COVID},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Racial/Ethnic Disparities in Post-acute Sequelae of SARS-CoV-2 Infection in New York: an EHR-Based Cohort Study from the RECOVER Program},

author = {Dhruv Khullar and Yongkang Zhang and Chengxi Zang and Zhenxing Xu and Fei Wang and Mark G. Weiner and Thomas W. Carton and Russell L. Rothman and Jason P. Block and Rainu Kaushal},

doi = {10.1007/s11606-022-07997-1},

year  = {2023},

date = {2023-02-16},

journal = {Journal of General Internal Medicine},

volume = {38},

issue = {5},

pages = {1127-1136},

abstract = {Background: Compared to white individuals, Black and Hispanic individuals have higher rates of COVID-19 hospitalization and death. Less is known about racial/ethnic differences in post-acute sequelae of SARS-CoV-2 infection (PASC).



Objective: Examine racial/ethnic differences in potential PASC symptoms and conditions among hospitalized and non-hospitalized COVID-19 patients.



Design: Retrospective cohort study using data from electronic health records.



Participants: 62,339 patients with COVID-19 and 247,881 patients without COVID-19 in New York City between March 2020 and October 2021.



Main measures: New symptoms and conditions 31-180 days after COVID-19 diagnosis.



Key results: The final study population included 29,331 white patients (47.1%), 12,638 Black patients (20.3%), and 20,370 Hispanic patients (32.7%) diagnosed with COVID-19. After adjusting for confounders, significant racial/ethnic differences in incident symptoms and conditions existed among both hospitalized and non-hospitalized patients. For example, 31-180 days after a positive SARS-CoV-2 test, hospitalized Black patients had higher odds of being diagnosed with diabetes (adjusted odds ratio [OR]: 1.96, 95% confidence interval [CI]: 1.50-2.56, q<0.001) and headaches (OR: 1.52, 95% CI: 1.11-2.08, q=0.02), compared to hospitalized white patients. Hospitalized Hispanic patients had higher odds of headaches (OR: 1.62, 95% CI: 1.21-2.17, q=0.003) and dyspnea (OR: 1.22, 95% CI: 1.05-1.42, q=0.02), compared to hospitalized white patients. Among non-hospitalized patients, Black patients had higher odds of being diagnosed with pulmonary embolism (OR: 1.68, 95% CI: 1.20-2.36, q=0.009) and diabetes (OR: 2.13, 95% CI: 1.75-2.58, q<0.001), but lower odds of encephalopathy (OR: 0.58, 95% CI: 0.45-0.75, q<0.001), compared to white patients. Hispanic patients had higher odds of being diagnosed with headaches (OR: 1.41, 95% CI: 1.24-1.60, q<0.001) and chest pain (OR: 1.50, 95% CI: 1.35-1.67, q < 0.001), but lower odds of encephalopathy (OR: 0.64, 95% CI: 0.51-0.80, q<0.001).



Conclusions: Compared to white patients, patients from racial/ethnic minority groups had significantly different odds of developing potential PASC symptoms and conditions. Future research should examine the reasons for these differences.},

keywords = {COVID-19, long COVID, racial/ethnic disparities},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Identifying environmental risk factors for post-acute sequelae of SARS-CoV-2 infection: An EHR-based cohort study from the recover program},

author = {Yongkang Zhang and Hui Hu and Vasilios Fokaidis and Colby Lewis and Jie Xu and Chengxi Zang and Zhenxing Xu and Fei Wang and Michael Koropsak and Jiang Bian and Jaclyn Hall and Russell L. Rothman and Elizabeth A. Shenkman and Wei-Qi Wei and Mark G. Weiner and Thomas W. Carton and Rainu Kaushal},

doi = {10.1016/j.envadv.2023.100352},

year  = {2023},

date = {2023-02-08},

urldate = {2023-02-08},

journal = {Environmental Advances},

volume = {11},

number = {100352},

abstract = {Post-acute sequelae of SARS-CoV-2 infection (PASC) affects a wide range of organ systems among a large proportion of patients with SARS-CoV-2 infection. Although studies have identified a broad set of patient-level risk factors for PASC, little is known about the association between "exposome"-the totality of environmental exposures and the risk of PASC. Using electronic health data of patients with COVID-19 from two large clinical research networks in New York City and Florida, we identified environmental risk factors for 23 PASC symptoms and conditions from nearly 200 exposome factors. The three domains of exposome include natural environment, built environment, and social environment. We conducted a two-phase environment-wide association study. In Phase 1, we ran a mixed effects logistic regression with 5-digit ZIP Code tabulation area (ZCTA5) random intercepts for each PASC outcome and each exposome factor, adjusting for a comprehensive set of patient-level confounders. In Phase 2, we ran a mixed effects logistic regression for each PASC outcome including all significant (false positive discovery adjusted p-value < 0.05) exposome characteristics identified from Phase I and adjusting for confounders. We identified air toxicants (e.g., methyl methacrylate), particulate matter (PM2.5) compositions (e.g., ammonium), neighborhood deprivation, and built environment (e.g., food access) that were associated with increased risk of PASC conditions related to nervous, blood, circulatory, endocrine, and other organ systems. Specific environmental risk factors for each PASC condition and symptom were different across the New York City area and Florida. Future research is warranted to extend the analyses to other regions and examine more granular exposome characteristics to inform public health efforts to help patients recover from SARS-CoV-2 infection.},

keywords = {air pollution, built environment, COVID-19, exposome, long COVID, neighborhood deprivation},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Identifying Contextual and Spatial Risk Factors for Post-Acute Sequelae of SARS-CoV-2 Infection: An EHR-based Cohort Study from the RECOVER Program},

author = {Yongkang Zhang and Hui Hu and Vasilios Fokaidis and Colby Lewis and Jie Xu and Chengxi Zang and Zhenxing Xu and Fei Wang and Michael Koropsak and Jiang Bian and Jaclyn Hall and Russell L. Rothman and Elizabeth A. Shenkman and Wei-Qi Wei and Mark G. Weiner and Thomas W. Carton and Rainu Kaushal},

doi = {10.1101/2022.10.13.22281010},

year  = {2022},

date = {2022-10-13},

journal = {medRxiv},

abstract = {Post-acute sequelae of SARS-CoV-2 infection (PASC) affects a wide range of organ systems among a large proportion of patients with SARS-CoV-2 infection. Although studies have identified a broad set of patient-level risk factors for PASC, little is known about the contextual and spatial risk factors for PASC. Using electronic health data of patients with COVID-19 from two large clinical research networks in New York City and Florida, we identified contextual and spatial risk factors from nearly 200 environmental characteristics for 23 PASC symptoms and conditions of eight organ systems. We conducted a two-phase environment-wide association study. In Phase 1, we ran a mixed effects logistic regression with 5-digit ZIP Code tabulation area (ZCTA5) random intercepts for each PASC outcome and each contextual and spatial factor, adjusting for a comprehensive set of patient-level confounders. In Phase 2, we ran a mixed effects logistic regression for each PASC outcome including all significant (false positive discovery adjusted p-value < 0.05) contextual and spatial characteristics identified from Phase I and adjusting for confounders. We identified air toxicants (e.g., methyl methacrylate), criteria air pollutants (e.g., sulfur dioxide), particulate matter (PM 2.5 ) compositions (e.g., ammonium), neighborhood deprivation, and built environment (e.g., food access) that were associated with increased risk of PASC conditions related to nervous, respiratory, blood, circulatory, endocrine, and other organ systems. Specific contextual and spatial risk factors for each PASC condition and symptom were different across New York City area and Florida. Future research is warranted to extend the analyses to other regions and examine more granular contextual and spatial characteristics to inform public health efforts to help patients recover from SARS-CoV-2 infection.},

keywords = {COVID-19, long COVID},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Machine Learning for Identifying Data-Driven Subphenotypes of Incident Post-Acute SARS-CoV-2 Infection Conditions with Large Scale Electronic Health Records: Findings from the RECOVER Initiative},

author = {Hao Zhang and Chengxi Zang and Zhenxing Xu and Yongkang Zhang and Jie Xu and Jiang Bian and Dmitry Morozyuk and Dhruv Khullar and Yiye Zhang and Anna Starikovsky Nordvig and Edward J. Schenck and Elizabeth A. Shenkman and Russell L. Rothman and Jason P. Block and Kristin Lyman and Mark G. Weiner and Thomas W. Carton and Fei Wang and Rainu Kaushal},

doi = {https://doi.org/10.1101/2022.05.21.22275412},

year  = {2022},

date = {2022-06-08},

urldate = {2022-06-08},

journal = {medRxiv},

abstract = {The post-acute sequelae of SARS-CoV-2 infection (PASC) refers to a broad spectrum of symptoms and signs that are persistent, exacerbated, or newly incident in the post-acute SARS-CoV-2 infection period of COVID-19 patients. Most studies have examined these conditions individually without providing concluding evidence on co-occurring conditions. To answer this question, this study leveraged electronic health records (EHRs) from two large clinical research networks from the national Patient-Centered Clinical Research Network (PCORnet) and investigated patients' newly incident diagnoses that appeared within 30 to 180 days after a documented SARS-CoV-2 infection. Through machine learning, we identified four reproducible subphenotypes of PASC dominated by blood and circulatory system, respiratory, musculoskeletal and nervous system, and digestive system problems, respectively. We also demonstrated that these subphenotypes were associated with distinct patterns of patient demographics, underlying conditions present prior to SARS-CoV-2 infection, acute infection phase severity, and use of new medications in the post-acute period. Our study provides novel insights into the heterogeneity of PASC and can inform stratified decision-making in the treatment of COVID-19 patients with PASC conditions.},

keywords = {COVID-19, long COVID},

pubstate = {published},

tppubtype = {article}

}