Researching COVID to Enhance Recovery (RECOVER) is an NIH-supported initiative that “brings together clinicians, scientists, caregivers, patients, and community members to understand, treat, and prevent Long COVID”.  Areas of research funded by this initiative include autopsy and pathology studies, clinical trials, prospective observational cohort studies, pathobiology studies, and observational studies using “Real World Data” (RWD) from the electronic health records of over 80 institutions.  

 

The iTHRIV informatics team and colleagues in the School of Data Science are contracted to support the National COVID Cohort Collaborative (N3C) arm of the RECOVER RWD initiative.  The UVA team provides project leadership, informatics infrastructure support, performs NIH query analytics, co-authors related manuscripts, and supports interactions with policy makers.  As one of the N3C RECOVER RWD leads, iTHRIV Director of Informatics Johanna Loomba serves in the query workgroup that shapes high level query topics into executable specifications. Johanna liaises with team members from other participating institutions and co-directs the multidisciplinary UVA team with Professor Don Brown, co-PI of iTHRIV.  The UVA analytics team includes staff data scientists (Andrea Zhou and Suchetha Sharma) and graduate students from the School of Data Science (Saurav Sengupta and Isabelle Liu) and Systems Engineering (Sihang Jiang).  In addition to executing NIH-prioritized queries, the UVA team has made extensive contributions to core analytic components such as cohort identification, derived fact pipelines, and helping to evolve computable Long COVID subtypes based on common symptom clusters. Careful design and implementation of these logical components is essential to rigorous research when working with Real World Data which is collected through the course of care rather than through controlled prospective research.

​

​

​

​

​

​

​

​

​

 

 

​

Screenshot of the Team 

​

The scientific impact of the iTHRIV and SDS RECOVER work is reflected in our resulting manuscripts that span a range of topics including Long COVID risk factors (1-5), correlation with COVID vaccinations (6) and COVID reinfections (7), drug efficacy in the prevention of Long COVID (8), disparities in Long COVID coding practices (9), and Long COVID computable phenotyping (10,11).
 

The UVA iTHRIV and SDS team also assisted Virginia Senator Tim Kaine’s office in submitting a query to RECOVER and performed the resulting analysis (12). Our team provided support for a January 2024 N3C RECOVER testimony before the Senate Health, Education, Labor, and Pensions (HELP) Committee.  The HELP Committee has recently released a draft legislative proposal, the Long COVID Moonshot Act (13), that would provide more funding to support national research in this area.  This project is an example of how our iTHRIV data science and informatics expertise is helping to shape health policy and is using data to improve health. 

​

​

References:

1. Sengupta, S., Loomba, J., Sharma, S., Chapman, S. A., & Brown, D. E. (2023). Determining risk factors for long COVID using positive unlabeled learning on electronic health records data from NIH N3C. 2023 International Conference on Machine Learning and Applications (ICMLA), 430–436. https://doi.org/10.1109/icmla58977.2023.00066 

2. Sengupta, S., Loomba, J., Sharma, S., Brown, D. E., ... Hong, S. (2022). Analyzing historical diagnosis code data from NIH N3C and recover programs using deep learning to determine risk factors for long covid. 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2797–2802. https://doi.org/10.1109/bibm55620.2022.9994851

3. Hill, E. L., Mehta, H. B., Sharma, S., … Cathey, E., Loomba, J., … Bennett, T. D. (2023). Risk factors associated with post-acute sequelae of SARS-COV-2: An N3C and NIH recover study. BMC Public Health, 23(1). https://doi.org/10.1186/s12889-023-16916-w 

4. Jiang, S., Loomba, J., Sharma, S., & Brown, D. (2022). Vital measurements of hospitalized COVID-19 patients as a predictor of long COVID: An EHR-based Cohort Study from the recover program in N3C. 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 3023–3030. https://doi.org/10.1109/bibm55620.2022.9995311

5. Mandel, H.L., Colleen, G., Abedian, S., … Loomba, J., … Zhou, A., Thorpe, L. E. (2023). Risk of post-acute sequelae of SARS-COV-2 infection associated with pre-coronavirus disease obstructive sleep apnea diagnoses: An electronic health record-based analysis from the recover initiative. SLEEP, 46(9). https://doi.org/10.1093/sleep/zsad126 

6. Brannock, M.D., Chew, R.F., Preiss, A.J., … Zhou, A.G., … Chute, C.G. (2023). Long covid risk and pre-COVID vaccination in an EHR-based Cohort Study from the recover program. Nature Communications, 14(1). https://doi.org/10.1038/s41467-023-38388-7 

7. Hadley, E., Yoo, Y. J., Patel, S., Zhou, A., … Loomba, J., … Moffitt, R. (2023). SARS-COV-2 reinfection is preceded by unique biomarkers and related to initial infection timing and severity: An N3C recover EHR-based Cohort Study. Communications Medicine. https://doi.org/10.1101/2023.01.03.22284042 

8. Preiss, A., Bhatia, A., Aragon, L. V., … Zhou, A., … Pfaff, E. (2024). Effect of PAXLOVID treatment during acute COVID-19 on long COVID onset: An EHR-based target trial emulation from the N3C and recover consortia. medRxiv : The Preprint Server for Health Sciences. https://doi.org/10.1101/2024.01.20.24301525 

9. Pfaff, E. R., Madlock-Brown, C., Baratta, J. M., …Loomba, J., … Haendel, M. (2023). Coding Long Covid: Characterizing a new disease through an ICD-10 lens. BMC Medicine, 21(1), 1–13. https://doi.org/10.1186/s12916-023-02737-6 

10. Crosskey, M., McIntee, T., Preiss, S., … Loomba, J., … Pfaff, E. (2023). Reengineering a machine learning phenotype to adapt to the changing COVID-19 landscape: A study from the N3C and recover consortia. medRxiv : The Preprint Server for Health Sciences. https://doi.org/10.1101/2023.12.08.23299718 

11. Reese, J. T., Blau, H., Casiraghi, E., Bergquist, T., Loomba, J. J., … Robinson, P. N. (2023). Generalisable Long covid subtypes: Findings from the NIH N3C and recover programmes. eBioMedicine, 87, 104413. https://doi.org/10.1016/j.ebiom.2022.104413 

12. Loomba, J., & Sharma, S. (2022, December 22). New Economic Instability Post-covid-19 infection: A Year 1 Quarter 4 PASC recover EHR-based query report from N3C. Zenodo. https://zenodo.org/records/7469477#.Y-vmg8fMKHs 

13.  Sanders, B. (2024, April 9). The Long COVID Moonshot Act. Senate.gov. https://www.sanders.senate.gov/wp- 

       content/uploads/4.9.2024-Factsheet_The-Long-COVID-Moonshot-Act.pdf