Post-Acute Sequalae of SARS-CoV-2 Infection (PASC), also known as Long COVID, can affect anyone, including children, and it can develop in people who had asymptomatic, mild, or severe COVID-19. To complement the National Institutes of Health (NIH) other Long COVID research initiatives, like Researching COVID to Enhance Recovery (RECOVER), the RADx-Radical (RADx-rad) program at the NIH is launching the Long COVID Computational Challenge (L3C). NIH designed this challenge to support creative data-driven solutions that meaningfully advance the current understanding of the risks of developing PASC/Long COVID. The total prize for this Challenge will be up to $500,000.
Despite ongoing research on the prevalence, duration, and clinical outcomes of PASC/Long COVID, a significant need remains in identifying prognostic factors that can reliably support clinical decisions for the management and prevention of PASC/Long COVID in SARS-COV-2 infected individuals. Understanding risk factors may also help clinicians better understand the underlying etiology of PASC/Long COVID. Advanced development of software tools and computing capacity has allowed artificial intelligence (AI)/machine learning (ML) approaches that are increasingly demonstrating the potential to provide insight into patient-level data from large amounts of data, to better understand the long-term effects of SARS-CoV-2 on patients.
The primary objective of the Long COVID Computational Challenge (L3C) is to focus on the prognostic problem by developing AI/ML models and algorithms that serve as open-source tools for using structured medical records to identify which patients infected with SARS-CoV-2 have a high likelihood of developing PASC/Long COVID.
Challenge participants are expected to develop, train, and test their models to aid in predicting the susceptibility to and likelihood of developing PASC/Long COVID in patients with SARS-CoV-2 infection. Challenge participants will utilize de-identified electronic health record (EHR) data available through NCATS’s National COVID Cohort Collaborative (N3C) Data Enclave, a central, harmonized data repository that represents EHR data from over 74 health centers across the U.S. To protect patient privacy, de-identified data provides information useful to researchers without revealing any information that could identify individual patients. The N3C enclave uses the Observational Medical Outcomes Partnership (OMOP) common data model version 5.3 (https://ohdsi.github.io/CommonDataModel/cdm53.html) which facilitates reproducibility and interoperability.
Future funding opportunities related to this topic may become available beyond this Challenge announcement depending on the state of the science, public health need, and availability of funds for further development of models and algorithms into clinical decision support to predict the development of PASC/Long COVID and improve understanding of clinical outcomes and the effectiveness of early interventions in preventing PASC/Long COVID.
Dates:
- Challenge Launch: August 25, 2022
- Challenge Webinar: Sep 21, 2022 at 03:00 PM Eastern Time
- Submission Start/End: August 15- December 15, 2022
- Judging Start/End: December 16, 2022 - February 15, 2023
- Winner Announced: March 2023
Attend the Application Technical Assistance Webinar on Sep 21, 2022 03:00 PM in Eastern Time (US and Canada). Register here: Webinar Registration - Zoom
Please send your inquiries to RADxLongCOVIDChallengeAdmin@synapse.org.