N3C Milestones, Efforts & Activities

N3C Milestones, Efforts & Activities

Michael G. Kurilla, MD, PhD - Director of NCATS Clinical Innovation

During the past several months (there are times when the weeks feel like days and then others when the days feel like months), we have been working to address the ongoing COVID-19 pandemic by creating a centralized, secure, cloud-based clinical data portal. To this end, NCATS recently launched the National COVID Cohort Collaborative (N3C) to build a centralized national data resource that focuses the power of Big Data harnessed from our large network of CTSA hubs and affiliated institutions.

In this month’s blog, I wanted to provide our CTSA Program community an update about N3C’s efforts, milestones, activities, and some key resources.

N3C is a cloud-based COVID analytics platform, a collaboration between NCATS, the CTSA Program, our Coordinating Center for Data to Health (CD2H), along with multiple federated clinical networks PCORnet, OHDSI, ACT/i2b2, and TriNetX.  This effort is not only an exemplar of team science with over 500 contributing individuals, but it highlights the value and power of a readily available national network of academic and healthcare institutions through our well-established CTSA Program.

With N3C, the goal is to collect and harmonize electronic clinical, laboratory and diagnostic data from hospitals and health care institutions around the nation following the highest standards for data security and confidentiality. This real-world data will allow us to evaluate both short-term as well as long-term consequences of COVID-19, including related co-morbidities, therapeutic approaches, and risk factors that can predict better (or worse) outcomes.

Only with the support of our CTSA consortium and N3C partners and collaborators can we achieve our goal of having a centralized national data repository and analytics platform with the power of Big Data to help assess, predict, and identify the most successful approaches that could have direct impact on curbing this “yet to be cracked” pandemic.    

We continue counting on all of you!

Milestones Achieved to Date:

  • APRIL 13
    • American Medical Informatics Association (AMIA) Kickoff
  • APRIL 20
    • Four workstreams launched
    • Central IRB established 
  • APRIL 27
    • Data Transfer Agreement (DTA) finalized by NCATS
    • COVID-19 phenotype v1.0 published
  • MAY 4
    • N3C platform provisioned in NCATS cloud
    • 1st DTA signed
    • Analytics platform training initiated
  • MAY 11
    • NCATS Director, Dr. Christopher P. Austin held N3C community meeting
    • N3C phenotype & extract scripts published
    • N3C data harmonization maps created
  • MAY 18
    • 13 DTAs signed
    • 500+ members participate in N3C
    • 4 sites data ingestion capable
    • 49 people trained on analytics software
    • 1st machine learning model tested in platform: intubation & acute kidney injury
    • Data harmonization pipeline built
  • MAY 25
    • 26 DTAs signed
    • 6 sites data ingestion capable
    • Completion of 3/4 Common Data Model (CDM) Mapping completed
    • NIGMS Institutional Development Award (IDeA) N3C NOSI released
  • JUNE 6
    • 30 DTAs signed
    • Data Use Agreement (DUA) and Data Use Request (DUR) drafts completed
    • Established Natural Language Processing (NLP) Working Group
  • June 8
    • 38 DTAs signed
    • 70 requests
    • 16 completed IRB
    • 7 sites data ingestion capable
    • Draft of 1st publication
    • Initial architecture de-duplication process and the linkage of different types of data proposed
  • June 15th – 22nd
    • Synthetic Data Working Group established
    • Submission of 1st manuscript to JAMIA
    • Clinical data and image linkage pilot project initiated
    • 45 DTAs signed
    • 9 sites data ingestion capable
    • All common data mapping completed

N3C Resources and Contact Information:

“People who deny basic scientific truth should also be denied penicillin and horseless carriages." -Josh Whedon