NCATS CTSA N3C
Download as PPTX, PDF0 likes200 views
The National COVID Cohort Collaborative (N3C) is creating a comprehensive clinical dataset on COVID-19 to enable machine learning algorithms, predictive modeling, and drug discovery. It aims to maximize data sharing and access through a centralized data enclave. Researchers from academic and commercial institutions can access limited datasets, while citizens can access synthetic data. The N3C tracks data provenance and requires researchers to attribute all outcomes to data contributors. It is organized into several workstreams on data ingestion, phenotypes, analytics, and governance.
NCATS CTSA N3C
- 1. National COVID Cohort Collaborative (N3C) NCATS CTSA COVID-19 Data Science Enclave Warren Kibbe @data2health @ncats_nih_g ov https://ncats.nih.gov/n3 c https://covid.cd2h.org/ @wakibbe
- 2. ● ML algorithms (diagnosis, triage, predictive, etc.) ● Best practices for resource allocation ● Drug discovery ● Reduced disease severity ● Coordinate our efforts to maximize efficiency All these things require the creation of a comprehensive clinical data set This pandemic highlights urgent needs
- 3. DUA Access Principles Access Principles: “Share widely and wisely” The end-goal is broad access, including: ● Academic and Commercial ● Credentialed researchers* (limited data set, LDS) and Individual / “citizen scientists” (Synthetic Data) ● Domestic ● Directed to COVID-Related research ● Activities in the N3C Enclave are recorded and can be audited ● Disclosure of research results to the N3C Enclave for the public good ● Contributor Attribution ● No download of Limited Data Set ● Access authorization must be renewed annually *Credentialed researchers are researchers from academic or commercial institutions who have completed Human Subjects Protection training
- 4. Architecting Attribution in the N3C The N3C Collaborative analytics platform will support robust tracking of provenance and attribution; the DUA will require attribution of all scientific outcomes to everyone who contributed.cd2h.org/attribution Artifact Contribution Agent Qualified contribution Contribution made to Contribution made by Qualified contribution Any research artifact or product, such as data, data quality tool, terminology, algorithm, or software The role of the person or organization in the creation of the artifact The person, group and/or organization
- 5. FDA Mitra Rocca Scott Gideon Wei Chen NIDDK Robert Star NIGMS Ming Lee NCATS ITRB Sam Michael Mariam Deacy Gary Berkson Josephine Kennedy Usman Sheikh Mark Backus Nam Ngo Amit Virakatmath Keats Kirsch Sulochana Nunna Rafael Fuentes Reid Simon Biju Mathew Tim Mierzwa Ke Wang Kalle Virtaneva Partners, Teams, Collaborators NCATS Chris Austin Joni Rutter Mike Kurilla Clare Schmitt Ken Gersing Xinzhi Zhang Erica Rosemond Sam Bozzette Lili Portilla Chris Dillon Penny Burgoon Emily Marti Meredith Temple- O’Connor Sam Jonson Christine Cutillo Nicole Garbarini NIH & HHS Partners NCI Janelle Cortner Stephen Hewitt Denise Warzel CD2H OHSU/OSU Melissa Haendel Anita Walden Julie McMurry Moni Munoz-Torres Andrea Volz Connor Cook Racquel Dietz Andrew Neumann Rich Lorimor Sage Bionetworks Justin Guinney James Eddy U of Iowa: Dave Eichmann Alexis Graves Northwestern: Kristi Holmes Justin Starren Lisa O’Keefe Washington U. Philip Payne Albert Lai Tom Dillon CD2H U. Of Washington Adam Wilcox Liz Zampino Johns Hopkins U Chris Chute Tricia Francis Jax Labs Peter Robinson Scripps Chunlei Wu Teams Phenotype & Acquisition Emily Pfaff, UNC ACT Michele Morris, Pitt Shyam Visweswaran, Pitt Shawn Murphy HRD OMOP Kristin Kostka, IQVIA Karthik Natarajan, Columbia Clare Blacketer JNJ PCORI Kellie Walters, UNC Robert Bradford, UNC Marshall Clark, UNC Adam Lee, UNC Evan Colmenares, UNC TriNetX Matvey Palchuk Lora Lingrey Teams Governance Sage Bionetworks John Wilbanks Christine Suver Data Harmonization JHU Davera Gabriel Stephanie Hong Harold Lehmann Tanner Zhang Richard Zhu SAMVIT Smita Hastak Charles Yaghmour NCATS Raju Hemadri Nancy Nurthen Sai Manjula Adeptia Sandeep Naredla Teams Analytics Warren Kibbe, Duke Heidi Sprait, UTMB Tell Bennett, U of CO Andrew Williams, Tufts Joel Saltz, SBU Janos Hajagos, SBU Richard Moffitt, SBU Tahsin Kurc, SBU Palantir Nabeel Qureshi Andrew Girvin Amin Manna Synthetic Data Regenstrief Peter Embi MDClone Daniel Blumenthal Hovav Dror Luz Erez Josh Rubel Microsoft Allison T Rodriguez Kenji Takeda
- 6. Data partnership & governance Phenotype & Data acquisition Data ingest & harmonizati Collaborative analytics & FAIR Sharing/Credit N3C Overview HarmonizeIngest Collaborate (Analytics Platform) OMO P LimitedDataSets Limited/Safe Harbor Data Sets
- 7. Common Data Model Harmonization First Stage Ingestion ● Unpack Zip’ed csv Files. Check data manifests ● Reconstitute into native CDM formats ● Hybrid Data Quality checks adapting OHDSI Data Quality Dashboard Workflow Data Quality Dashboard (shared with site) ✔️ ✔️ ✔️
- 8. Discover Dashboards Reports Studies Researchers Analyze Build Two-factor Auth DAC NCATS Cloud Palantir NCATS Translator Collaborative Analytics - N3C Secure Data Enclave
- 10. Predictive Modeling: Risk of Ventilation and AKI Random forest model trained on 200 COVID-19 patients, 100 of whom required ventilation, and 100 did not. It performs well, with an AUC of 0.85. Shown are the top features in the model predicting ventilator usage as an outcome. Using these features, we are able to see separation in a PCA plot between the ventilator population in orange and the non- ventilator population in blue.
- 11. N3C Community Workstreams NCATS N3C website: ncats.nih.gov/n3c CD2H N3C website: covid.cd2h.org Hub Partnership packet: https://covid.cd2h.org/partnership_welcome_packet Onboarding to N3C: bit.ly/cd2h-onboarding-form
- 12. Join the conversation Onboarding to N3C: bit.ly/cd2h-onboarding-form Joining Workstreams: N3C Data Ingestion & Harmonization Workstream Slack Channel Harmonization Google Group Harmonization N3C Phenotype & Data Acquisition Workstream Slack Channel Phenotype Google Group Phenotype N3C Collaborative Analytics Workstream Slack Channel Analytics Google Group Analytics N3C Data Partnership & Governance Workstream Slack Channel Governance Google Group Governance N3C Synthetic Data Workstream Slack Channel Synthetic Data Google Group Synthetic Data Additional Information: Onboarding N3C, Slack, Google | Finding and Joining a Google Group
- 13. Thank you!