CHoRUS RO-Crate Package

Version: 1.0 Beta

Datasheet Summary

The Collaborative Hospital Repository Uniting Standards (CHoRUS) for Clinical Care AI is a clinical data network developing a flagship multi-hospital, multimodal, high-resolution dataset under the NIH Bridge2AI program. CHoRUS harmonizes electronic health record (EHR) data, imaging, high-resolution physiologic signals (including telemetry data and EEG where available), and tokenized note and report text (via OHNLP toolkit) with raw text retained locally across participating institutions using... [read full description]

Dataset Statistics
Total Data Volume: 1.2 tb
Total Files: N/A
Access Data
AI-Readiness Score (View Details)
Fairness
4/4
Provenance
4/4
Characterization
4/5
Explainability
3/3
Ethics
4/4
Sustainability
4/4
Computability
4/4
Overall
96%

Release Overview

ROCrate ID
ark:59853/rocrate-chorus-ro-crate-package
DOI
Release Date
03/04/2026
Size
1.2 tb
Description
The Collaborative Hospital Repository Uniting Standards (CHoRUS) for Clinical Care AI is a clinical data network developing a flagship multi-hospital, multimodal, high-resolution dataset under the NIH Bridge2AI program. CHoRUS harmonizes electronic health record (EHR) data, imaging, high-resolution physiologic signals (including telemetry data and EEG where available), and tokenized note and report text (via OHNLP toolkit) with raw text retained locally across participating institutions using standardized data models and governance frameworks. The repository is designed to enable secure, auditable, and reproducible artificial intelligence (AI) research to improve recovery from acute illness. Data are curated within a NIST 800-53–aligned secure enclave architecture with role-based access controls, audit logging, and controlled-access governance review. CHoRUS supports AI model development, validation, benchmarking, and translational research while maintaining compliance with HIPAA and NIH data-sharing policies.
Authors
Eric S. Rosenthal(1), Rishikesan Kamaleswaran(2), Yulia Levites Strekalova(3), Andrew E. Williams(4), Ashley Cordes(5), Ishan C. Williams(6), Parisa Rashidi(3), Barbara J. Evans(3), J. Randall Moorman(6), Soojin Park(7), Edilberto Amorim(8), Paul M. Vespa(9), Xiaoqian Jiang(10), Hongfang Liu(10), Mihai V. Podgoreanu(2), Vitaly Herasevich(11), Mark Wainwright(12), Andrew J. Barros(6), Brynne A. Sullivan(6), Michael J. Young(1), Marta Alvarez(4), Polina Talapova(4), Jennifer A. Muszynski(13), Alasdair Gent(2), Delgersuren Bold(14), Manlik Kwong(4), Dileep Gunda(14), Jackie Le(1), India Loar(6), Brian J. Gow(15), Heidi Schmidt(1), Jared Houghtaling(4), Robert T. Miller(4), Timothy Clark (6), William B. Ashe(6), Tony C. Pan(14), Tom J. Pollard(15), Ciera McCrary(1), Azra Bihorac(3), Xiao Hu(14), Gilles Clermont(6) on behalf of the CHoRUS Investigators (1) Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA (2) Duke University, Durham, North Carolina, USA (3) University of Florida, Gainesville, Florida, USA (4) Tufts CTSI / Tufts Medical Center, Boston, Massachusetts, USA (5) University of Oregon, Eugene, Oregon, USA (6) University of Virginia, Charlottesville, Virginia, USA (7) Columbia University Irving Medical Center, New York, New York, USA (8) University of California, San Francisco, San Francisco, California, USA (9) David Geffen School of Medicine at UCLA, Los Angeles, California, USA (10) McWilliams School of Biomedical Informatics, UTHealth Houston, Houston, Texas, USA, Mayo Clinic, Rochester, Minnesota, USA (11) Mayo Clinic, Rochester, Minnesota, USA (12) Seattle Children’s Hospital, Seattle, Washington, USA (13) Nationwide Children’s Hospital / The Ohio State University, Columbus, Ohio, USA (14) Emory University, Atlanta, Georgia, USA (15) Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
Publisher
B2AI CHoRUS
Principal Investigator
Eric Rosenthal, EROSENTHAL@mgh.harvard.edu
Contact Email
Data Governance Committee
Eric Rosenthal, EROSENTHAL@mgh.harvard.edu
Ethical Review
Eric S. Rosenthal, Michael J. Young, Ishan Williams, Ashley Cordes, and Barbara J. Evans in collaboration with the Mass General Brigham IRB with local context review by IRBs, HIPAA Privacy Officers, and institutional counsels at contributing medical centers.
Copyright
License
Terms of Use
https://chorus4ai.org/wp-content/uploads/2025/10/Data-Agreement-9.30.2025.docx
HL7 Confidentiality Level
HL7:2V (very restricted)
Keywords
Bridge2AI, CHoRUS, Electronic health records, physiological data, medical images
Cite As
The CHoRUS for Clinical Care AI Network. The Bridge2AI CHoRUS for Clinical Care AI Dataset: A Multi-Center, Multi-Modal, High-Resolution Critical Care Dataset, version 1.0 Beta. Harvard Dataverse, Apr. 2026.
Funding
NIH Common Fund OT2OD032701
Completeness
Interim release with partial data. Not all patients in the CHoRUS full cohort are included. No DICOM images are included.
Related Publications

Human Subjects & Regulatory

Human Subjects Research: Yes
De-identified Samples: Yes
FDA Regulated: Yes
IRB Protocol ID: #2022P000707
Institutional Review Board:
Mass General Brigham Institutional Review Board (MGB IRB)
IRB Reliance and Compliance irbreliance@mgb.org +1-857-282-1900
399 Revolution Drive, Suite 710, Somerville, MA 02145 , US
Human Subjects Exemptions:

HIPAA exemption 4 ((45 CFR 46.104(d)(4))

AI Ready Details

Limitations:
• Observational data; and not randomized; collected as real-world clinical data, not through prospective research interactions with patient. • Documentation quality dependent on routine clinical workflows and data elements being collected in clinical practice. • Variable sampling rates across real-world data from hospital waveform systems and middleware • Institutional heterogeneity in coding and clinical data collection practices • Limited generalizability beyond participating hospitals • Not appropriate for re-identification, contact tracing, or patient-level intervention • Hold-out splits are available for testing; training and validation in development splits require internal mechanisms to avoid overfitting
Potential Sources of Bias:
• Referral bias from tertiary/quaternary academic centers • Socioeconomic and demographic distribution reflective of participating institutions • Documentation bias in clinical notes • Missingness not at random (MNAR) in laboratory, waveform, and imaging acquisition • Differential care pathways affecting label assignment (e.g., ICU vs non-ICU populations) • Temporal trends related to evolving clinical practice Bias assessment is ongoing and documented in dataset release notes
Maintenance Plan:
• Versioned dataset releases e.g., CHoRUS vX.Y) • Release notes documenting schema changes, harmonization updates, and known issues • Governance committee oversight for structural modifications • Data upload • Deprecation policy includes: o Advance notice of schema changes o Backward compatibility window where feasible o Archive of prior versions within enclave where possible or incremental change records Primary maintainers: CHoRUS Data Pillar in collaboration with institutional data stewards.
Data Collection:
Data are derived from routine clinical care at participating hospitals under IRB oversight. Collection includes: • Electronic health record extraction and transformation to OMOP common data model • Imaging metadata de-identification using RSNA Clinical Trial Processor and pixel-level de-identification using IbisWorks EICON. • High-resolution physiologic waveform capture extraction and transformation to the WFDB standard, • Standardized harmonization to common data model Ethical safeguards include: • IRB approval or waiver as appropriate • Compliance with CHoRUS governance • Layered privacy protection including de-identification, data use agreement, controlled access data repository with adherence to NIST 800-53 principles, audit-level protection, registration, role-based access controls, protection against data exfiltration. Data are not collected solely for research but repurposed from clinical workflows under ethical oversight.
Missing Data:
Variable sampling rates across real-world data from hospital waveform systems and middleware
Personal/Sensitive Information:
CHoRUS operates within a secure enclave environment aligned with NIST 800-53 controls., De-identification consistent with HIPAA Safe Harbor, Removal or tokenization of direct identifiers, Date shifting or limited date fields when required, Role-based access control (RBAC), Multi-factor authentication, Full audit logging of data access and queries, Prohibition of re-identification attempts, Data export restrictions and output review procedures to reduce risk of re-identification, Re-identification risk is periodically assessed and mitigation strategies updated as needed.

Composition (Datasets 3)

CHoRUS RO-Crate Package

ROCrate ID: ark:59853/rocrate-chorus-ro-crate-package
Description: The Collaborative Hospital Repository Uniting Standards (CHoRUS) for Clinical Care AI is a clinical data network developing a flagship multi-hospital, multimodal, high-resolution dataset under the NIH Bridge2AI program. CHoRUS harmonizes electronic health record (EHR) data, imaging, high-resolution physiologic signals (including telemetry data and EEG where available), and tokenized note and report text (via OHNLP toolkit) with raw text retained locally across participating institutions using standardized data models and governance frameworks. The repository is designed to enable secure, auditable, and reproducible artificial intelligence (AI) research to improve recovery from acute illness. Data are curated within a NIST 800-53–aligned secure enclave architecture with role-based access controls, audit logging, and controlled-access governance review. CHoRUS supports AI model development, validation, benchmarking, and translational research while maintaining compliance with HIPAA and NIH data-sharing policies.
Authors: Eric S. Rosenthal(1), Rishikesan Kamaleswaran(2), Yulia Levites Strekalova(3), Andrew E. Williams(4), Ashley Cordes(5), Ishan C. Williams(6), Parisa Rashidi(3), Barbara J. Evans(3), J. Randall Moorman(6), Soojin Park(7), Edilberto Amorim(8), Paul M. Vespa(9), Xiaoqian Jiang(10), Hongfang Liu(10), Mihai V. Podgoreanu(2), Vitaly Herasevich(11), Mark Wainwright(12), Andrew J. Barros(6), Brynne A. Sullivan(6), Michael J. Young(1), Marta Alvarez(4), Polina Talapova(4), Jennifer A. Muszynski(13), Alasdair Gent(2), Delgersuren Bold(14), Manlik Kwong(4), Dileep Gunda(14), Jackie Le(1), India Loar(6), Brian J. Gow(15), Heidi Schmidt(1), Jared Houghtaling(4), Robert T. Miller(4), Timothy Clark (6), William B. Ashe(6), Tony C. Pan(14), Tom J. Pollard(15), Ciera McCrary(1), Azra Bihorac(3), Xiao Hu(14), Gilles Clermont(6) on behalf of the CHoRUS Investigators (1) Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA (2) Duke University, Durham, North Carolina, USA (3) University of Florida, Gainesville, Florida, USA (4) Tufts CTSI / Tufts Medical Center, Boston, Massachusetts, USA (5) University of Oregon, Eugene, Oregon, USA (6) University of Virginia, Charlottesville, Virginia, USA (7) Columbia University Irving Medical Center, New York, New York, USA (8) University of California, San Francisco, San Francisco, California, USA (9) David Geffen School of Medicine at UCLA, Los Angeles, California, USA (10) McWilliams School of Biomedical Informatics, UTHealth Houston, Houston, Texas, USA; Mayo Clinic, Rochester, Minnesota, USA (11) Mayo Clinic, Rochester, Minnesota, USA (12) Seattle Children’s Hospital, Seattle, Washington, USA (13) Nationwide Children’s Hospital / The Ohio State University, Columbus, Ohio, USA (14) Emory University, Atlanta, Georgia, USA (15) Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
Date: 03/04/2026
Size: 1.2 tb
DOI: https://doi.org/10.18130/V3/XNBOPG
Contact: Ciera McCrary, cmccrary@mgh.harvard.edu
Copyright: © 2026 THE GENERAL HOSPITAL CORPORATION D/B/A MASSACHUSETTS GENERAL HOSPITAL. Copyrights are owned by each subaward site for curation performed locally. Copyrights are jointly held for software jointly developed. All rights reserved
License: Data Use Agreement available at 'https://chorus4ai.org/dataset/'
Terms of Use: https://chorus4ai.org/wp-content/uploads/2025/10/Data-Agreement-9.30.2025.docx
Keywords: Bridge2AI, CHoRUS, Electronic health records, physiological data, medical images
Funding: NIH Common Fund OT2OD032701

Content Summary

📊 Files (3)
Formats: unknown (3)
Access: Available (3)
💻 Software & Instruments (0)
🧪 Inputs (0)
⚙️ Other Components
Experiments: 0
Computations: 0
Schemas: 0
Other: 0
View Full Dataset Details

CHoRUS RO-Crate Waveforms SubRoCrate

ROCrate ID: b9b41c72-0895-4ec2-9e39-8de2a83abcd6
Provenance ID: waveforms/ro-crate-prov-graph.html
Description: Waveforms sub ro-crate for Bridge2AI CHoRUS RO-Crate Package
Authors: Eric S. Rosenthal(1), Rishikesan Kamaleswaran(2), Yulia Levites Strekalova(3), Andrew E. Williams(4), Ashley Cordes(5), Ishan C. Williams(6), Parisa Rashidi(3), Barbara J. Evans(3), J. Randall Moorman(6), Soojin Park(7), Edilberto Amorim(8), Paul M. Vespa(9), Xiaoqian Jiang(10), Hongfang Liu(10), Mihai V. Podgoreanu(2), Vitaly Herasevich(11), Mark Wainwright(12), Andrew J. Barros(6), Brynne A. Sullivan(6), Michael J. Young(1), Marta Alvarez(4), Polina Talapova(4), Jennifer A. Muszynski(13), Alasdair Gent(2), Delgersuren Bold(14), Manlik Kwong(4), Dileep Gunda(14), Jackie Le(1), India Loar(6), Brian J. Gow(15), Heidi Schmidt(1), Jared Houghtaling(4), Robert T. Miller(4), Timothy Clark (6), William B. Ashe(6), Tony C. Pan(14), Tom J. Pollard(15), Ciera McCrary(1), Azra Bihorac(3), Xiao Hu(14), Gilles Clermont(6) on behalf of the CHoRUS Investigators (1) Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA (2) Duke University, Durham, North Carolina, USA (3) University of Florida, Gainesville, Florida, USA (4) Tufts CTSI / Tufts Medical Center, Boston, Massachusetts, USA (5) University of Oregon, Eugene, Oregon, USA (6) University of Virginia, Charlottesville, Virginia, USA (7) Columbia University Irving Medical Center, New York, New York, USA (8) University of California, San Francisco, San Francisco, California, USA (9) David Geffen School of Medicine at UCLA, Los Angeles, California, USA (10) McWilliams School of Biomedical Informatics, UTHealth Houston, Houston, Texas, USA; Mayo Clinic, Rochester, Minnesota, USA (11) Mayo Clinic, Rochester, Minnesota, USA (12) Seattle Children’s Hospital, Seattle, Washington, USA (13) Nationwide Children’s Hospital / The Ohio State University, Columbus, Ohio, USA (14) Emory University, Atlanta, Georgia, USA (15) Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
Date: 03/04/2026
Size: 1201567472832
DOI: https://doi.org/10.18130/V3/XNBOPG
Contact: Ciera McCrary, cmccrary@mgh.harvard.edu
Copyright: © 2026 THE GENERAL HOSPITAL CORPORATION D/B/A MASSACHUSETTS GENERAL HOSPITAL. Copyrights are owned by each subaward site for curation performed locally. Copyrights are jointly held for software jointly developed. All rights reserved
License: See Data Use Agreement
Terms of Use: https://chorus4ai.org/wp-content/uploads/2025/10/Data-Agreement-9.30.2025.docx
Keywords: Bridge2AI, CHoRUS, Electronic health records, physiological data, medical images
Funding: NIH Common Fund OT2OD032701

Content Summary

📊 Files (1425)
Formats: unknown (1), wfdb (1424)
Access: Available (1425)
💻 Software & Instruments (0)
🧪 Inputs (0)
⚙️ Other Components
Experiments: 0
Computations: 1
Schemas: 0
Other: 0
View Full Dataset Details

CHoRUS RO-Crate EHR SubRoCrate

ROCrate ID: 08cf7419-b94d-4508-8f64-c99c557351d7
Provenance ID: ehr/ro-crate-prov-graph.html
Description: Electronic Health Records sub ro-crate for Bridge2AI CHoRUS RO-Crate Package
Authors: Eric S. Rosenthal(1), Rishikesan Kamaleswaran(2), Yulia Levites Strekalova(3), Andrew E. Williams(4), Ashley Cordes(5), Ishan C. Williams(6), Parisa Rashidi(3), Barbara J. Evans(3), J. Randall Moorman(6), Soojin Park(7), Edilberto Amorim(8), Paul M. Vespa(9), Xiaoqian Jiang(10), Hongfang Liu(10), Mihai V. Podgoreanu(2), Vitaly Herasevich(11), Mark Wainwright(12), Andrew J. Barros(6), Brynne A. Sullivan(6), Michael J. Young(1), Marta Alvarez(4), Polina Talapova(4), Jennifer A. Muszynski(13), Alasdair Gent(2), Delgersuren Bold(14), Manlik Kwong(4), Dileep Gunda(14), Jackie Le(1), India Loar(6), Brian J. Gow(15), Heidi Schmidt(1), Jared Houghtaling(4), Robert T. Miller(4), Timothy Clark (6), William B. Ashe(6), Tony C. Pan(14), Tom J. Pollard(15), Ciera McCrary(1), Azra Bihorac(3), Xiao Hu(14), Gilles Clermont(6) on behalf of the CHoRUS Investigators (1) Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA (2) Duke University, Durham, North Carolina, USA (3) University of Florida, Gainesville, Florida, USA (4) Tufts CTSI / Tufts Medical Center, Boston, Massachusetts, USA (5) University of Oregon, Eugene, Oregon, USA (6) University of Virginia, Charlottesville, Virginia, USA (7) Columbia University Irving Medical Center, New York, New York, USA (8) University of California, San Francisco, San Francisco, California, USA (9) David Geffen School of Medicine at UCLA, Los Angeles, California, USA (10) McWilliams School of Biomedical Informatics, UTHealth Houston, Houston, Texas, USA; Mayo Clinic, Rochester, Minnesota, USA (11) Mayo Clinic, Rochester, Minnesota, USA (12) Seattle Children’s Hospital, Seattle, Washington, USA (13) Nationwide Children’s Hospital / The Ohio State University, Columbus, Ohio, USA (14) Emory University, Atlanta, Georgia, USA (15) Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
Date: 03/04/2026
Size: 18.136671 mb
DOI: https://doi.org/10.18130/V3/XNBOPG
Contact: Ciera McCrary, cmccrary@mgh.harvard.edu
Copyright: © 2026 THE GENERAL HOSPITAL CORPORATION D/B/A MASSACHUSETTS GENERAL HOSPITAL. Copyrights are owned by each subaward site for curation performed locally. Copyrights are jointly held for software jointly developed. All rights reserved
License: See Data Use Agreement
Terms of Use: https://chorus4ai.org/wp-content/uploads/2025/10/Data-Agreement-9.30.2025.docx
Keywords: Bridge2AI, CHoRUS, Electronic health records, physiological data, medical images
Funding: NIH Common Fund OT2OD032701

Content Summary

📊 Files (45)
Formats: unknown (1), text/tab-separated-values (44)
Access: Available (45)
💻 Software & Instruments (1)
Software: 1
Instruments: 0
🧪 Inputs (1)
Datasets: 1
unknown (1)
⚙️ Other Components
Experiments: 0
Computations: 1
Schemas: 44
Other: 0
View Full Dataset Details

Distribution Information

Publisher:
B2AI CHoRUS
License:
Data Use Agreement available at 'https://chorus4ai.org/dataset/'
Release Date:
03/04/2026
Version:
1.0 Beta