CHORUS d4d core

Datasheet for Dataset - Human Readable Format

🎯

Motivation

For what purpose was the dataset created?

DescriptionIDName
Answer the grand challenge of improving recovery from acute illness by developing high-resolution multi-center datasets as a critical first step towards actionable and trustworthy AI in critical care. Address the urgent need for infrastructure to support artificial intelligence and machine learning (AI/ML) in critical care settings.
chorus:purpose:1Improve recovery from acute illness
Develop a publicly available, AI-ready critical care dataset from more than 100,000 critically ill patients while ensuring methods promote privacy, accountability, and clinical benefit. Generate the most diverse, high-resolution, ethically sourced dataset for AI/ML applications in acute and critical care, expanding AI and Machine Learning to improve recovery from acute illness.
chorus:purpose:2Create AI-ready critical care dataset
Unify standards to harmonize multi-modal EHR, waveform, imaging, and text data. Develop software and tooling to interact with and extract insight from clinical data in diverse formats. Create validated semantic mappings for connecting clinical data in various source formats to international standards (OMOP Common Data Model, DICOM, WFDB, OHNLP).
chorus:purpose:3Establish data standards and tools
Ensure comprehensive sets of patient conditions and clinical treatment strategies with appropriate contextual factors such as geographic distance to nearest hospital and Social Determinants of Health. Develop the skills and workforce for a next generation of diverse academic and community AI scientists through comprehensive training and education programs in partnership with AIM-AHEAD.
chorus:purpose:4Promote diversity and health equity
  • ID
    chorus:funder:1
    Name
    NIH Common Fund Bridge2AI Program
    Description
    Funded through National Institutes of Health grant OT2OD032701 (project number 1OT2OD032701-01), administered by NIH Office of the Director. Opportunity Number: OTA-21-008. Study Section: Data Coordination, Mapping, and Modeling (DCMM). Fiscal Year 2022. Total funding in 2022: $5,880,300 (all direct costs). Project dates: September 1, 2022 to November 30, 2026 (with approved no-cost extension). Award notice date: September 1, 2022. Assistance Listing Number: 93.310.
📊

Composition

What do the instances that comprise the dataset represent?

DescriptionFormatIDMedia TypePath
Structured electronic health record data in OMOP Common Data Model format (proprietary clinical data standard). Contains 1.6 billion rows. Available in secure enclave with controlled access at https://chorus4ai.org/. Published OMOP schema metadata available.
chorus:dist:1https://chorus4ai.org/
Waveform telemetry data (23 TB) in WFDB (WaveForm DataBase) format following extended PhysioNet schema (binary waveform data format). Available in secure enclave with controlled access at https://chorus4ai.org/.
chorus:dist:2https://chorus4ai.org/
Medical imaging data (7,642 admissions with radiology; 1,000 images currently available) in DICOM format (Digital Imaging and Communications in Medicine) with comprehensive metadata. De-identification in process for larger cohort. Planned controlled access at https://chorus4ai.org/.
chorus:dist:3https://chorus4ai.org/
Clinical notes distributed as OHNLP-tokenized plain text following open source OHNLP schema. Stored locally at contributing sites (except tokens). Controlled access planned at https://chorus4ai.org/.
TXTchorus:dist:4text/plainhttps://chorus4ai.org/
EEG waveform data in EDF+ (European Data Format) and Persyst formats following open source schemas (binary physiological signal formats). Extraction in process, planned for controlled access at https://chorus4ai.org/.
chorus:dist:5https://chorus4ai.org/
  • ID
    chorus:instance:1
    Name
    Critically ill patients in ICU settings
    Description
    Individual critically ill patients requiring acute or critical care admitted to intensive care units (ICU), pediatric intensive care units (PICU), or neonatal intensive care units (NICU) across 14 data acquisition centers. As of August 2025, the dataset covers 14 different hospitals with over 45,000 unique admissions, with 50,000 patient admissions from ICU, PICU, and NICU currently released. Target enrollment exceeds 100,000 critically ill patients. Retrospective data collection from patients with acute or critical illness.
DescriptionIDName
Patients distributed across 14 different hospitals within the CHoRUS network spanning 20 academic centers in the United States, ensuring geographic and institutional diversity in critical care settings.
chorus:subpop:1Critically ill patients by hospital
Patients admitted to intensive care units (ICU), pediatric intensive care units (PICU), and neonatal intensive care units (NICU) across contributing hospitals, with 50,000 patient admissions in the current released dataset.
chorus:subpop:2ICU, PICU, and NICU patients
DescriptionIDName
Structured electronic health record data distributed in OMOP Common Data Model format enabling use of OHDSI tool stack for analysis. Contains 1.6 billion rows. Available in secure enclave with controlled access. Published OMOP schema metadata available.
chorus:format:1OMOP Common Data Model (structured EHR data)
Waveform telemetry data (23 TB) distributed in WFDB (WaveForm DataBase) format following extended PhysioNet schema. Available in secure enclave with controlled access. Published PhysioNet schema (extended) metadata available.
chorus:format:2WFDB waveform format (bedside monitor telemetry)
Medical imaging data (7,642 admissions with radiology; 1,000 images currently available) distributed in DICOM format with comprehensive metadata following DICOM schema. De-identification in process for larger cohort. Planned controlled access.
chorus:format:3DICOM format (medical imaging)
Clinical notes distributed as OHNLP-tokenized text following open source OHNLP schema. Stored locally at contributing sites (except tokens). Controlled access planned.
chorus:format:4OHNLP tokenized format (clinical notes)
EEG waveform data distributed in EDF+ (European Data Format) and Persyst formats following open source schemas. Extraction in process, planned for controlled access.
chorus:format:5EDF+ and Persyst formats (EEG waveforms)
  • ID
    chorus:distdate:1
    Name
    Initial release date
    Description
    Dataset made available for access beginning September 2022 (project start date). Current release (August 2025) includes 50,000 patient admissions with 1.6 billion rows of EHR OMOP data. Ongoing expansion through November 30, 2026 project end date.
🔍

Collection Process

How was the data associated with each instance acquired?

https://chorus4ai.org/
CHoRUS
Patient-Focused Collaborative Hospital Repository Uniting Standards (CHoRUS) for Equitable AI
CHoRUS for Equitable AI is a Bridge2AI data generation project developing the most diverse, high-resolution, ethically sourced, AI-ready critical care dataset to answer the grand challenge of improving recovery from acute illness. The project spans 20 academic centers (14 data acquisition centers) and is building a publicly available dataset targeting over 100,000 critically ill patients with multi-modal data including structured EHR, waveform telemetry, medical imaging, EEG, and clinical notes. All structured data is standardized to the OMOP Common Data Model with additional formats (DICOM, WFDB, OHNLP tokenization) and comprehensive metadata schemas. Patient-focused efforts determine ethical and legal approaches to manage privacy and bias while accounting for Social Determinants of Health. A visualization and annotation environment labels data with targets important for prediction. The project emphasizes skills and workforce development for a next generation of diverse academic and community AI scientists through training programs and partnerships with AIM-AHEAD. As of August 2025, the dataset covers 14 different hospitals with over 45,000 unique admissions and includes 50,000 patient admissions from ICU, PICU, and NICU, 1.6 billion rows of EHR OMOP data, 7,642 admissions with radiology data, and 23 TB of waveform data.
https://chorus4ai.org/
en
CHoRUS Consortium / Massachusetts General Hospital
False
  • CHoRUS
  • Bridge2AI
  • critical care
  • acute illness
  • AI-ready dataset
  • OMOP Common Data Model
  • electronic health records
  • EHR
  • waveform telemetry
  • medical imaging
  • DICOM
  • EEG
  • clinical notes
  • OHNLP
  • health equity
  • social determinants of health
  • federated access
  • multi-modal data
  • high-resolution data
  • ethical AI
  • trustworthy AI
  • workforce development
  • data standardization
  • privacy preservation
  • bias mitigation
  • ICU
  • intensive care
DescriptionIDName
Address the absence of large-scale, diverse, high-resolution multi-center datasets for critical care AI/ML by creating a dataset spanning 20 academic centers with 100,000+ critically ill patients and ensuring balanced, diverse cohorts through federated access and sampling methods across 14 data acquisition centers.
chorus:gap:1Lack of diverse multi-center critical care datasets
Overcome the lack of unified standards in critical care data by harmonizing multi-modal EHR, waveform, imaging, and text data to OMOP Common Data Model and other international standards (DICOM, WFDB, OHNLP).
chorus:gap:2Insufficient data standardization in critical care
Address ethical and legal challenges in AI through patient-focused efforts that determine approaches to manage privacy and bias while accounting for Social Determinants of Health and performing community-facing ethics focus groups to determine what data is appropriate for public sharing.
chorus:gap:3Privacy and bias concerns in clinical AI
Bridge the gap in diverse AI/ML workforce through comprehensive educational approaches, training programs (including AIM-AHEAD partnership), and cultivation of expertise in lay and scientific communities to improve AI literacy and utilization.
chorus:gap:4Limited diversity in AI/ML workforce
RoleNameORCIDAffiliation
ContributorEric S. Rosenthalchorus:creator:1-
ContributorAzra Bihoracchorus:creator:2-
ContributorAshley Cordeschorus:creator:3-
ContributorGilles Clermontchorus:creator:4-
ContributorGari David Cliffordchorus:creator:5-
ContributorBarbara J. Evanschorus:creator:6-
ContributorXiao Huchorus:creator:7-
ContributorRishikesan Kamaleswaranchorus:creator:8-
ContributorYulia A. Levites Strekalovachorus:creator:9-
ContributorParisa Rashidichorus:creator:10-
ContributorCynthia Rudinchorus:creator:11-
ContributorIshan Canty Williamschorus:creator:12-
ContributorAndrew Ewing Williamschorus:creator:13-
ContributorXiaoqian Jiangchorus:creator:14-
ContributorMorteza Zabihichorus:creator:15-
ContributorZhenhong Huchorus:creator:16-
ContributorDebora Simmonschorus:creator:17-
ContributorAliyah Geerchorus:creator:18-
ContributorCiera McCrarychorus:creator:19-
DescriptionIDName
Complete electronic health records including demographics, diagnoses, procedures, medications, nursing documentation, and clinical notes for critically ill patients. Contains protected health information subject to HIPAA and institutional privacy requirements. De-identified before release through OMOP transformation and privacy scanning tools.
chorus:sensitive:1Protected health information - clinical EHR data
Continuous waveform telemetry from bedside monitors and EEG recordings capturing detailed physiological states of critically ill patients. May reveal sensitive health conditions and treatment responses. Stored in WFDB format (telemetry) and EDF+/Persyst formats (EEG) with controlled access.
chorus:sensitive:2Physiological monitoring and EEG waveform data
Diagnostic imaging studies in DICOM format from hospital PACS systems. De-identification in process to remove embedded patient information while preserving clinical utility. As of August 2025, 1,000 images available with de-id in process for larger cohort (7,642 admissions with radiology data total).
chorus:sensitive:3Medical imaging data
Contextual factors including geographic information (distance to hospital) and social determinants of health data. Collected to support health equity research while maintaining patient privacy through privacy-preserving transformations.
chorus:sensitive:4Social Determinants of Health data
DescriptionIDName
Data collected exclusively from academic medical centers (14 acquisition centers across 20 academic institutions), which may not represent community hospital or rural care settings. Patient populations at academic centers may differ systematically from the broader critically ill patient population in terms of disease severity, demographics, and treatment patterns.
chorus:bias:1Academic medical center population bias
Retrospective collection from hospital electronic health records introduces potential selection biases based on documentation practices, coding patterns, and clinical workflows that vary across the 14 acquisition centers. Documentation completeness and accuracy may vary by site, modality, and time period.
chorus:bias:2Retrospective data collection bias
DescriptionIDName
As of August 2025, the dataset covers 14 hospitals with over 45,000 unique admissions and 50,000 released (ICU, PICU, NICU); target exceeds 100,000 critically ill patients. EEG extraction and full imaging de-identification are still in process. Clinical notes are stored locally at sites with only tokens available in the enclave. Cohort coverage varies by data modality and ongoing collection continues through November 2026.
chorus:limitation:1Dataset still actively growing and not yet complete
All data requires signed data use agreement and institutional email registration, limiting accessibility for researchers at institutions without established data sharing agreements. Access through secure enclave (Azure-based infrastructure) imposes computational and logistical constraints.
chorus:limitation:2Controlled access restricts open research
  • ID
    chorus:confidential:1
    Name
    De-identified clinical data under controlled access
    Description
    All data distributed under controlled access model requiring institutional email registration and signed licensing agreement. Data de-identified before release. Full clinical notes stored locally at sites; only OHNLP tokens available in enclave. Data use agreement prohibits re-identification attempts.
DescriptionIDName
Demographics, medication administration (dosing time-stamped upon each infusion change or dose administration), procedures, nursing flowsheets (high-frequency documentation), and diagnoses acquired from electronic health records and standardized to OMOP Common Data Model. Controlled access with published OMOP schema metadata. Contains 1.6 billion rows of OMOP data as of August 2025.
chorus:acquisition:1Structured EHR data via OMOP transformation
Clinical notes extracted from EHR systems and tokenized using OHNLP (Open Health Natural Language Processing) toolkit. Stored locally at sites except for tokens. Controlled access planned with OHNLP open source schema metadata.
chorus:acquisition:2Clinical notes via OHNLP tokenization
Imaging data acquired from hospital PACS systems in DICOM format. De-identification in process. Planned controlled access with published DICOM schema metadata.
chorus:acquisition:3Medical imaging via DICOM from PACS
Bedside monitor waveform data acquired through gateway and middleware systems. Stored in WFDB format with controlled access and published PhysioNet schema (extended) metadata. 23 TB available as of August 2025.
chorus:acquisition:4Waveform telemetry via WFDB from bedside monitors
EEG recordings from hospital databases in EDF+ and Persyst formats. Extraction in process. Planned controlled access with open source EDF+ and Persyst schema metadata.
chorus:acquisition:5EEG waveforms from hospital databases
DescriptionIDName
Retrospective data collection from electronic health record systems at 14 data acquisition centers. Data extracted includes demographics, medication administration (dosing time-stamped upon each infusion change or dose administration), procedures, nursing flowsheets (high-frequency documentation), diagnoses, and clinical notes. Standardized to OMOP Common Data Model.
chorus:collection:1Retrospective EHR extraction
Continuous waveform telemetry data captured from bedside monitors through gateway and middleware systems at each contributing hospital. Stored in WFDB (WaveForm DataBase) format following extended PhysioNet schema. Contains 23 TB of waveform data as of August 2025.
chorus:collection:2Waveform telemetry capture
Medical imaging data acquired from hospital Picture Archiving and Communication Systems (PACS) and stored in DICOM format with comprehensive metadata following DICOM schema. 7,642 admissions have radiology data; 1,000 images currently available.
chorus:collection:3Medical imaging acquisition from PACS
Electroencephalography recordings extracted from hospital EEG databases in EDF+ (European Data Format) and Persyst formats with metadata following open source schemas. Extraction in process as of August 2025.
chorus:collection:4EEG recording extraction
  • ID
    chorus:timeframe:1
    Name
    Project data collection period
    Description
    Retrospective and ongoing data collection from September 1, 2022 through November 30, 2026 (project end date with approved no-cost extension). As of August 2025, data covers 14 different hospitals with over 45,000 unique admissions. Target enrollment exceeds 100,000 critically ill patients by project completion.
  • ID
    chorus:collector:1
    Name
    CHoRUS Data Acquisition Centers
    Description
    14 data acquisition centers across 20 academic institutions in the United States responsible for extracting and contributing clinical data (EHR, waveforms, imaging, notes, EEG) from their hospital systems. Site statuses tracked through GitHub interface and Google Form submissions. Data Acquisition sub-team manages extraction per Chorus_SOP standard operating protocols.
  • ID
    chorus:sampling:1
    Name
    Multi-center federated sampling
    Description
    Federated access enables sampling methods to ensure a balanced and diverse cohort across 20 academic centers (14 data acquisition centers). Legal framework established for collecting data at scale with sampling to ensure comprehensive sets of patient conditions and clinical treatment strategies. Community-facing ethics focus groups conducted to determine what data is appropriate for public sharing.
DescriptionIDNameSource Description
Electronic health record systems at 14 data acquisition centers across the United States providing structured clinical data (demographics, medications, procedures, diagnoses, nursing flowsheets) in diverse institutional formats prior to OMOP standardization.
chorus:rawsource:1Hospital EHR systems at 14 acquisition centers
Institutional EHR systems (diverse formats) at 14 academic data acquisition centers in the United States, containing structured clinical data for critically ill patients.
Proprietary bedside patient monitoring systems at participating hospitals serving as the raw source for continuous waveform telemetry data prior to WFDB standardization.
chorus:rawsource:2Bedside monitoring systems (waveform)
Proprietary bedside patient monitoring gateway and middleware systems at 14 participating hospitals, capturing continuous physiological waveform telemetry for ICU patients.
Picture Archiving and Communication Systems at participating hospitals serving as the raw source for medical imaging data in DICOM format prior to de-identification.
chorus:rawsource:3Hospital PACS systems (imaging)
Hospital Picture Archiving and Communication Systems (PACS) at participating institutions, containing radiology imaging data (CT, X-ray, MRI, and other modalities) in DICOM format.
Hospital electroencephalography databases serving as raw source for EEG recordings in EDF+ and Persyst formats prior to extraction and standardization.
chorus:rawsource:4Hospital EEG databases
Hospital electroencephalography recording systems and databases at participating sites, containing EEG recordings in EDF+ (European Data Format) and Persyst formats.
  • ID
    chorus:missing:1
    Name
    Incomplete modality coverage across sites
    Description
    Not all data modalities are available from all 14 acquisition centers. EEG extraction and full imaging de-identification are in process as of August 2025. Clinical notes stored locally at sites with only OHNLP tokens available in the central enclave. Cohort coverage varies by data modality during ongoing data collection.
  • ID
    chorus:raw:1
    Name
    Raw multi-institutional clinical data
    Description
    Unprocessed clinical data from 14 acquisition centers in diverse institutional formats including proprietary EHR exports, raw waveform streams from bedside monitors, DICOM images from PACS, and clinical notes in free-text format prior to any standardization or de-identification processing.
DescriptionIDName
All structured electronic health record data standardized to the OMOP (Observational Medical Outcomes Partnership) Common Data Model. Ensures interoperability and enables use of OHDSI (Observational Health Data Sciences and Informatics) tool stack for analysis. Data from all 14 acquisition centers unified through this transformation. Validated semantic mappings for connecting clinical data maintained in chorus-mapping repository. Characterization reports returned to contributing sites via CHoRUSReports.
chorus:preproc:1OMOP Common Data Model transformation
Clinical notes processed using OHNLP (Open Health Natural Language Processing) toolkit for extraction and tokenization. Protects patient privacy while enabling natural language processing and analysis of clinical text data. Full notes stored locally at sites; only tokens available in enclave.
chorus:preproc:2Clinical note tokenization via OHNLP
Waveform telemetry data from diverse bedside monitoring systems standardized to WFDB (WaveForm DataBase) format following extended PhysioNet schema. Scripts available in chorus_waveform repository.
chorus:preproc:3Waveform standardization to WFDB format
DICOM imaging data undergoing de-identification process to remove patient identifiable information from image metadata while preserving clinical utility and image quality. Privacy scan tool (privacy_scan_tool) used for medical records privacy scanning.
chorus:preproc:4Medical imaging de-identification
Data transformed using approaches that limit re-identification while maintaining analytical utility. Multiple preprocessing strategies employed to protect patient privacy across all data modalities per HIPAA and institutional requirements. Geocoding via DeGauss (UF-Geocoding tool) for OMOP Location entities.
chorus:preproc:5Re-identification limitation transformations
DescriptionIDName
Data from 14 acquisition centers harmonized through validated semantic mappings and standard operating protocols (SOPs). Ensures consistency and interoperability across diverse institutional EHR systems and clinical practices. Mappings maintained in chorus-mapping repository with clinical validation SOP. Cross-site data quality checks through CHoRUSReports characterization reports.
chorus:cleaning:1Multi-center data harmonization with validated semantic mappings
All data modalities validated against published metadata schemas (OMOP, DICOM, WFDB, OHNLP, EDF+, Persyst) to ensure compliance and data quality across the multi-modal dataset. Schema extensions documented for OMOP high-frequency nursing flowsheets.
chorus:cleaning:2Schema compliance validation across all modalities
  • ID
    chorus:labeling:1
    Name
    Visualization and annotation environment for prediction targets
    Description
    Custom visualization and annotation environment developed to label data with targets important for prediction tasks in critical care AI applications. Supports labeling for characterizing acute illness, predicting complications, and measuring treatment response. Annotation interface for clinical expert labeling with quality control through review processes per Chorus_SOP standard operating procedures.
DescriptionIDName
Multi-institutional consortium managing dataset maintenance including 14 data acquisition centers, coordinating teams at Massachusetts General Hospital (lead), University of Florida, UT Health Science Center, and Tufts Medicine, plus infrastructure development team. Standards, Data Acquisition, and Tooling sub-teams manage ongoing data delivery and quality. Contact: cmccrary@mgh.harvard.edu (Ciera McCrary, Program Manager, MGH).
chorus:maintainer:1CHoRUS Consortium
Active GitHub organization housing repositories for software, semantic mappings, standard operating protocols, and project management. 28 repositories with comprehensive documentation and community support. GitHub organization at https://github.com/chorus-ai.
chorus:maintainer:2CHoRUS GitHub Organization (chorus-ai)
ID
chorus:retention:1
Name
Long-term dataset retention per NIH data sharing policies
Description
Digital data maintained according to NIH data sharing policies and institutional requirements at participating centers. Controlled access model ensures long-term availability for research while protecting patient privacy. Funded under NIH award OT2OD032701 with project end date of November 30, 2026.
ID
chorus:extension:1
Name
Site contribution and GitHub-based development
Description
Dataset extended through contributions from 14 data acquisition centers via standardized extraction protocols (Chorus_SOP). Software tools and semantic mappings extended through GitHub organization (chorus-ai) with 28 active repositories. New sites may join through established data acquisition framework. Community contributions to mapping efforts via chorus-mapping repository and clinical validation SOP.
  • ID
    chorus:ethics:1
    Name
    Institutional Review Board approvals at 14 acquisition centers
    Description
    Retrospective data collection approved through institutional review board processes at all 14 data acquisition centers across the United States. Community-facing ethics focus groups conducted to determine what data is appropriate for public sharing. Legal framework established for collecting data at scale.
ID
chorus:atrisk:1
Name
Critically ill patients and vulnerable ICU populations
Description
Dataset includes critically ill patients (ICU, PICU, NICU) who are vulnerable due to acute illness and critical care needs. Pediatric (PICU) and neonatal (NICU) patients represent particularly vulnerable populations. Dataset also includes patients with diverse social determinants of health and geographic factors. Privacy protections include de-identification, controlled access model, and data use agreement restrictions. Community ethics focus groups engaged to protect patient interests.
ID
chorus:ip:1
Name
Institutional data use agreement and NIH award terms
Description
Data use is governed by the CHoRUS licensing agreement and NIH grant terms (OT2OD032701). GitHub repositories use MIT License and Apache-2.0 licenses for software components. Clinical data ownership remains with contributing institutions subject to applicable law. Re-use outside terms of the data use agreement is prohibited.
ID
chorus:regulatory:1
Name
HIPAA and human subjects research compliance
Description
Dataset subject to HIPAA (Health Insurance Portability and Accountability Act) compliance requirements for protected health information. Subject to 45 CFR 46 (Common Rule) for human subjects research protections. Institutional data privacy regulations at each of the 14 contributing sites apply. NIH Common Fund Bridge2AI program ethical and trustworthy AI requirements must be met. Export control regulations may apply for international users.
ID
chorus:deid:1
Name
De-identified with controlled access
Description
All data de-identified before distribution. EHR data de-identified through OMOP CDM transformation and privacy scanning tools (privacy_scan_tool). Clinical notes tokenized via OHNLP toolkit with full text remaining local; only tokens available in enclave. Medical imaging undergoing DICOM header de-identification. Waveform and EEG data in WFDB/EDF+ formats with controlled access. Despite de-identification, controlled access model maintained due to sensitivity of clinical data and re-identification risk.
DescriptionIDName
Official project website with dataset overview, team information, project components, and access instructions
chorus:resource:1CHoRUS Project Website
Comprehensive GitHub organization with 28 repositories including software, documentation, SOPs, and tooling at https://github.com/chorus-ai
chorus:resource:2CHoRUS GitHub Organization
Centralized standard operating protocol documentation with interactive workflow diagrams for data extraction and contribution at https://github.com/chorus-ai/Chorus_SOP
chorus:resource:3Chorus_SOP Documentation Site
Federal grant information and project details from NIH Research Portfolio Online Reporting Tools for grant 1OT2OD032701-01 at https://reporter.nih.gov/project-details/10472824
chorus:resource:4NIH RePORTER Project Details
Parent NIH Common Fund program supporting AI-ready biomedical datasets across four data generation projects at https://bridge2ai.org/chorus
chorus:resource:5Bridge2AI Program
Partnership with AIM-AHEAD for Bridge2AI Clinical Care Training Program (Cohort 1 and Cohort 2) providing AI/ML training for underrepresented trainees at https://aim-ahead.net/
chorus:resource:6AIM-AHEAD Bridge2AI Training Program
Observational Health Data Sciences and Informatics community supporting OMOP Common Data Model used for CHoRUS structured EHR data at https://www.ohdsi.org/
chorus:resource:7OHDSI Community and OMOP CDM
Peer-reviewed publication documenting CHoRUS dataset methodology and design in Neurocritical Care journal at https://doi.org/10.1007/s12028-024-02007
chorus:resource:8Published Research (Neurocritical Care)
🚀

Uses

Has the dataset been used for any tasks already?

DescriptionIDName
Generate data for ML/AI applications aimed at characterizing acute and critical care illness patterns, progression, and outcomes across diverse patient populations and hospital settings.
chorus:task:1Characterize acute and critical care illness
Enable prediction of complications among patients with acute or critical illness using multi-modal data including structured EHR, waveforms, imaging, and clinical notes.
chorus:task:2Predict complications in critically ill patients
Support measurement and analysis of treatment response among critically ill patients through high-frequency documentation, medication administration records, and clinical outcomes data.
chorus:task:3Measure treatment response
Provision a holdout test set accessible for model external validation to aid marketplace adoption of AI-developed models for implementation in acute and critical care settings.
chorus:task:4External validation for AI model marketplace adoption
Utilize visualization and annotation environment to label data with targets important for prediction tasks in critical care AI applications.
chorus:task:5Label data for prediction targets
DescriptionIDName
Primary intended use is development and training of artificial intelligence and machine learning models to characterize acute and critical care illness, predict complications, and measure treatment response in critically ill patients across diverse hospital settings.
chorus:use:1AI/ML model development for critical care
Provision of holdout test set accessible for model external validation to aid marketplace adoption of AI-developed models for implementation in acute and critical care settings.
chorus:use:2External validation of AI models
Studies examining health equity, social determinants of health, and disparities in critical care outcomes across diverse patient populations and hospital settings. Dataset includes contextual factors such as geographic distance to nearest hospital.
chorus:use:3Health equity and disparities research
Training and education of next generation of diverse academic and community AI scientists through hands-on experience with real-world critical care datasets. Integrated with AIM-AHEAD Bridge2AI for Clinical Care Training Program (Cohorts 1 and 2).
chorus:use:4Educational and training purposes for AI scientists
DescriptionIDName
Dataset is for research purposes only. AI/ML models developed should undergo appropriate clinical validation, regulatory approval, and institutional review before use in patient care or clinical decision-making. Models trained on CHoRUS data must undergo independent clinical validation and regulatory approval processes (e.g., FDA clearance) before clinical deployment.
chorus:discouraged:1Clinical decision-making without proper validation and regulatory approval
Attempts to re-identify patients from de-identified data violate ethical principles, data use agreements, and legal frameworks established for privacy protection under HIPAA and institutional requirements. Re-identification attempts are prohibited by the signed data use agreement.
chorus:discouraged:2Re-identification attempts
As data collection continues through November 2026 and quality assurance processes are ongoing, early dataset versions should be used with awareness of completeness limitations and ongoing expansion (from 45K to target 100K+ admissions). EEG extraction and full imaging de-identification still in process as of 2025.
chorus:discouraged:3Use without awareness of ongoing data collection limitations
DescriptionIDName
Explicitly prohibited under the data use agreement and applicable law (HIPAA). Any attempt to re-identify individual patients from the de-identified data is a violation of the data use agreement and may result in termination of access and legal consequences.
chorus:prohibited:1Re-identification of de-identified patients
Redistribution, sharing, or transfer of CHoRUS data to third parties outside the terms of the signed data use agreement is explicitly prohibited. Data must remain within the secure enclave environment or as explicitly permitted by the agreement.
chorus:prohibited:2Redistribution of data outside the data use agreement
DescriptionIDName
Subsets of the dataset used in the AIM-AHEAD Bridge2AI for Clinical Care Training Program (Cohort 1: 2024-2025, Cohort 2: 2025-2026). Training provides foundational hands-on experience using Jupyter Notebooks with Bridge2AI CHoRUS ecosystem, workshops on OHDSI/OMOP common data model and clinical AI, and development of practical use cases.
chorus:existing:1AIM-AHEAD Bridge2AI Clinical Care Training Program
Dataset methodology and design documented in peer-reviewed publications including Neurocritical Care journal (doi: 10.1007/s12028-024-02007). Dataset used for initial characterization and training activities as the full cohort undergoes expansion and quality assurance.
chorus:existing:2Peer-reviewed research publications
DescriptionIDName
The CHoRUS dataset has potential to become a foundational resource for critical care AI/ML research, enabling development of models that could improve patient outcomes in ICU settings across diverse populations. External validation capabilities support broader adoption of AI-developed clinical tools.
chorus:impact:1Potential to transform critical care AI research
AI/ML models trained on CHoRUS data may inherit biases present in clinical documentation, treatment patterns, or data collection at academic medical centers. Models developed without appropriate bias mitigation could perpetuate or amplify healthcare disparities if deployed in clinical practice without careful validation.
chorus:impact:2Risk of algorithmic bias propagation
ID
chorus:license:1
Name
CHoRUS Controlled Access License with Data Use Agreement
Description
Dataset distributed under controlled access requiring institutional email registration and signed licensing agreement. Access granted after review and approval process. Participants must complete registration form with name, institutional email (not personal), and institution. Once approved, users receive email with access instructions to CHoRUS secure enclave. For training program access, program administrators assist with licensing. Access request contacts - dbold@emory.edu or jared.houghtaling@tuftsmedicine.org. Funded under NIH award OT2OD032701.
📤

Distribution

Will the dataset be distributed to third parties outside of the entity on behalf of which it was created?

Controlled Access - Data Use Agreement Required (OT2OD032701)
ID
chorus:versionaccess:1
Name
Controlled access versioned releases
Description
Dataset versions accessible through secure enclave with controlled access. Users must register with institutional email and sign licensing agreement to access current and future versions. Version history maintained as data collection expands from 45K to target 100K+ critically ill patient admissions.
🔄

Maintenance

Who will be supporting, hosting, or maintaining the dataset?

ID
chorus:updates:1
Name
Ongoing data collection and continuous expansion
Description
Dataset updated continuously as data collection progresses at 14 acquisition centers. As of August 2025, covers 14 hospitals with over 45,000 unique admissions; current released dataset includes 50,000 patient admissions (ICU, PICU, NICU) and 1.6 billion rows of EHR OMOP data. Target exceeds 100,000 critically ill patients. Project timeline extends through November 30, 2026 (approved no-cost extension). Regular status updates tracked through GitHub project management system.
👥

Human Subjects

Does the dataset relate to people?

ID
chorus:hsr:1
Name
CHoRUS Human Subjects Research
Description
Retrospective data collection from critically ill patients (ICU, PICU, NICU) approved through institutional review processes at 14 data acquisition centers. Community-facing ethics focus groups conducted to determine what data is appropriate for public sharing. Legal framework established for collecting data at scale. Patient-focused efforts determine ethical and legal approaches to manage privacy and bias while accounting for Social Determinants of Health. Project includes expertise from law, ethics, health services, biomedical science, engineering, and scientific journal publications disciplines. Ethics of AI component addressed through AIM-AHEAD training curriculum (safety, risk, and legal considerations; IRB, HIPAA/GDPR compliance for OMOP/FHIR data).
Involves Human Subjects
True
  • ID
    chorus:consent:1
    Name
    Retrospective data and waiver of consent framework
    Description
    Retrospective data collection from critically ill patients using waiver of individual consent framework approved by IRBs at participating institutions. Community-facing ethics focus groups engaged to determine appropriate data for public sharing and guide ethical data governance. Patient-focused ethics pillar of CHoRUS project determines ethical and legal approaches to privacy, bias, and Social Determinants of Health considerations.
Generated on 2026-04-27 00:03:44 using Bridge2AI Data Sheets Schema