Icon Legend

This session is not in your schedule.

This session is in your schedule. Click again to remove it.

Session Icons

Thought Leader Session

Guidelines Session

Aging Adult Track

Additional Registration Fee

Research Snapshot Theater: Quality and Patient Safety, Adult and Pediatric III

The Initial 50,000 ICU Admissions Within the CHoRUS Bridge2AI Multimodal Dataset

Sunday, March 22, 2026

12:15 PM - 1:15 PM Central Time

Location: Connections Central - RST 10

ER

Eric S. Rosenthal, MD (he/him/his)

Massachusetts General Hospital, Massachusetts

Disclosure(s): No relevant financial relationship(s) to disclose.
GC

Gilles Clermont, MD, MS

Professor of Critical Care Medicine
University of Pittsburgh

Disclosure information not submitted.
AW

Andrew Williams, PhD

Professor
Tufts University

Disclosure information not submitted.
EA

Edilberto Amorim, MD

Assistant Professor
University of California, San Francisco

Disclosure information not submitted.
SP

Soojin Park, MD

Professor
Columbia University Medical Center

Disclosure information not submitted.
MW

Mark Wainwright, MD PhD

Professor
Seattle Children's Hospital

Disclosure information not submitted.
JM

Jennifer Muszynski, MD, MPH, FCCM

Associate Professor
Nationwide Children's Hospital At Ohio State University

Disclosure information not submitted.
Paul M. Vespa, MD, FCCM

UCLA David Geffen School of Medicine

Disclosure(s): Ceribell: Consultant (Ongoing)
PR

Parisa Rashidi, PhD

Professor
University of Florida

Disclosure information not submitted.
YL

Yulia Levites Strekalova, PhD

Assistant Professor
University of Florida

Disclosure information not submitted.
VH

Vitaly Herasevich, MD, PhD, FCCM

Mayo Clinic

Disclosure information not submitted.
Andrew Barros, MD, MS (he/him/his)

University of Virginia

Disclosure(s): No relevant financial relationship(s) to disclose.
MD

Masoom Desai, MD

Assistant Professor
University of New Mexico

Disclosure information not submitted.
dB

delgersuren Bold, MS

Research Informatics Specialist
Emory University Nell Hodgson Woodruff School of Nursing

Disclosure information not submitted.
TP

Tom Pollard, PhD

Research Scientist
Massachusetts Institute of Technology

Disclosure information not submitted.
JH

Jared Houghtaling, N/A

Assistant Professor
Tufts Medical Center

Disclosure information not submitted.
Rishikesan Kamaleswaran, PhD

Duke University, North Carolina

Disclosure(s): No relevant financial relationship(s) to disclose.
Azra Bihorac, MD, MS, FCCM

University of Florida School of Medicine, Florida

Disclosure information not submitted.
XH

Xiao Hu, PhD

Professor
Emory University School of Nursing

Disclosure information not submitted.

Introduction: Precision critical care requires large and representative data. We developed a multi-center, multimodal, high-resolution critical care dataset including electronic health record (EHR), imaging, and waveform data. We report the composition of the initial 50,000 patient admissions and lessons learned.

Methods: We included a random sample of adults, pediatric and neonatal intensive care unit (ICU) admissions. Data partitions specified 60% training, 20% test, and 20% hold-out sets to enhance robustness and facilitate regulatory compliance (e.g. FDA filings). The CHoRUS Trusted Research Environment (TRE) and AI/ML workspace were developed on cloud to promote collaborative computing and privacy. EHR data included thousands of lab, med, nurse flowsheet data, diagnoses, and notes, mapped to the Observational Medical Outcomes Partnership (OMOP) Common Data Model, extended for custom ICU concepts and linkages to imaging (DICOM) and waveforms (WFDB). OHDSI tools (ATLAS) enabled comparing variations in ICU practice patterns.

Results: As of 7/1/25, the CHoRUS dataset accrued 50,637 ICU admissions: 1.6 billion rows of OMOP EHR data, 23 Tb of waveforms, and initial radiology data for 7,642 patients, representing ICD-10 diagnoses for acute kidney injury (9,491 patients), sepsis (8,880), shock (5,221), trauma (3,068), ARDS (951), acute MI (2,264), pulmonary embolism (1,677), subarachnoid hemorrhage (1,637), subdural hemorrhage (2,661), and intracranial hemorrhage (1,053). No site exceeded 18% of the cohort. Race and ethnicity varied by hospital: < 10% to >35% Black and < 5% to >30% Hispanic. Age distribution was bimodal, peaking for neonates and ages 60-70 years. Death was recorded in 21.4%. The CHoRUS TRE had onboarded 226 active user accounts including an NIH AI training program (AIM-AHEAD) and 3 datathons, yielding iterative data quality improvement cycles. The TRE hosts AI/ML tools for data labeling and model development/validation.

Conclusions: The Bridge2AI CHoRUS critical care dataset offers multimodal, multi speciality, high-resolution data in a trusted research environment to support generalizable clinical care AI and comparative effectiveness research. Details are available at www.github.com/chorus-ai.