SOURCE METADATA
Project: CHORUS
Source ID: nih_reporter_project
Source type: NIH project page
Source URL: https://reporter.nih.gov/project-details/10472824
Raw file: data/raw/CHORUS/reporter_nih_gov_project-details-10472824_row7.txt
--------------------------------------------------------------------------------
NIH RePORTER Project
Source: https://reporter.nih.gov/project-details/10472824
Application ID: 10472824
Project number: 1OT2OD032701-01
Core project number: OT2OD032701
Title:  Bridge2AI: Patient-Focused Collaborative Hospital Repository Uniting Standards (CHoRUS) for Equitable AI
Principal investigator: ROSENTHAL, ERIC S.
Organization: MASSACHUSETTS GENERAL HOSPITAL
Fiscal year: 2022
Award amount: 5880300
Project start: 2022-09-01T00:00:00
Project end: 2026-11-30T00:00:00

Abstract Text
There is an urgent need for infrastructure to support artificial intelligence and machine learning (AI/ML) in critical care. Developing high-resolution multi-center data sets is a critical first step towards actionable and trustworthy AI. As part of the NIH Common Fund’s Bridge2AI program, the CPatient-Focused Collaborative Hospital Repository Uniting Standards (CHoRUS) for Clinical Care AI data generation project will meet the need of generating data for ML/AI applications aimed at characterizing acute and critical care illness, predicting complications, and measuring treatment response among patients with acute or critical illness. Through 3 pillars, the CHoRUS data generation project will addresses multiple challenges relevant for acquiring an AI-ready data set from more than 100,000 critically ill patients: 1) Data (Standards, Tool Development and Optimization, and Data Acquistion) 2) Ethics (Ethical and Trustworthy AI) and 3) People (Team Science and Skill and Workforce Development). The project’s overarching goal is to develop a publicly available, AI-ready critical care dataset, while ensuring the methods promote privacy, accountability, and clinical benefit, while promoting a new generation of AI clinicians and scientists. The dataset will also 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. Drawing expertise from a comprehensive set of disciplines such as team science, law, ethics, health services, biomedical science, engineering, and scientific journal publications, this project will A) establish a legal framework for collecting data at scale, sampling to ensure comprehensive sets of patient conditions and clinical treatment strategies; B) perform community-facing ethics focus groups to determine what data is appropriate for public sharing; C) ensure that data elements feature appropriate contextual factors such as geographic distance to the nearest hospital; D) develop capabilities across a multi-center network to acquire, standardize, tokenize, store, visualize, and label data such as structured electronic health record data, tokenized unstructured electronic health record data, telemetry and EEG waveforms, imaging, and social determinants of health; E) acquire data, standardize data to the OMOP Common Data Model, transform data using approaches that limit re-identification, and label data for ; and F) cultivate expertise in the lay and scientific community to improve AI literacy nd utilization through multimodal educational approaches. To accomplish this, the project will involve extensive collaboration between centers as well as through the NIH Bridge2AI program, the NIH Bridge2AI Bridge Center, external biomedical and clinical organizations, industry, and regulatory agencies.

The Patient-Focused Collaborative Hospital Repository Uniting Standards (CHoRUS) for Equitable AI will develop the necessary network, tools, standards, data, and education to build machine-learning (ML) and artificial intelligence (AI)-derived models to improve the care and outcomes of patients requiring critical care.  By performing legal and ethical research, developing tools for data storage, labeling and analysis, acquiring and standardizing a dataset of unprecedented diversity and high resolution, sequestering holdout datasets for external validation, and enriching the community through education, this data generation project will catalyze the biomedical research and expertise necessary to promote the patient-focused deployment of AI in acute and critical care.

Preferred terms:
Accountability;Acute;Address;Adoption;Artificial Intelligence;Biomedical Research;Bridge to Artificial Intelligence;Clinical;Collaborations;Communities;Critical Care;Critical Illness;Data;Data Element;Data Set;Data Storage and Retrieval;Deterioration;Diagnosis;Discipline;Education;Electroencephalography;Electronic Health Record;Engineering;Ensure;Ethics;Event;Focus Groups;Funding;Generations;Goals;Health Services;Hospitals;Image;Industry;Infrastructure;Intelligence;Journals;Label;Laws;Legal;Machine Learning;Measures;Methods;Modeling;Patient-Focused Outcomes;Patients;Privacy;Publications;Research;Resolution;Sampling;Science;Scientist;Standardization;Telemetry;Testing;United States National Institutes of Health;Validation;Workforce Development;acute care;care delivery;care outcomes;data acquisition;data modeling;data standards;data tools;electronic structure;improved;literacy;multimodality;programs;repository;skill acquisition;social health determinants;tool;tool development;treatment response;trustworthiness
