HHS Announces 2024 LEAP in Health IT Awardees Focused on Data Quality for Responsible AI and Accelerating Adoption of Behavioral Health IT

The U.S. Department of Health and Human Services (HHS), through the Assistant Secretary for Technology Policy and Office of the National Coordinator for Health Information Technology (ASTP), today announced two awards totaling $2 million under the Leading Edge Acceleration Projects in Health Information Technology (LEAP in Health IT) funding opportunity. LEAP in Health IT awardees seek to create methods and tools to improve care delivery, advance research capabilities, and address emerging challenges related to interoperable health IT.

The May 2024 Special Emphasis Notice sought applications for two areas of interest: (1) develop innovative ways to evaluate and improve the quality of health care data used by artificial intelligence (AI) tools in health care, and (2) accelerate adoption of health IT in behavioral health settings.

“AI and behavioral health are two high priority areas for HHS. We hope that the funding each awardee receives supercharges their entrepreneurial spirit and positions them to make a real impact in people’s lives,” said Steve Posnack, principal deputy assistant secretary for technology policy. “We are cheering them on and look forward to their future results.”

The 2024 LEAP in Health IT awardees are:

Area 1: Develop innovative ways to evaluate and improve the quality of health care data used by artificial intelligence (AI) tools in health care

Awardee: The Trustees of Columbia University in the City of New York, the governing board of Columbia University in New York City.
Project: Scalable, Shareable, and Computable Clinical Knowledge for AI-Based Processing of Hospital-Based Nursing Data (SC2K)

Overview: Advanced AI methods will increasingly use data documented by nurses. Insufficient knowledge of nursing practice, nurse decision-making, and nursing workflows risks both inaccurate and undiscovered data signals. The proposed study seeks to harness nursing knowledge in a systematic way to better capture the nuances of nursing data, leading to more comprehensive, accurate, and transparent algorithms. Additionally, the study seeks to develop scalable computational approaches to evaluate and improve the quality of data recorded by inpatient nurses and used in AI algorithms.

Objectives:

1. Test and validate different computational methods (e.g., large language model), logistic regression, neural network) within a health care process modeling (HPM) framework applied to two AI-based use cases (classifying missing data versus missed care; classifying implicit biases) that leverage inpatient nursing and multi-modal data ready for integration with knowledge graphs. The HPM framework moves data science methods beyond transactional data analytics to model clinical knowledge, decision-making, and behavior to classify and make predictions about patients that are consistent with and can enhance the quality of the data captured used to discover previously unknown patterns.
2. Generate and validate a set of applicable knowledge graphs related to HPMs that are generalizable and valuable for the two AI-based use cases that leverage inpatient nursing and multi-modal data.
3. Extend multi-modal approaches to HPM-informed scalable computational processes combined with knowledge graphs across five additional AI-based use cases that leverage inpatient nursing and multi-modal data.
4. Build an open-source pipeline to share and reuse the HPM-informed scalable computational processes combined with knowledge graphs.

Area 2: Accelerate adoption of health IT in behavioral health settings

Awardee: Oregon Health & Science University (OHSU). OHSU, a system of hospitals and clinics across Oregon and southwest Washington, is Oregon’s only public academic health center.

Project: Behavioral Health eCarePlan Collaborative Project

Overview: This project seeks to adapt an open-source SMART on Fast Health Interoperability Resources® (FHIR®) application based on the HL7® Multiple Chronic Condition (MCC) care plan effort for three behavioral health use cases and pilot the application in stand-alone behavioral health clinics with challenges in exchanging health information.

Objectives:

1. Fine tune the MyCarePlanner/eCarePlanner applications to improve the exchange of structured behavioral health data, enabling both standard storage to a supplemental data store and write-back to any electronic health record (EHR) available. The system is built to allow any structured data collection form to be incorporated and translated into FHIR questionnaire queries.
2. Connect and pilot the MyCarePlanner/eCarePlanner applications to a set of behavioral health providers with EHRs with limited health information exchange capabilities.
3. Perform a formal evaluation of the applications’ capabilities for three key behavioral health use cases.
4. The results will be shared not only with the behavioral health sites and their patients, but also with a number of key groups focused on open-source tools, including HL7, behavioral health peer support networks, and the eCarePlan cross-agency management group.