Scalable, Shareable, and Computable Clinical Knowledge
for AI-Based Processing of Hospital-Based Nursing Data (SC2K)
This project focuses on improving the use and understanding of hospital-based nursing documentation—both data entry and information retrieval—within electronic health records (EHRs) and supporting systems. It emphasizes the richness and complexity of nursing-generated data. Despite its abundance, nursing data remains underutilized in data science, leading to missed opportunities for enhancing patient outcomes and hospital efficiency. The project aims to close the gap between nursing practice and AI by leveraging high-
Funding
performance models (HPMs) and knowledge graphs to evaluate and improve the quality and transparency of nursing data used in algorithms, ensuring relevance and utility for real-world nursing workflows.
Funding for this project has been provided by the Assistant Secretary for Technology Policy (ASTP) as part of the Special Emphasis Notice (SEN) under the Leading Edge Acceleration Projects (LEAP) in Health Information Technology (Health IT).
Aim 1. Test and validate different computational methods (e.g., LLM, logistic regression, neural network) within an HPM framework applied to 2 AI-based use cases (1. classifying missing data versus missed care, and 2. classifying implicit biases) that leverage inpatient nursing and multi-modal data ready for integration with knowledge graphs. (Year 1).
Aim 2. Generate and validate a set of applicable knowledge graphs related to HPMs that are generalizable and valuable for 2 AI-based use cases (1. classifying missing data versus missed care, and 2. classifying implicit biases) that leverage inpatient nursing and multi-modal data. (Year 2)
Aim 3. Extend multi-model approaches to HPM informed scalable computational processes combined with knowledge graphs across 5 additional AI-based use cases that leverage inpatient nursing and multimodal data (Years 3)
Aim 4. To build an Open Source pipeline to share and reuse our HPM informed scalable computational processes combined with knowledge graphs (Years 4 & 5)
Team Members
Columbia University
Sarah C. Rossetti, RN, PhD
Shalmali Joshi, PhD
Rachel Lee, PhD, RN
Varsha Vakhedi, MA Student
Vicky Wang, MA Student
Temmi Daramola, Project Coordinator
Brandon Lau, Software Engineer
University of Pennsylvania
Kenrick Cato, PhD, RN, CPHIMS, FAAN
University of Colorado
David Albers, PhD
University of Utah
Victoria L. Tiase, PhD, RN-BC, FAMIA, FNAP, FAAN
Carolyn M. Scheese, DNP, MS, BSN
Data Engineer Consultant
Amy Finnegan, PhD
Advisory Board
Noemie Elhadad, PhD, Columbia University
Hojjat Salmasian, MD, MPH, PhD, Children’s Hospital of Philadelphia
Anna Schoenbaum, DNP, MS, RN, NI-BC, FHIMSS, University of Pennsylvania
Amanda Hessels, PhD, MPH, RN, CIC, FAPIC, FAAN, Columbia University
Funding Statement:
This project is supported by the Assistant Secretary for Technology Policy (ASTP) of the U.S. Department of Health and Human Services (HHS) under 90AX0042/01-02, Scalable, Shareable, and Computable Clinical Knowledge for AI-Based Processing of Hospital-Based Nursing Data, $998,903. This information or content and conclusions are those of the author and should not be construed as the official position or policy of, nor should any endorsements be inferred by ASTP, HHS, or the U.S. Government.
