Custom CSS
double-click to edit, do not edit in source
5/20/2026 |
2:00 PM – 3:15 PM |
Mt. Elbert B - 555 Building, 2nd Floor
TRI31: Operationalizing Informatics: Maturity Models, Platforms, and Practice (Oral Presentations)
Presentation Type: Oral Presentations
LabSage: Structural-Semantic Decoupling for Enhanced Retrieval-Augmented Generation in Clinical Laboratories
Presentation Type: Paper - Student
Click to View Presentation
Presentation Time: 02:00 PM - 02:12 PM
Primary Track: Data Science/Artificial Intelligence
Modern clinical laboratory operates within a stringent regulatory ecosystem requiring precise adherence to Standard Operating Procedures (SOPs). However, standard Retrieval-Augmented Generation (RAG) approaches frequently fail in this domain due to context fragmentation, where fixed-size segmentation arbitrarily severs critical procedural dependencies. To address this, we introduce LabSage, a domain-adapted framework implementing structural-semantic decoupling. This hierarchical architecture indexes compact search units for optimal retrieval precision while dynamically retrieving expanded context units to preserve procedural completeness during inference. Evaluated on authentic laboratory queries using Qwen-2.5-7B as backbone, LabSage achieved an Answer Accuracy of 0.780 and Context Recall of 0.909, outperforming standard RAG by 8.3% and 5.7%, respectively. These findings demonstrate that decoupling vector search from reasoning context is a critical architectural advancement in regulated medical domains to mitigate safety-critical omissions and ensure compliance.
Speaker(s):
Hang Zhang, MSUniversity of Pittsburgh
Author(s):
Hang Zhang, MS -
University of Pittsburgh;
Yuelyu Ji, PhD -
University of Pittsburgh;
Chenyu Li, M.S. -
University of Pittsburgh;
Hooman Rashidi, MD -
University of Pittsburgh;
Sarah Wheeler, MD -
University of Pittsburgh;
Yanshan Wang, PhD -
University of Pittsburgh;
Hang
Zhang,
MS - University of Pittsburgh
Toward Sustainable REDCap-Based Patient-Facing Technologies: Development of a Four-Tier Maturity Model
Presentation Type: Podium Abstract
Click to View Presentation
Presentation Time: 02:12 PM - 02:24 PM
Primary Track: Clinical Research Informatics
Many Patient-Facing Technologies (PFTs) become isolated data silos lacking sustainability. We propose a four-tier maturity model aimed to guide the design and implementation of REDCap-based PFTs. This framework helps researchers shift from a customized project mindset to the REDCap platform mindset, encouraging sustainable investment and preventing resource misallocation. The model charts an evolutionary path from passive data collection tools (Tier 1) to proactive, intelligent assistants (Tier 4) in patient care.
Speaker(s):
Yun Jiang, PhD, MS, RN, FAMIAUniversity of Michigan
Author(s):
Zhengcan Xie, MS -
UT Health Houston;
Yuheng Shi, MS -
UTHealth Houston;
Eric Yang, MS -
UT Health Houston;
Yun Jiang, PhD, MS, RN, FAMIA -
University of Michigan;
Yang Gong, MD, PhD -
UTHealth Houston;
Yun
Jiang,
PhD, MS, RN, FAMIA - University of Michigan
The Maturity of Maturity Models in Healthcare and Informatics
Presentation Type: Paper - Regular
Click to View Presentation
Presentation Time: 02:24 PM - 02:36 PM
Working Group: Informatics Maturity Working Group
Primary Track: Clinical Research Informatics
Maturity models can be used to assess organizational capability in specific areas. Over the past decade, maturity model use has increased along with the development of maturity models for many specific areas related to healthcare informatics. A challenge in the use and development of maturity models is understanding what makes a model functional, which can be considered the “maturity” of the model. We developed a meta-maturity model for assessing models, and evaluated it by applying it to models that have been developed and used in areas related to health care and informatics. The distribution of models across this meta-maturity model shows that there is wide variation of model effectiveness. The application of this meta-maturity model can help individuals and organizations choose the most appropriate models, and can also assist those who are developing models to consider how models can be improved.
Speaker(s):
Adam Wilcox, PhDWashington University in St. Louis
Author(s):
David Dorr, MD, MS, FACMI, FAMIA, FIAHSI -
Oregon Health & Science University;
Boyd Knosp, MS, FAMIA -
Self-employed;
Robin Champieux, MLIS -
Oregon Health & Science University;
William Barnett, PhD -
Harvard Medical School;
Nicholas Anderson, PhD -
University of California, Davis;
Justin Starren, MD, PhD, FACMI, FAMIA -
University of Arizona;
Jodyn Platt, PhD, MPH -
University of Michigan Medical School;
Ashish Vaidyanathan, BS -
Washington University in St Louis;
Peter Embi, MD, MS -
VUMC;
Adam
Wilcox,
PhD - Washington University in St. Louis
Enhancing Inter-institutional AI Research Collaboration Across Multidisciplinary Teams to Increase the National AI Workforce in Healthcare
Presentation Type: Paper - Regular
Click to View Presentation
Presentation Time: 02:36 PM - 02:48 PM
Primary Track: Data Science/Artificial Intelligence
Inter-institutional team collaboration is critical for impactful multidisciplinary AI research in healthcare. The goal of our project (AIM-AHEAD Connect) is to increase multidisciplinary collaborations by connecting AI/ML experts and healthcare researchers, trainees and professionals to enhance research and improve health for all Americans. As of November 2025, AIM-AHEAD Connect has over 9,700 AI/ML and healthcare experts from across 2,290 institutions, has made more than 7,400 connections and facilitated 170 collaborative online groups. We conducted a unique study to understand collaboration, and analyzed profile, connection, and platform engagement metrics to determine if AI experts and healthcare researchers with more inter-institutional connections are more successful in obtaining research and training funding. By creating this bridge to foster collaborations between AI/ML experts and healthcare professionals, this project has created a unique space to enhance healthcare outcomes for all.
Speaker(s):
Toufeeq Syed, PhD, MSUT Health Houston
Author(s):
Toufeeq Syed, PhD, MS -
UT Health Houston;
Sarah Popal, MS -
The University of Texas Health Science Center at Houston;
D'Laney Kernan, BS -
The University of Texas Health Science Center at Houston;
Deevakar Rogith, MBBS, PhD -
The University of Texas Health Science Center at Houston (UTHealth) School of Biomedical Informatics;
Zulfiia Ditto, PhD, MS -
The University of Texas Health Science Center at Houston;
Paul Warhurst, PhD -
The University of Texas Health Science Center at Houston;
Jay Johnson, HS -
The University of Texas Health Science Center at Houston;
Jamboor K. Vishwanatha, PhD -
University of North Texas Health Science Center at Fort Worth;
Toufeeq
Syed,
PhD, MS - UT Health Houston
Development of a Pilot Artificial Intelligence Education Curriculum for Hospital Staff
Presentation Type: Paper - Student
Click to View Presentation
Presentation Time: 02:48 PM - 03:00 PM
Primary Track: Data Science/Artificial Intelligence
Artificial intelligence (AI) is rapidly advancing, yet many healthcare staff lack foundational knowledge, risking inefficient or unsafe use. To address this, we developed an internal voluntary AI Primer pilot curriculum for all staff, including non-clinicians, within a safety-net health system. The micro-learning program included six modules featuring creative AI-generated content to enhance engagement. In its first three months, 80 staff voluntarily enrolled, generating over 500 views. Participants who completed an optional post-course survey (n = 7) scored highly on post-course assessments (86-100%), found the content relevant, and felt it addressed AI safety (85%). Most appreciated the design, and nearly one-third enrolled out of curiosity about AI in healthcare. Our pilot’s early findings suggest strong interest among diverse staff role types, tangible benefit, feasibility for broader adoption, and contribute to a nascent body of literature on this topic. Future efforts may incorporate clinical case examples and strategies to expand participation.
Speaker(s):
Brian Lefchak, MD, MPHUniversity of Minnesota-Hennepin Healthcare
Author(s):
Brian Lefchak, MD, MPH -
University of Minnesota-Hennepin Healthcare;
Uzoma Abakporo;
Gagandeep Anand, BCS, MPH, MD -
University of Minnesota & Thrive Wellness Institute;
Justin Gaines, BA -
Hennepin Healthcare;
Christopher Adams, MD, MBA -
University of Minnesota-Hennepin HealthCare;
Ryan Jelinek, DO -
Hennepin County Medical Center;
Brian
Lefchak,
MD, MPH - University of Minnesota-Hennepin Healthcare
Gamifying Education in Decision-Making with AI Technologies in Healthcare
Presentation Type: Podium Abstract
Click to View Presentation
Presentation Time: 03:00 PM - 03:12 PM
Primary Track: Data Science/Artificial Intelligence
This project introduces a game that aims to facilitate learning, decision-making, and policy formation for AI technologies in healthcare. Users simulate decision-making regarding AI technologies in various healthcare roles (i.e. clinicians, patients, administrators, policymakers), experimenting with hypothetical scenarios modeled on field data and real-world experiences. These simulations are pedagogical and methodological innovations that facilitate reflection on decisions and outcomes in a low-/zero-stakes environment to inform and improve real-time decision-making with AI technologies for patient care.
Speaker(s):
Carrie Alexander, Ph.D.University of California Davis
Author(s):
Carrie Alexander, Ph.D. -
University of California Davis;
Nicholas Anderson, PhD -
University of California, Davis;
Carrie
Alexander,
Ph.D. - University of California Davis
