Facilitating Capstone Collaboration in Health Informatics

Presentation Time: 02:00 PM - 02:12 PM

Abstract Keywords: Education and Training, Teaching Innovation, Curriculum Development
Primary Track: Foundations
Programmatic Theme: Academic Informatics / LIEAF

We describe the development of a two-part solution to increase assignment clarity, clarify stakeholder involvement, and facilitate collaboration across stakeholder groups to improve capstone project execution in a health informatics master’s program. The resulting matrix clarifies roles and responsibilities across stakeholders, while Office 365 OneDrive integration within Canvas LMS provides an integrated collaboration environment. The framework improves accountability, enhances coordination, and reduces ambiguity. Early results indicate improved stakeholder engagement and more efficient project management.

Speaker:
Bunyamin Ozaydin, PhD
University of Alabama at Birmingham

Authors:
Sue Feldman, RN, MEd, PhD, FACMI - University of Alabama at Birmingham; Amanda Dorsey, MSHI - University of Alabama at Birmingham; Shannon Houser, PhD - University of Alabama at Birmingham; Abdulaziz Ahmed, PhD - University of Alabama at Birmingham; Akanksha Singh, PhD - University of Alabama at Birmingham; Larissa Pierce, MD, MSHI - University of Alabama at Birmingham;

---

Preliminary Results from an AI Workforce Development Needs Assessment

Presentation Time: 02:12 PM - 02:24 PM

Abstract Keywords: Workforce Development, Artificial Intelligence, Education and Training
Primary Track: Applications
Programmatic Theme: Academic Informatics / LIEAF

This study presents preliminary results from an AI workforce development needs assessment conducted at an academic health science center. The survey, which included faculty, staff, and students, aimed to understand current AI usage, perceptions, and training needs. Findings indicate a high belief in the inevitability of AI use and highlight the need for updated policies and comprehensive training programs to prepare the current and future workforce for an AI-enabled future.

Speaker:
Susan Fenton, PhD
UTHealth Houston McWilliams School of Biomedical Informatics

Authors:
Susan Fenton, PhD - UTHealth Houston McWilliams School of Biomedical Informatics; Richard Halpin, EdD, MEd, EMBA - UTHealth Houston; Litao Wang, EdD - UTHealth Houston; Md. Saifur Rahman, PhD - UTHealth Houston; Diana Keosayian, EdD - UTHealth Houston; Mack Sheraton, MD, MS - Univerisity of Texas Medical center at houston;

---

Perceptions of AI-Based Surgical Simulation for Surgical Resident Training

Presentation Time: 02:24 PM - 02:36 PM

Abstract Keywords: Artificial Intelligence, Human-computer Interaction, Fairness and elimination of bias, Evaluation
Primary Track: Foundations
Programmatic Theme: Academic Informatics / LIEAF

We investigated surgical residents' concerns regarding AI-based surgical simulation in training. Results showed significant apprehension about AI oversimplifying surgical performance into numerical metrics, potentially influencing career progression unfairly. Residents feared that reliance on standardized AI assessments could overlook critical human factors like adaptability and decision-making. Concerns also included AI-driven efficiency pressures that might compromise patient safety. While AI offers objectivity and continuous feedback, its limitations in capturing the complexities of surgical expertise raise doubts about its role in training. Further research is needed to address these concerns and ensure AI supports rather than dictates surgical education and assessment.

Speaker:
Elmira Deldari, PhD
University of Maryland, Baltimore County

Author:
Helena Mentis - University of Maryland Baltimore County;

---

Linking Informatics and Community: An Experiential Practicum for Health Improvement

Presentation Time: 02:36 PM - 02:48 PM

Abstract Keywords: Education and Training, Workforce Development, Population Health
Primary Track: Applications
Programmatic Theme: Academic Informatics / LIEAF

This practicum course at Medical University of South Carolina, BDSI 772, provides experiential learning in biomedical informatics and data science, focused on improving community health. Students collaborate with South Carolina organizations to identify and address health inequities in rural and underserved areas. Through project-based work, they design and propose informatics solutions, gaining hands-on experience and contributing to real-world challenges. This approach mirrors Wagner chronic care model and bridges academic learning with tangible community impact, fostering skills in problem-solving and ethical considerations for health improvement.

Speaker:
Alexander Alekseyenko, PhD, FAMIA, FACMI
Medical University of South Carolina

Author:
Alexander Alekseyenko, PhD, FAMIA, FACMI - Medical University of South Carolina;

---

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?

Presentation Time: 02:48 PM - 03:00 PM

Abstract Keywords: Artificial Intelligence, Large Language Models (LLMs), Clinical Decision Support
Primary Track: Applications
Programmatic Theme: Academic Informatics / LIEAF

Large Language Models (LLMs) show great promise in clinical systems due to their superior medical text processing
capabilities. However, traditional ML models like SVM and XGBoost remain dominant in clinical prediction tasks.
This raises the question: Can LLMs outperform traditional ML models in clinical prediction? To answer this, we
introduce a new benchmark, ClinicalBench, which evaluates 14 general-purpose LLMs, 8 medical LLMs, and 11
traditional ML models across three clinical tasks and two datasets. Our extensive empirical study reveals that both
general-purpose and medical LLMs, regardless of model scale, prompting, or fine-tuning strategies, still fail to
surpass traditional ML models in clinical prediction, highlighting their surprising limitations in clinical reasoning.

Speaker:
Kai Shu, PhD
Emory University

Authors:
Canyu Chen, Bachelor - Illinois Institute of Technology; Jian Yu, BS - N/A; Shan Chen, M.S - Havard-MGB; Che Liu, BS - Imperial College London; Zhongwei Wan, BS - Ohio State University; Danielle Bitterman, MD - Harvard Medical School; Fei Wang, PhD - Weill Cornell Medicine; Kai Shu, PhD - Emory University;

---

Documenting Disclosure: Limited Reporting of Generative AI in Radiology Research Manuscripts

Presentation Time: 03:00 PM - 03:12 PM

Abstract Keywords: Artificial Intelligence, Large Language Models (LLMs), Legal, Ethical, Social and Regulatory Issues
Primary Track: Applications
Programmatic Theme: Academic Informatics / LIEAF

Generative AI tools are increasingly utilized in research manuscript preparation, yet disclosure rates in radiology journals remain unclear. This study systematically analyzed 1,746 radiology manuscripts published in 2024, assessing generative AI disclosure frequency. Results showed only 1.7% of manuscripts declared AI use, predominantly for editing. No significant trend in disclosure rates or peer review duration differences was observed. Findings highlight the need for clearer disclosure guidelines to align practices with widespread AI adoption.

Speaker:
Jonah Barrett, BS
University of Alabama Birmingham Heersink School of Medicine

Authors:
Jonah Barrett, BS - University of Alabama Birmingham Heersink School of Medicine; Richard Heng, BS - University of Alabama Birmingham Heersink School of Medicine; Jordan Perchik, MD - Department of Radiology, Heersink School of Medicine;

---