Patient Attitudes Toward Secondary Use of AI Scribe-Generated Health Data

Presentation Type: Podium Abstract
Presentation Time: 08:00 AM - 08:12 AM

Abstract Keywords: Artificial Intelligence, Data Sharing, Real-World Evidence Generation, Clinical Decision Support, Documentation Burden, Governance
Programmatic Theme: Clinical Informatics

Ambient AI scribe tools are entering clinical care, creating new streams of sensitive clinical data. This cross-sectional survey of adult patients (n=431) examined comfort and acceptability regarding AI-generated audio, transcripts, and notes for secondary use. Patients were most comfortable with uses that support care and quality improvement than with developing new AI tools, and they strongly disfavored commercial use. Findings highlight the need for transparent governance, consent options, and patient-centered framework on AI data use.

Speaker(s):
Sean Tan, MPP
University of Michigan Medical School

Author(s):
Kerry Ryan, Master's in Sociology - University of Michigan Medical School; Morgan Sielaff, Bachelor of Science in Biology, Health, and Society - University of Michigan Medical School; Reema Hamasha, Master's of Health Informatics; Paige Nong, PhD - University of Minnesota; Jodyn Platt, PhD, MPH - University of Michigan Medical School;

Multi-stakeholder Co-design and Trust Calibration as Emerging Grand Challenges in Visual Analytics for Healthcare: Findings from VAHC 2025

Presentation Type: Podium Abstract
Presentation Time: 08:12 AM - 08:24 AM

Abstract Keywords: Information Visualization, Artificial Intelligence, Human-computer Interaction
Programmatic Theme: Clinical Informatics

Current discussions among forty Visual Analytics in Healthcare (VAHC) researchers, as conducted at the Grand Challenge session at IEEE VIS 2025, identify two cross-cutting challenges at the intersection of VAHC and learning health systems: inability of current design study methodology to support multi-stakeholder co-design at scale, and an absence of visualization-specific frameworks for trust calibration in human-centered AI workflows. We outline a corresponding research agenda for the medical informatics community.

Speaker(s):
David Gotz, PhD
University of North Carolina

Author(s):
Gabriela Morgenshtern, MSc - University of Zurich; Arleo Alessio, PhD - Eindhoven University of Technology; David Gotz, PhD - University of North Carolina; Robert Laramee, PhD - University of Nottingham; Sylvia Miksch, PhD - TU Wien; Renata Raidou, PhD - TU Wien; Jürgen Bernard, PhD - University of Zurich;

Operationalizing Robotic and Autonomous Systems for Public Health Emergency Response and Disaster Logistics

Presentation Type: Paper - Regular
Presentation Time: 08:24 AM - 08:36 AM

Abstract Keywords: Public Health, Population Health, Global Health
Programmatic Theme: Public Health Informatics

Robotic and autonomous systems (RAS) have the potential to strengthen public health emergency logistics by augmenting human-driven response operations in hazardous and rapidly evolving environments. We present a computational informatics platform that coordinates fleets of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) to support data-driven decision making in disaster response. The system integrates geospatial data fusion, fleet modeling, stochastic optimization, resilience analytics, and human-in-the-loop control within a unified architecture for semi-autonomous or fully autonomous operations. In a simulated anthrax dispersion scenario across the Atlanta metropolitan area, UAVs conduct reconnaissance and plume assessment while UGVs deliver medical countermeasures, protective equipment, and logistical supplies to Points of Dispensing (PODs). The optimization engine dynamically allocates routes, vehicle tasks, and resources under uncertainty. Results suggest improved timeliness of prophylaxis delivery and greater supply reliability compared with conventional logistics. This work highlights the role of public health informatics in enabling scalable, data-driven emergency response systems.

Speaker(s):
Eva Lee, PhD
The Data and Analytics Innovation Institute

Author(s):
Michael Wright, MBA - Grady Health Systems; Taylor Leonard, PhD - United States Air Force Academy;

Understanding User Perceptions of Human-centered AI-Enhanced Support Group Formation in Online Healthcare Communities

Presentation Type: Paper - Student
Presentation Time: 08:36 AM - 08:48 AM

Abstract Keywords: Human-computer Interaction, Artificial Intelligence, Patient Engagement and Preferences, Data Sharing, Clinical Decision Support, Chronic Care Management
Working Group: Consumer Health Informatics Working Group
Programmatic Theme: Consumer Health Informatics

Peer support is critical to managing chronic health conditions. Online health communities (OHCs) enable patients and caregivers to connect with similar others, yet their large scale makes it challenging to find the most relevant peers and content. This study assessed perceived value, preferred features, and acceptance conditions for algorithmically personalized support group formation within OHCs. A two-phase, mixed-methods survey (N=165) examined OHC participation patterns, personalization priorities, and acceptance of a simulated personalized support group. Perceived value of the simulated support group was high (mean 4.55/5; 62.8% rated 5/5) and 91.5% would join this group. The importance participants placed on peer matching strongly correlated with perceived value (ρ=0.764, p<0.001). Qualitative findings revealed conditional acceptance: participants demand security, transparency, human oversight, and user control over data. Personalized support groups may be desired, but they will not be adopted unless trust, privacy, and algorithmic governance concerns are addressed.

Speaker(s):
Pronob Kumar Barman, PhD in Information Systems
University of Maryland Baltimore County

Author(s):
Pronob Kumar Barman, PhD in Information Systems - University of Maryland Baltimore County; James R. Foulds, PhD - University of Maryland Baltimore County; Tera L. Reynolds, PhD - University of Maryland Baltimore County;

Understanding Over-the-Counter Medication Decision-Making Among Older Adults and Caregivers

Presentation Type: Paper - Student
Presentation Time: 08:48 AM - 09:00 AM

Abstract Keywords: Human-computer Interaction, Patient Safety, Qualitative Methods, Patient Engagement and Preferences, User-centered Design Methods, Delivering Health Information and Knowledge to the Public
Programmatic Theme: Consumer Health Informatics

Over-the-counter (OTC) medications are widely used in the U.S., yet everyday OTC decisions can be safety-critical for older adults and informal caregivers who must reconcile symptoms, comorbidities, and concurrent prescription and supplement use. Through semi-structured interviews with 17 participants (12 older adults and 5 informal caregivers of individuals with cognitive impairment), we examined how older adults and caregivers make OTC decisions in everyday life and what information they need to use OTCs safely. Our findings characterize OTC decision-making as a staged process involving (1) deciding whether medication is necessary, (2) determining which OTC is appropriate given personal conditions and concurrent medications, and (3) prioritizing safe use over time through dosing and timing practices. We discuss opportunities for personalized, caregiver-aware OTC decision support that helps users translate safety information into actionable, context-specific guidance.

Speaker(s):
Mengying Li, M.S.
University of Maryland

Author(s):
Harshitha Kommaraju, B.S. - University of Maryland; Jarrett Lee, M.S. - University of Maryland; Seongjae Bae, B.S. - Yonsei University; Siqiao Ao, M.S. - University of Maryland; Bongshin Lee, Ph.D. - Yonsei University; Eun Kyoung Choe, PhD - University of Maryland;

Beyond Screening: The Impact of Information Flow on Human Trafficking Recognition in the Emergency Department Setting

Presentation Type: Paper - Student
Presentation Time: 09:00 AM - 09:12 AM

Abstract Keywords: Qualitative Methods, Workflow, Delivering Health Information and Knowledge to the Public, Evaluation
Programmatic Theme: Clinical Research Informatics

Human trafficking is under-recognized in healthcare settings. Understanding sociotechnical contexts where trafficking victims encounter healthcare, such as emergency departments (EDs), is crucial to effective interventions. To characterize how information related human trafficking is documented, accessed, and used, we observed workflow, communication, and documentation in a large academic medical center ED. Observational field notes were analyzed using an inductive thematic approach. We identified facilitators and barriers affecting information flow relevant to trafficking recognition. Dedicated personnel focused on trauma-informed care were key to building trust and collecting meaningful patient information. However, workflow pressures and inconsistent screening practices created limited opportunities for disclosure, and fragmentation of sensitive information presented challenges for pattern recognition. These findings suggest that trafficking recognition in the ED depends not only on screening tools, but also on clear documentation, information sharing, and the longitudinal use of information across encounters. Informatics approaches that better support these processes are urgently needed.

Speaker(s):
Michelle Gomez, PhD Candidate
Vanderbilt University

Author(s):
Michelle Gomez, PhD Candidate - Vanderbilt University; Michael Ward, MD, PhD, MBA - Vanderbilt University Medical Center; Ellen Clayton, MD, JD - Vanderbilt Medical Center; Joshua Smith, PhD - Vanderbilt University Medical Center; Colin Walsh, MD MA - Department of Biomedical Informatics, Vanderbilt University; Kim Unertl, PhD - Vanderbilt University Medical Center;