Introductions/opening (8:30 AM –)
Opening remarks on the Human-AI Interaction theme, workshop goals, and participant and organizer introductions.
Oral Presentations 1 (9:00 – 10:10 AM)
The presentations are listed below.
Coffee Break (10:10 – 10:30 AM)
Poster (10:30 – 12:00 PM)
The posters are listed below.
Lunch (12:00 – 1:30 PM)
Lunch is on your own; attendees are encouraged to connect and dine together.
Coffee Break (2:30 – 2:45 PM)
WISH Town Hall & Closing Reflection (3:45 – 4:30 PM)
Reflect on key research themes, identify gaps and opportunities for future research and collaboration, and discuss ways to strengthen the WISH community. Invite participants to join the WISH organizing team and explore opportunities to collaborate on an NIH R13 grant application to support next year's workshop. Conclude with key takeaways and next steps.
Each presentation is allotted 14 minutes, including Q&A. Presenters are indicated in bold.
Women’s Genetic Health as Family Information Work: Implications for AI-enabled Health Systems
Ziqi Yang, University of California, Irvine; Yunan Chen, University of California, Irvine; Daniel A. Epstein, University of California, Irvine
Consumer Perspectives on Three GenAI Concepts for Understanding and Using Medical Records
Yachi Jitendrabhai Patel, University of Maryland, Baltimore County; Tera L. Reynolds, University of Maryland, Baltimore County
Supporting Over-the-Counter Medication Decision-Making Among Older Adults and Caregivers
Mengying Li, UMD; Jarrett G.W. Lee, UMD; Seongjae Bae, Yonsei University; Harshitha Kommaraju, UMD; Siqiao Austin Ao, UMD; Bongshin Lee, Yonsei University; Eun Kyoung Choe, UMD
Meet REMI: Feasibility and Safety of an LLM-Delivered Reminiscence Therapy Program for Older Adults with Mild Cognitive Impairment
Alexander L. Rasgon (1); Eunhye Ko (2); X. Yang (2), M. Bapatla (2); S. Tamirisa (2); Chris Wu (3); Ying Ding, PhD (2) (1)Dell Medical School, The University of Texas at Austin; (2)School of Information, The University of Texas at Austin; (3) Westlake High School
Stakeholder Perspectives on LLM Evaluation in Healthcare
Manvi S, Emory University; Sumon Kanti Dey, Emory University; Thao Le, Emory University; Selvi Ramalingam, Emory university; Azra Ismail, Emory University
Physical posters will be presentered throughout the session. Presenters are indicated in bold.
Evaluating AI Caregiving Support Tools for Cognitive Empathy: Applying the AI Cognitive Empathy Scale (AICES)
Lamia Alam, Vanderbilt University Medical Center; Shane T. Mueller, Michigan Tech University
NeuroFHIR-SAFE: Can Human-First Be Enforced? Formal Verification of an Evidence-First Clinical AI Review Workflow
Sanghati Basu, University of Illinois
Making Hidden Work Visible in Community-Generated SRH Datasets for Multilingual Health AI Evaluation
Sumon Kanti Dey, Emory University; Kirti Shukla, Myna Mahila Foundation, India; Swarali Manoj Kuthe, Emory University; Zeel Mehta, Myna Mahila Foundation, India; Suhani Jalota, Stanford University; Azra Ismail, Emory University
Evaluating Potential Harms in LLM-Based Substance Use Disorder Recovery Support: A Taxonomy-Guided, Multi-Turn Model Auditing Framework
Anh Duong, Indiana University Indianapolis; Jesse C. Stewart, Indiana University Indianapolis and IU Institute for Human Health and Wellbeing; Brandon G. Oberlin, Indiana University Indianapolis and Indiana University School of Medicine; Dong Whi Yoo, Indiana University Indianapolis and IU Institute for Human Health and Wellbeing
Transient or Persistent? Decomposing Multi-Turn Diagnostic Failure in LLMs
Jinrui Fang (The University of Texas at Austin); Runhan Chen (New York University); Xu Yang (The University of Texas at Austin); Jian Yu (The University of Texas at Austin); Jiawei Xu (The University of Texas at Austin); Ashwin Vinod (The University of Texas at Austin); Wenqi Shi (The University of Texas Southwestern Medical Center); Tianlong Chen (University of North Carolina at Chapel Hill); Heng Ji (University of Illinois Urbana-Champaign); ChengXiang Zhai (University of Illinois Urbana-Champaign); Ying Ding (The University of Texas at Austin); Yuji Zhang (University of Illinois Urbana-Champaign)
Beyond Algorithmic Accuracy: Simulating Physician Reliance and Disagreement Resolution in Clinical Decision Support
Emily Garcia, Vanderbilt University Medical Center; Zachary J. Hass, Purdue University
Understanding the Perceptions of People from Underserved Communities around Generative Artificial Intelligence for Health Information Work
Md Alomgeer Hussein, University of Maryland, Baltimore County; Rushali Sreedhar, University of Maryland, Baltimore County; Yachi Jitendrabhai Patel, University of Maryland, Baltimore County; Sanika Bishnoi, University of Maryland, Baltimore County; Tera L. Reynolds, University of Maryland, Baltimore County
“I Talked to an AI Chatbot, So What’s Next?” How US Young Adults Imagine Responsible AI for Emotion Coping
Jiaying Liu, Nanyang Technological University, Singapore; Nimra Ishfaq, University of Texas at Austin, USA
Beyond Predictive Accuracy: Auditing What LLM Summaries of Depression-Screening Interviews Keep and Add
Avyay Kodali, Walnut Grove High School; Deepthi Potluri, The University of Texas at Austin; Alexander Rasgon, The University of Texas at Austin; Ying Ding, The University of Texas at Austin
Toward Subphenotyping Pediatric POTS with Electronic Health Records and a Literature-Grounded Knowledge Graph
Kyu-Won (Kelly) Lee, Baylor College of Medicine, Texas Children's Hospital; Lin Yao, Baylor College of Medicine, Texas Children's Hospital; Benjamin Choi, Baylor College of Medicine, Texas Children's Hospital; Seon-Young (Serena) Kim, Baylor College of Medicine, Texas Children's Hospital; Zhandong Liu, Baylor College of Medicine, Texas Children's Hospital; Hyun-Hwan Jeong, Baylor College of Medicine, Texas Children's Hospital
Needs Assessment for Asynchronous Suicide Risk Assessment and Intervention
Hannah Slater, Vanderbilt University Medical Center; Laurie Novak, Vanderbilt University Medical Center; Colin G. Walsh, Vanderbilt University Medical Center
When Prediction Is Not Enough: Clinicians-in-the-Loop AI for HIV Clinical Decision Support
Dezhi Wu, PhD¹, USC; Valerie Vera, PhD¹, USC; Sai Krishna Revanth Vuruma, MS¹, USC; Lucas Aust, BS¹, USC; Bharat Sowrya Yaddanapalli, MS¹, USC; Jiaxuan Zhang, MS¹, USC; Rithika Markanti, MS¹, USC; Jiajia Zhang, PhD², USC; Xiaoming Li, PhD³, USC; Sharon Weissman, MD⁴˒⁵ USC, Prisma Health; Bankole Olatosi, PhD⁶, USC
EmoPatient: An Emotion-Directed Patient Simulator for Realistic Palliative Care Communication Training
Yining Wu, University of Texas at Austin; Tianshu Du, University of Texas at Austin; Jinrui Fang, University of Texas at Austin; Chi Zhang, University of Texas at Austin; Sonal Admane, University of Texas MD Anderson Cancer Center; Ying Ding, University of Texas at Austin
REMI: Design and Preliminary Evaluation of an AI-Assisted Reminiscence Therapy Chatbot for Older Adults
Yue Wu, Westlake High School; Alexander L. Rasgon, Dell Medical School, The University of Texas at Austin; Eunhye Ko, Ying Ding, School of Computing, The University of Texas at Austin
ComCare: Piloting Measures of Record Fidelity and Appropriate Reliance for an AI-Enabled Tool Supporting AD/ADRD Caregivers
Jiawei Zhou1, Ying Lei2, Sunyang Fu1, Hongfang Liu1, Jiaming Liang3 1 University of Texas at Austin, Dell Medical School; 2 Simon Fraser University; 3 University of Texas Health Science Center at Houston, School of Public Health