Impact of Digital Support Interventions on Patient Portal Use Among Patients in an Urban Safety-Net Health System

Presentation Type: Podium Abstract

Click to View Presentation

2026 Symposium Health Equity Presentation

Presentation Time: 10:00 AM - 10:12 AM

Abstract Keywords: Patient Engagement and Preferences, Real-World Evidence Generation, Health Equity, Mobile Health, Diversity, Equity, Inclusion, and Accessibility, Workflow
Programmatic Theme: Consumer Health Informatics

We evaluated whether bilingual digital support increased patient portal use at a large urban safety-net health system. Among 286 adults receiving one-on-one patient portal support (144 basic support, 142 tailored assistance), average monthly portal users increased from 52% to 71% post-intervention. Basic portal support yielded a 12% relative increase, while tailored assistance produced a 91% relative increase and fivefold higher login frequency. Embedding bilingual digital support in care workflows may improve digital health engagement.

Speaker(s):
Taylor Rapson, PhD, MPH
University of Washington
Author(s):
Taylor Rapson, PhD, MPH - University of Washington; Monica Naranjo-Arellano, BA - UCSF; James Ralston, MD - Kaiser Permanente Washington Health Research Institute, Kaiser Permanente Washington; Faviola Garcia; Beverly Green, MD, MPH; Christian Gutierrez, BA - UCSF; Sara Guzman-Estrada, Bachleor of Science - University of California, San Francisco; Elaine Khoong, MD, MS - University of California San Francisco; Urmimala Sarkar, MD MPH - UCSF; Jaekyu Shin, PharmD, MS - UCSF; Crystal Zhou, PharmD - UCSF; Courtney Lyles, PhD - UC Davis Center for Healthcare Policy and Research;

---

Social Workers’ Information-Gathering Challenges in the EHR and Opportunities for AI Chatbot Support in Emergency Behavioral Health Care

Presentation Type: Paper - Student
Presentation Time: 10:12 AM - 10:24 AM

Abstract Keywords: Workflow, Usability, Human-computer Interaction
Programmatic Theme: Clinical Informatics

Emergency departments (EDs) increasingly serve patients presenting with behavioral health crises, placing substantial demands on social workers. This qualitative study aimed to characterize social worker information-gathering workflows, identify information-gathering challenges in the electronic health record (EHR), examine the perceived impact of these challenges on care delivery and burden, and explore opportunities for artificial intelligence (AI) chatbot support in emergency behavioral health care settings. We conducted semi-structured interviews with 10 emergency behavioral health care social workers and performed inductive thematic analysis. Participants reported information-gathering challenges associated with reviewing extensive clinical notes and difficulty accessing information due to the EHR’s user-unfriendly design. Although these challenges were viewed as manageable due to experience and adaptation and perceived to have minimal impact on care quality, care delivery, or burden, participants anticipated that an AI chatbot support could reduce information-gathering burden. Participants emphasized that AI chatbot should provide traceable, source-referenced information retrieval.

Speaker(s):
Hyunjoon Lee, MS
Vanderbilt University Medical Center
Author(s):
Hyunjoon Lee, MS - Vanderbilt University Medical Center; Brandon Buxton, MS - Vanderbilt University; Matthew Murrow, PhD - Vanderbilt University Medical Center; Colin Walsh, MD MA - Department of Biomedical Informatics, Vanderbilt University; Jessica Ancker, MPH, PhD, FACMI - Vanderbilt University Medical Center;

---

Bridging the Cognitive Gap: Co-Designing and Evaluating a Voice-Enabled Community Chatbot for Older Adults

Presentation Type: Paper - Student

Click to View Presentation

Presentation Time: 10:24 AM - 10:36 AM

Abstract Keywords: Human-computer Interaction, Usability, Large Language Models (LLMs), User-centered Design Methods, Evaluation, Patient Engagement and Preferences, Information Retrieval
Programmatic Theme: Consumer Health Informatics

Digital portals in retirement communities often create physical and cognitive barriers for older adults, leading to digital avoidance. Generative AI offers a solution by enabling natural language interaction, yet its adoption is hindered by the opaque, “Black Box” nature of these systems and lingering usability challenges. To address this, we evaluated a voice-enabled Large Language Model (LLM) chatbot at a continuing care retirement community in the Pacific Northwest. Through a mixed-methods Co-Design and Literacy Workshop (N=25), we applied a “Glass Box” approach combining multimodal accessibility with intentional AI education. The intervention significantly improved participants’ technical understanding (p=0.004) and perceived transparency (p=0.001), shifting their interaction model from blind trust to informed reliance prioritizing verifiable evidence. While voice input reduced cognitive load, usability scores dropped significantly for users aged 80 and older (r=-0.50), indicating that truly age-inclusive AI must evolve beyond touch-based interfaces toward zero-touch navigation.

Speaker(s):
Feng Chen, MS
University of Washington
Author(s):
Feng Chen, MS - University of Washington; Xingyu Li, MS - University of Washington; Ray-Yuan Chung, PhD in Biomedical and Health Informatics - University of Washington; Wenyu Zeng, MS - University of Washington; Yein Jeon, M.S. - University of Washington; Yizhou Hu, High School - Elgin Park Secondary School; Oleg Zaslavsky, PhD - University of Washington;

---

Design and Usability Testing of a Digital Tool to Enhance Recruitment in Phase I HIV Vaccine Trials

Presentation Type: Podium Abstract

Click to View Presentation

2026 Symposium Health Equity Presentation

Presentation Time: 10:36 AM - 10:48 AM

Abstract Keywords: User-centered Design Methods, Usability, Health Equity, Delivering Health Information and Knowledge to the Public, Mobile Health
Programmatic Theme: Clinical Research Informatics

Transgender women (TW) are disproportionately affected by HIV, yet they are severely underrepresented in HIV vaccine clinical trials. We developed VaxCom, a digital tool to provide priority information to TW in a way that resonates with them, while supporting recruitment specialists to recruit TW within existing workflows. We developed the tool through iterative participatory design, then tested in simulated recruitment sessions for feasibility, acceptability, and usability. Feedback indicated the tool had excellent usability and acceptability.

Speaker(s):
Samantha Stonbraker, PhD, MPH, RN, FAAN, FAMIA
University of Colorado Anschutz Medical Campus
Author(s):
Samantha Stonbraker, PhD, MPH, RN, FAAN, FAMIA - University of Colorado Anschutz Medical Campus; Jorge Soler, PhD, MPH - Precision AQ; Brittany Curet, MSN, RN - University of Colorado College of Nursing; Hong-Van Tieu, MD, MS - Clinical Medicine in the Division of Infectious Diseases at Columbia University Irving Medical Center; Christine Tagliaferri Rael, PhD - University of Colorado College of Nursing;

---

Experience with and Willingness to Use AI Chatbots for Healthcare Tasks Among the US Public

Presentation Type: Podium Abstract
Presentation Time: 10:48 AM - 11:00 AM

Abstract Keywords: Patient Engagement and Preferences, Artificial Intelligence, Large Language Models (LLMs), Delivering Health Information and Knowledge to the Public
Programmatic Theme: Consumer Health Informatics

US adults have limited experience using chatbots for general healthcare tasks like scheduling appointments, reviewing test results, getting reminders for routine tests and vaccines, resolving billing issues, and managing medications (24.8%). Willingness to use a health system's chatbot was much higher (70.6%), especially for scheduling, reviewing test results, and reminders for tests and vaccines. Investment in patient-facing AI will likely have higher impact if it serves these functions rather than medication management or billing.

Speaker(s):
Paige Nong, PhD
University of Minnesota
Author(s):
Jodyn Platt, PhD, MPH - University of Michigan Medical School;

---

Phase 2 Design and Evaluation of EMPATHICA: A Patient-Centered Medication Information Chatbot

Presentation Type: Paper - Regular

Click to View Presentation


Click to View Handout

2026 Symposium Health Equity Presentation

Presentation Time: 11:00 AM - 11:12 AM

Abstract Keywords: Health Equity, Patient Engagement and Preferences, Patient Safety, Large Language Models (LLMs), Human-computer Interaction, User-centered Design Methods, Evaluation, Healthcare Quality
Programmatic Theme: Consumer Health Informatics

Medication information is often difficult for patients to understand, contributing to low medication literacy, preventable errors, and reduced treatment adherence. EMPATHICA is a patient-centered, AI-powered medication chatbot designed to improve comprehension through empathetic communication, plain-language explanations, and grounding in FDA-approved labeling using Retrieval-Augmented Generation (RAG). The system was developed through a participatory design process involving patients, doctors, and medication safety experts, combining Whole Person Care principles with a Learning Health System approach to enable ongoing improvements. In a mixed-methods evaluation, participants completed structured usability tasks and reported high clarity, trust, and perceived empathy, alongside substantial reductions in reading level compared with standard drug information. Safety guardrails prevented unsupported medical advice. Participants expressed a strong preference for institutional backing as a key driver of trust. The findings suggest a co-design process that patients find important for AI tools.

Speaker(s):
Yuri Quintana, PhD
Beth Israel Deaconess Medical Center
Author(s):
Ava Homiar, HBSc - Beth Israel Deaconess Medical Center; Glenda Thomas, BS - Beth Israel Deaconess Medical Center; Betsy Lowe, BA - Beth Israel Deaconess Medical Center; Katherine Bloom, BA - Beth Israel Deaconess Medical Center; Gyana Srivastava, BA - Beth Israel Deaconess Medical Center; David Hampton, BS - Takeda; Valdeci Da Cunha, Sc.D. - Takeda; Lance Nicholls, PharmD, ACHIP, FAMIA - Pfizer; Beverly Buckta, Sc.D. - Pfizer; Natalie Bohm, PhD - Pfizer; Natalia Petrei, B.Sc - Pfizer; Mariya Teslya, B.Sc. - Guardsquare; Louis Ferger-Andrews, B.Sc. - EY;

---