From Chronic Health Condition to Disability Identity: Opportunities for Health Informatics Engagement

2025 Annual Symposium On Demand

Presentation Time: 09:45 AM - 09:57 AM

Abstract Keywords: Disability, Accessibility, and Human Function, Chronic Care Management, Diversity, Equity, Inclusion, and Accessibility, Qualitative Methods
Primary Track: Foundations
Programmatic Theme: Consumer Health Informatics

Of the millions of Americans with chronic health conditions (CHCs), a growing number are coming to identify as disabled due to their CHCs. Their definition of disability differs substantially from how health informatics has traditionally thought about disability and CHCs. Rather than seeing disability as worsening CHCs that ought to be prevented, disability community definitions see disability as a form of social difference, akin to race and gender. To understand the impact of this perspective on disability on people with CHCs, we interviewed 15 participants who identify as disabled due to their CHCs. We found that it was often difficult to develop a disability identity, but doing so had significant benefits: greater self-acceptance, accessibility, and community. We conclude by identifying opportunities for health informatics to enable more people with CHCs to develop and benefit from a disability identity.

Speaker:
Emma McDonnell, PhD
University of Washington

Authors:
Emma McDonnell, PhD - University of Washington; Wanda Pratt, PhD, FACMI - University of Washington;

---

Metabolic Monitoring among Patients with Type 2 Diabetes Prescribed Second Generation Antipsychotics

2025 Annual Symposium On Demand

Presentation Time: 09:57 AM - 10:09 AM

Abstract Keywords: Chronic Care Management, Clinical Decision Support, Public Health, Precision Medicine, Pediatrics
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Annual metabolic monitoring is strongly recommended for patients with type 2 diabetes (T2D) prescribed second-generation antipsychotics (SGA). Our objective was to study the rates of monitoring in the period after index SGA prescription following T2D diagnosis, relative to those prescribed first-generation antipsychotics (FGA) and neither. Among 469,503 adults in Epic Cosmos, we estimated the rates of monitoring (%) of weight, HbA1c, LDL, and renal function for Years 1 to 3 using marginal logistic models. We adjusted for demographic, clinical covariates, encounter frequency, and Charlson Comorbidity Index. Although those prescribed SGA and FGA had more healthcare visits, monitoring decreased following index prescription for all groups. Relative to those prescribed neither, renal function was monitored more frequently among patients prescribed SGA and FGA only in Year 1, while HbA1c and LDL were monitored less for all years. Poor metabolic monitoring following SGA prescription may hinder risk management for T2D complications among this vulnerable population.

Speaker:
Jiali Guo, MPH
Emory University

Author:
Jithin Varghese, PhD - Emory University;

---

Charting the Way with TRAX for Chronic Disease Surveillance

2025 Annual Symposium On Demand

Presentation Time: 10:09 AM - 10:21 AM

Abstract Keywords: Population Health, Public Health, Data Standards, Interoperability and Health Information Exchange, Informatics Implementation, Chronic Care Management
Primary Track: Applications
Programmatic Theme: Public Health Informatics

In December 2022, the Washington Healthcare Forum Board and Washington Department of Health (DOH) senior leadership agreed to develop a plan for improving public health chronic disease surveillance in Washington state. Through a joint planning committee process, we created a plan for a cooperatively governed, technologically flexible, secure platform for sharing data. The approach, known as TRAX (Transformational Repository & Analytics eXchange), recognizes the importance of effective governance alongside health information exchange (HIE). TRAX governance partners identified priority conditions, diabetes and hypertension, to scope early projects (using anonymous patient-level longitudinal data). Leveraging public health HIE advances, like the eCR Now FHIR App, and the national Trusted Exchange Framework and Common Agreement (TEFCA) infrastructure, is reducing development time and administrative burden1. Using nationally available standards and infrastructure, TRAX is an adaptable approach; a reproducible data sharing solution for cross-jurisdictional healthcare systems; and a potential national model for chronic disease surveillance.

Speaker:
Chris Baumgartner, .
WA ST Department of Health

Authors:
Bryant Thomas Karras MD, MD - WA State Dept of Health, Chief Informatics Officer; Ashley Petyak, RN, MS - WA State Dept of Health;

---

APEA: A Type 1 Diabetes Self-Management Ambient-AI Assistance Tool that Bridges Trajectory Prediction, Interactive Explanation, and Just-in-Time Adaptive Intervention Action

2025 Annual Symposium On Demand

Presentation Time: 10:21 AM - 10:33 AM

Abstract Keywords: Clinical Decision Support, Deep Learning, Machine Learning, Large Language Models (LLMs), Personal Health Informatics, Pediatrics
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Helping patients self-managing diseases like type 1 diabetes (T1D) requires innovative informatics tools delivering real-time predictions with explainable, actionable guidance. However, many healthcare AI solutions lack actionable recommendations and user-friendly explanations, limiting clinical impacts. While large language models (LLMs) offer interactive, context-aware explanations that complement static explainable AI outputs, they lack structured data training/inference efficiency like specialized/task-specific AI models. We introduce APEA, a pediatric T1D self-management Ambient-AI assistance tool, integrating glucose multi-trajectory-scenarios Prediction, interactive, context-aware LLM Explanations, and just-in-time adaptive intervention policy optimization for Actionable real-time suggestions through reinforcement learning. Using T1DEXIP dataset with 262 pediatric T1D patients, our results showed improved glucose control outcomes: 60.17% over human management, 21.21% over infusion-pump management. APEA addresses healthcare AI implementation gaps by bridging what might happen, what can be done about it, and why it makes clinical sense. APEA’s framework is adaptable to conditions requiring continuous management and general health optimization.

Speaker:
Kun-Yi Chen, M.S.
University of Missouri

Authors:
Chi-Ren Shyu, PhD, FACMI, FAMIA - University of Missouri-Columbia; Kun-Yi Chen, M.S. - University of Missouri; Erin Tallon, PhD, RN - Children's Mercy Kansas City;

---

REPEAT BP: Reviewing Effective Practices for Elevating Adherence in Treatment of Hypertension

2025 Annual Symposium On Demand

Presentation Time: 10:33 AM - 10:45 AM

Abstract Keywords: Information Visualization, Informatics Implementation, Workflow, Health Equity, Chronic Care Management, Usability, Fairness and elimination of bias
Primary Track: Applications
Programmatic Theme: Clinical Informatics

We report on the implementation of an evidence-based program for improving blood pressure (BP) control—the American Medical Association’s MAP framework—across an integrated health system with almost 400 primary care providers. We developed dashboards to track key metrics: the number of patients with uncontrolled BP, the frequency of recording confirmatory BP measurements during office visits, and the follow-up rates within 30 days for patients with repeated elevated readings. Our findings highlight the complexity of incorporating confirmatory BP measurements into clinic encounters, revealing significant variability in adoption by clinic and by provider. The implementation of the evidence-based program demonstrates that clinic-to-clinic and week-to-week inconsistencies in repeating BP measurements necessitate a systemic approach for effective BP control.

Speaker:
Kevin Ly, MD
Geisinger

Authors:
Seneca Harberger, MD - Geisinger; Alexander Chang, MD - Geisinger; Jeff Wheeler, Business Analyst - Geisinger; David Vawdrey, PhD - Geisinger; Shana Heimer, MHA - Geisinger; Narayana Murali, MD - Geisinger; Maria Kobylinski, MD - Geisinger; Keith Boell, DO - Geisinger;

---

“Write at a 5th Grade Level" Isn’t Enough: Designing and Evaluating Inclusive, Health-Literate Messaging for a Diabetes Support System

2025 Annual Symposium On Demand

Presentation Time: 10:45 AM - 10:57 AM

Abstract Keywords: Large Language Models (LLMs), Patient / Person Generated Health Data (Patient Reported Outcomes), Chronic Care Management, Patient Engagement and Preferences, Usability, User-centered Design Methods
Primary Track: Applications
Programmatic Theme: Consumer Health Informatics

We developed an AI-generated messaging system to provide educational and motivational support for diabetes self-management, grounded in evidence-based health communication guidelines. Despite explicit instructions to generate content at or below a 5th-grade reading level, automated readability assessments and qualitative evaluations revealed significant issues. Messages frequently fell short in readability, numeracy clarity, and serving size communication. Readability formulas often masked deeper comprehension problems. Our findings highlight that instructing generative AI tools on readability levels alone does not ensure patient-safe, understandable communication, emphasizing the critical role of robust communication design in creating equitable and effective digital health interventions.

Speaker:
Katerina Andreadis, MS
NYU Grossman School of Medicine

Authors:
Lynn Xu, MPH - NYU Grossman School of Medicine; Amelia Shunk, MMCi - NYU Grossman School of Medicine; Priscilla D'antico, PhD - NYU Grossman School of Medicine; Gina-Maria Arena, MA - NYU Grossman School of Medicine; Ronaldo Flores, BA - NYU Grossman School of Medicine; Antoinette Schoenthaler, EdD - NYU Grossman School of Medicine; JaeEun Kwon, Master of Public Policy - NYU Langone Health; Veda Sripada, MS - NYU Grossman School of Medicine; Devin Mann, MD - NYU Grossman School of Medicine;

---