Infographics Administered Through a SMART on FHIR App Lead to Improvements in Health Outcomes: Results of a Multisite Randomized Controlled Trial

2025 Annual Symposium On Demand

Presentation Time: 08:00 AM - 08:12 AM

Abstract Keywords: Information Visualization, Mobile Health, Nursing Informatics
Working Group: Nursing Informatics Working Group
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics

Our team created an informatics-based intervention to improve clinical HIV-related communication by rigorously developing and incorporating evidence-based infographics into a Substitutable Medical Applications and Reusable Technology (SMART)® application (app) compatible with the Fast Healthcare Interoperability Resources (FHIR).® We then conducted an international two-site randomized controlled trial to assess the efficacy of the intervention as compared to standard care in improving CD4 count, viral load and other outcomes. We randomized N=164 PWH (N=82/site) to intervention or control groups and followed them for 4 visits. Results showed improvements in most outcomes though results were significant within, but not between, groups. Findings have important implications regarding infographic design and methods to integrate interventions into SMART on FHIR apps.

Speaker:
Samantha Stonbraker, PhD, MPH, RN, FAAN
University of Colorado Anschutz Medical Campus

Authors:
Samantha Stonbraker, PhD, MPH, RN, FAAN - University of Colorado Anschutz Medical Campus; Yazmina Espiritusanto Castro, BA - Clínica de Familia La Romana; Stefanie Mayorga, MS - University of Colorado; Pamela Baez Caraballo, MD, MSc - Clínica de Familia La Romana; Mehmet Kazgan, MS, MBA - cliexa, Inc.; Burak Cetin, BS - cliexa, Inc.; Arin Seidlitz, BS - cliexa, Inc.; Beatrice A. Francis, MS - Denver Health and Hospital Authority; Yanjun Gao, PhD - University of Colorado; Kellie Hawkins, MD, MPH - Denver Health and Hospital Authority; Margaret McLees, MD - Denver Health and Hospital Authority; Christine Tagliaferri Rael, PhD - University of Colorado; Zachary Giano, PhD - University of Colorado; Edward Gardner, MD - Denver Health and Hospital Authority; Adriana Arcia, PhD, RN, FAAN - University of San Diego;

EHR-Based Social Needs Screening and Referral in Primary Care: Clinician and Staff Perspectives on Practices, Barriers, and Benefits

2025 Annual Symposium On Demand

Presentation Time: 08:12 AM - 08:24 AM

Abstract Keywords: Surveys and Needs Analysis, Workflow, Health Equity
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Identifying social drivers of health (SDoH) can help healthcare professionals connect patients with community resources that impact health outcomes. However, screening and referral require time and effort, highlighting the potential for electronic health record (EHR)-based support. We surveyed primary care clinicians and staff about their current SDoH screening and referral practices, as well as perceived barriers and benefits for standardizing those practices with EHR support. Although the majority of respondents currently screen and refer patients for SDoH at least occasionally, most respondents document in the EHR using unstructured formats and rate current practices as only moderately feasible and acceptable. While the majority reported feeling competent with SDoH screening, key barriers included time constraints, lack of dedicated staff, and a desire for access to more community resources. Findings underscore the need for an EHR-based standardized screening and referral implementation with flexibility to adapt workflows to different clinic settings and clinical positions.

Speaker:
Ziqing Ji, Biomedical and Health Informatics
University of Washington

Authors:
Ziqing Ji, Biomedical and Health Informatics - University of Washington; Patrick Wedgeworth, MD, MISM - University of Washington; Kathleen Mertens, DNP, MN, MPH, RN - Harborview Medical Center, UW Medicine; Sara Jackson, MD, MPH - Harborview Medical Center, UW Medicine; Nkem Akinsoto, MS - Primary Care & Population Health, UW Medicine; Jared Klein, MD, MPH - Harborview Medical Center, UW Medicine; Margaret Isaac, MD - Harborview Medical Center, UW Medicine; Andrea Hartzler, PhD - University of Washington;

An Electronic Health Record-Based Platform for Social Needs Assessment and Intervention: Preliminary Results of a Randomized Controlled Trial

2025 Annual Symposium On Demand

Presentation Time: 08:24 AM - 08:36 AM

Abstract Keywords: Clinical Decision Support, Population Health, Real-World Evidence Generation
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Our team has developed an electronic health record (EHR)- integrated platform, including a clinical decision support and closed-loop referral tool, to identify patients with social needs and provide assessment and navigation services. This paper presents the results of the first six months of an ongoing randomized clinical trial assessing the effectiveness of this platform. Our preliminary findings show that structuring a social needs assessment and intervention within clinical EHRs can improve the social needs assessment and intervention process.

Speaker:
Elham Hatef, MD, MPH
Johns Hopkins University

Authors:
Elham Hatef, MD, MPH - Johns Hopkins University; Thomas Richards, MS - Johns Hopkins University; Sofia Hail, MD - Johns Hopkins University; Talan Zhang, PhD - Johns Hopkins University; Kristin Topel, MS - Johns Hopkins University; Christopher Kitchen, MS; Katherine Shaw, MD - Johns Hopkins University; Jonathan Weiner, DrPH - Johns Hopkins University;

Bridging the Gap: Barriers and Facilitators to Integrating FHIR-Based Applications into Electronic Health Records

2025 Annual Symposium On Demand

Presentation Time: 08:36 AM - 08:48 AM

Abstract Keywords: Standards, Qualitative Methods, Usability
Primary Track: Applications

This qualitative study investigates the barriers and facilitators to integrating third-party FHIR-based applications into electronic health records (EHRs). Using interviews with health IT experts across diverse organizations, findings were categorized using the Technology-Organization-Environment (TOE) framework. Key challenges include technical incompatibility, organizational resource constraints, and policy uncertainty. While federal mandates promote FHIR adoption, sustained success requires infrastructure support, stakeholder alignment, and improved interoperability strategies.

Speaker:
Jyotsna Gutta, MPH
Center for Health Policy

Authors:
Jyotsna Gutta, MPH - Center for Health Policy; Magda Francois, MA - University of Florida; julie diiulio, MS; Michelle Wang Whitlock, MS - Applied Decision Science LLC; Laura Militello - Applied Decision Science, LLC; Miranda Reid, MPH - University of Florida; Katy Hilts, Phd, MPH - Indiana University Indianapolis; Khoa Nguyen, Pharm.D - University of Florida; Francisco Martinez-Wittinghan, MD, PhD - UF Health; Mario El Hayek, MD; Laura Marcial, PhD - RTI International; Ramzi Salloum, PhD; Christopher Harle, PhD - Indiana University;

Generating Counterfactual Patient Timelines from Real-World Data

2025 Annual Symposium On Demand

Presentation Time: 08:48 AM - 09:00 AM

Abstract Keywords: Real-World Evidence Generation, Artificial Intelligence, Clinical Decision Support, Deep Learning, Machine Learning, Large Language Models (LLMs), Bioinformatics, Precision Medicine
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics

Counterfactual simulation—modeling hypothetical outcomes under alternative clinical scenarios for individual patients—holds promise for personalized medicine and in-silico trials. However, it remains challenging due to methodological limitations. Here, we show that an autoregressive generative model, trained on data from over 300,000 patients and 400 million patient timeline entries, can generate clinically plausible counterfactual trajectories. As a validation task, we applied the model to patients hospitalized with COVID-19 in 2023, modifying age, serum C-reactive protein (CRP), and serum creatinine to simulate 7-day outcomes. Increased in-hospital mortality was observed in counterfactual simulations with older age, elevated CRP, and elevated serum creatinine. Remdesivir prescriptions increased in simulations with higher CRP values and decreased in those with impaired kidney function. These counterfactual trajectories reproduced known clinical patterns. These findings suggest that autoregressive generative models trained on real-world data in a self-supervised manner can establish a foundation for counterfactual clinical simulation.

Speaker:
Yu Akagi, M.D.
The University of Tokyo

Authors:
Tomohisa Seki, MD PhD - the University of Tokyo hospital; Toru Takiguchi, M.D., Ph.D. - The University of Tokyo; Hiromasa Ito, M.D., Ph.D. - The University of Tokyo; Yoshimasa Kawazoe, M.D., Ph.D. - The University of Tokyo; Kazuhiko Ohe, MD, PhD - University of Tokyo Hospital;

An Information Model for Exchanging Context and Provenance Rich Patient Generated Health Data with Electronic Health Record

2025 Annual Symposium On Demand

Presentation Time: 09:00 AM - 09:12 AM

Abstract Keywords: Patient / Person Generated Health Data (Patient Reported Outcomes), Interoperability and Health Information Exchange, Data Sharing, Data Standards, Data transformation/ETL, Workflow, Controlled Terminologies, Ontologies, and Vocabularies, Knowledge Representation and Information Modeling
Primary Track: Applications
Programmatic Theme: Consumer Health Informatics

Patient Generated Health Data (PGHD) empower patients and support their longitudinal care, with several studies and initiatives attempting to integrate these data into clinical electronic health records (EHR). However, studies have indicated clinicians’ desire and interest in having additional contextual information about these data. There are limited studies that consider the context and the provenance of these data at the point and time of data collection. This has implications around the reliability and usability of PGHD shared with EHR as well as clinician's trust in this data. This paper seeks to describe how an ontology-driven information model was employed to capture PGHD with provenance and context, with the aim of making it more useful for clinical decision making. We evaluated the model using two PGHD sources, and outline the process of sharing this information with an EHR in standardized RDF/FHIR formats. Future studies will seek to evaluate the model in a practical context with clinicians, to ensure alignment with their clinical practice and workflow.

Speaker:
Abdullahi Abubakar Kawu, Student
Technological University, Dublin

Authors:
Dympna O'Sullivan - Technological University Dublin; Lucy Hederman, Lecturer - Trinity College Dublin;