When AI Writes Back: Ethical Considerations by Physicians on AI-Drafted Patient Message Replies

Presentation Time: 02:00 PM - 02:12 PM

Abstract Keywords: Qualitative Methods, Legal, Ethical, Social and Regulatory Issues, Large Language Models (LLMs), Artificial Intelligence
Primary Track: Applications
Programmatic Theme: Clinical Informatics

The increasing burden of responding to large volumes of patient messages has become a key factor contributing to physician burnout. Generative AI (GenAI) shows great promise to alleviate this burden by automatically drafting patient message replies. The ethical implications of this use have however not been fully explored. To address this knowledge gap, we conducted a qualitative interview study with 21 physicians who participated in a GenAI pilot program. We found that human oversight as ethical safeguard, transparency and patient consent of AI use, patient misunderstanding of AI’s role, and patient privacy and data security as prerequisites are notable ethical considerations expressed by the physician participants. Additionally, our findings suggest that the physicians believe the ethical responsibility of using GenAI in this context primarily lies with users, not with the technology. These findings may provide useful insights into guiding the future implementation of GenAI in clinical practice.

Speaker:
Di Hu, Master of Science in Information Systems
University of California - Irvine

Authors:
Di Hu, Master of Science in Information Systems - University of California - Irvine; Yawen Guo, MISM - University of California - Irvine; Ha Na Cho, Ph.D - University of California, Irvine; Emilie Chow, MD - University of California, Irvine; Dana Mukamel, PhD - University of California, Irvine; Dara Sorkin, PhD - University of California, Irvine; Andrew Reikes, MD - University of California, Irvine; Danielle Perret, MD - University of California, Irvine; Deepti Pandita, MD, FACP, FAMIA - University of California Irvine; Kai Zheng, PhD - University of California, Irvine;

---

Right Patient, Right Specialist, Right Time: Retrieval Augmented Generation for Specialty Referral Routing

Presentation Time: 02:12 PM - 02:24 PM

Abstract Keywords: Machine Learning, Large Language Models (LLMs), Clinical Decision Support, Documentation Burden, Information Retrieval, Deep Learning
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Effective triage and routing of electronic consultations (eConsults) are essential for optimizing specialty care access. We present an embedding-based retrieval system that automatically directs physician clinical questions to the most relevant specialist-curated question template, which is necessary for the specialist to provide a clinically relevant response. The system utilizes MPNet, a transformer-based model, to generate dense vector representations of both clinical queries and 24 predefined clinical templates. Given a clinical question, the system computes cosine similarity between the query and template embeddings to retrieve the most relevant matches. When validated against real-world, retrospective eConsults across five specialties, the system accurately identified the most relevant template in 87% of cases (success@1) and included it in the top three results 99% of the time (success@3). Automating specialty selection and clinical question referrals reduces the administrative burden on physicians, minimizes care delivery delays, and improves specialist responses by providing proper context.

Speaker:
Fateme Nateghi Haredasht, PhD
Stanford University

Authors:
Ethan Goh, MD, MS - Stanford University; Vishnu Ravi, MD - Stanford University School of Medicine; Pooya Ashtari, Postdoctoral researcher - Department of Electrical Engineering (ESAT), STADIUS Center, KU Leuven; Yixing Jiang, PhD candidate - Stanford; François Grolleau, MD, PhD - Stanford Center for Biomedical Informatics Research; Robert Gallo, MD - VA Palo Alto Health Care System; Aaryan Shah, BSc - Department of Biomedical Data Science, Stanford University; Evelyn Hur, MSc - Department of Computer Science, Stanford University; Kanav Chopra, BSc - Department of Computer and Information Sciences, Webster University; Olivia Jee, MD - Division of Primary Care and Population Health, Stanford University School of Medicine; Julie Lee, MD, MPH - Stanford School of Medicine; Leah Rosengaus, MSc - Stanford Health Care, Stanford Medicine; Lena Giang, MPH - Stanford Health Care, Stanford Medicine; Kevin Schulman; Jason Hom, MD - Stanford University, School of Medicine; Arnold Milstein, MD, MPH - Clinical Excellence Research Center, Stanford University School of Medicine; Andrew Y. Ng, PhD - Department of Computer Science, Stanford University; Jonathan Chen, MD, PhD - Stanford University Hospital;

---

Computational Use of Patient–Provider Secure Messaging Data to Achieve Better Clinical Efficiency and Quality of Communication: A Systematic Review

Presentation Time: 02:24 PM - 02:36 PM

Abstract Keywords: Clinical Decision Support, Patient / Person Generated Health Data (Patient Reported Outcomes), Natural Language Processing, Artificial Intelligence
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Secure messaging (SM) between patients and providers has seen increasing adoption over the past decade, prompting development of computational methods to enable automation and research to enhance clinical efficiency and quality of communication. Through a systematic review, we examined the extant literature to investigate how previous studies had applied computational analyses to SM data. After screening 1,374 papers, we identified 19 relevant studies published between 2017 and 2024, most of which focused on applications for streamlining clinical workflows, facilitating early disease detection, supporting personalized decision making, and enhancing patient health literacy. Among the computational methods used, BERT was consistently shown to deliver best performance. However, all existing studies were constrained by small-size datasets and limited healthcare settings, leading to inadequate validation and poor generalizability. The results of this review highlight key research gaps, particularly the need for more robust computational approaches that ensure scalability, fairness, and clinical applicability.

Speaker:
Yawen Guo, MISM
University of California - Irvine

Authors:
Yawen Guo, MISM - University of California - Irvine; Di Hu, Master of Science in Information Systems - University of California - Irvine; Yiliang Zhou, PhD - University of California, Irvine; Tianchu Lyu, PhD - University of California, Irvine; Kai Zheng, PhD - University of California, Irvine;

---

Recommending Clinical Trials for Online Patient Cases using Artificial Intelligence

Presentation Time: 02:36 PM - 02:48 PM

Abstract Keywords: Clinical Decision Support, Real-World Evidence Generation, Usability, Social Media and Connected Health, Precision Medicine, Interoperability and Health Information Exchange, Large Language Models (LLMs), Machine Learning
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics

Clinical trials are crucial for assessing new treatments; however, recruitment challenges—such as limited awareness, complex eligibility criteria, and referral barriers—hinder their success. With the growth of online platforms, patients, caregivers, and family members increasingly post medical cases on social media and health communities, while physicians publish case reports accessible on platforms like PubMed—collectively expanding recruitment pools beyond traditional clinical trial pathways. Recognizing this potential, we utilized TrialGPT, a framework that leverages a large language model, to match 50 online patient cases (collected from case reports and social media) to clinical trials and evaluate performance against traditional keyword-based searches. Our results show that TrialGPT outperformed traditional methods by 46%, with patients eligible, on average, for 7 of the top 10 recommended trials. Additionally, outreach to case authors and trial organizers yielded positive feedback. These findings highlight TrialGPT’s potential to expand patient access to specialized care through non-traditional sources.

Speaker:
Joey Chan, M.S.
National Library of Medicine

Authors:
Joey Chan, Master's Degree - National Library of Medicine; Qiao Jin, M.D. - National Institutes of Health; Nicholas Wan, Bachelor of Engineering - National Institutes of Health; Charalampos Floudas, MD, DMSc, MS - NIH/NCI; Elisabetta Xue, M.D. - National Cancer Institute; Zhiyong Lu, PhD - National Library of Medicine, NIH;

---

Understanding Primary and Secondary Concerns from Patient Portal Messages through Clinical Data Annotation, Analysis, and Modeling

Presentation Time: 02:48 PM - 03:00 PM

Abstract Keywords: Deep Learning, Patient Engagement and Preferences, Natural Language Processing
Primary Track: Applications

Efficient triage and response to patient portal messages (PPMs) are critical for enhancing patient-centered care. To improve the understanding of primary and secondary concerns expressed by patients, this study annotated and analyzed a set of 2,239 PPMs. We also automated the patient concern identification and analysis by leveraging pretrained language models with binary classification to discern all patient concerns and with multi-class classification to identify primary patient concerns. These multi-class classifications were further enhanced by integrating convolutional neural networks that utilize embeddings from the binary classification. This approach demonstrated significant potential of AI in managing the growing volume of PPMs and promptly addressing the healthcare needs of patients, thereby facilitating more effective and timely medical interventions.

Speaker:
Yuqi Wu, PhD, MPH, MPA
Mayo Clinic

Authors:
Yuqi Wu, PhD, MPH, MPA - Mayo Clinic; Yang Ren, Ph.D. - Yale University; Heling Jia, MD - Mayo Clinic; Taylor Harrison, MS, MBA - Mayo Clinic; Jungwei Fan, Ph.D. - Mayo Clinic; Hongfang Liu, PhD - University of Texas Health Science Center at Houston; Ming Huang, PhD - UTHealth Houston;

---

CaLM-ADRD: A Dual-Knowledge Conversational AI System for Dementia Caregiving Support

Presentation Time: 03:00 PM - 03:12 PM

Abstract Keywords: Artificial Intelligence, Large Language Models (LLMs), Delivering Health Information and Knowledge to the Public
Primary Track: Applications

CaLM-ADRD is a domain-specific conversational AI system designed to support family caregivers of individuals with Alzheimer’s disease and related dementias (ADRD). Built on a retrieval-augmented generation framework with a dual knowledge base, it combines peer support and clinically validated content. CaLM-ADRD demonstrated strong retrieval performance and generation quality comparable to GPT-4o. This system offers an efficient, interpretable, and emotionally responsive tool for addressing the complex informational and emotional needs of dementia caregivers.

Speaker:
Yuxuan Zhou, Master
University of Pittsburgh

Authors:
Yuxuan Zhou, Master of Science - University of Pittsburgh; Bayu Aryoyudanta, Master - University of Pittsburgh; Haomin Hu, PhD in Rehabilitation Science - University of Pittsburgh; Hongtao Wang, Bachelor of Arts - University of Pittsburgh; Andi Saptono, PhD - University of Pittsburgh School of Health and Rehabilitation Services; Bambang Parmanto, PhD - University of Pittsburgh; Yong Kyung Choi, PhD, MPH - University of Pittsburgh;

---