Times are displayed in (UTC-04:00) Eastern Time (US & Canada) Change
11/17/2025 |
2:00 PM – 3:15 PM |
Room 4
S35: Choose Wisely: AI Enhanced Decision Support Across Clinical and Public Health Settings
Presentation Type: Oral Presentations
Sensitivity Analyses of a Scoring System for a Contraception Decision Aid
2025 Annual Symposium On Demand
Presentation Time: 02:00 PM - 02:12 PM
Abstract Keywords: Clinical Decision Support, Evaluation, Delivering Health Information and Knowledge to the Public, Knowledge Representation and Information Modeling, Education and Training, Health Equity, Patient Engagement and Preferences, User-centered Design Methods
Primary Track: Foundations
Programmatic Theme: Clinical Informatics
We conducted formal analyses of a scoring system for a contraception decision aid to support transgender and gender-nonconforming (TGNC) assigned female at birth (AFAB) individuals. For this purpose, we developed a methodology framework to assess the weights for each decision factor, to conduct univariate and multivariate sensitivity analyses, and to provide data visualization, which led to successful identification of critical values in weight assignment that can impact the recommendations generated by the system. These analyses made critical contributions to development and validation of the system’s knowledge base, providing explainable recommendations, and conducting additional research related to system users and functions. Future research is required to explore high-dimensional sensitivity analyses, to address technical issues identified, and to examine the generalizability of the methodology to other applications.
Speaker:
Sanyam Paresh Shah, Bachelor of Science in Biomedical Informatics
Arizona State University
Authors:
Sanyam Paresh Shah, Bachelor of Science in Biomedical Informatics - Arizona State University; Tanuj Singh Shekhawat, PhD - Arizona State University; Vi-Anh Hoang, B.S. - Washington University School of Medicine in St. Louis; Erin Chiou, PhD - Arizona State University; Jennifer Brian, PhD - Arizona State University; Dongwen Wang, PhD - Arizona State University;
2025 Annual Symposium On Demand
Presentation Time: 02:00 PM - 02:12 PM
Abstract Keywords: Clinical Decision Support, Evaluation, Delivering Health Information and Knowledge to the Public, Knowledge Representation and Information Modeling, Education and Training, Health Equity, Patient Engagement and Preferences, User-centered Design Methods
Primary Track: Foundations
Programmatic Theme: Clinical Informatics
We conducted formal analyses of a scoring system for a contraception decision aid to support transgender and gender-nonconforming (TGNC) assigned female at birth (AFAB) individuals. For this purpose, we developed a methodology framework to assess the weights for each decision factor, to conduct univariate and multivariate sensitivity analyses, and to provide data visualization, which led to successful identification of critical values in weight assignment that can impact the recommendations generated by the system. These analyses made critical contributions to development and validation of the system’s knowledge base, providing explainable recommendations, and conducting additional research related to system users and functions. Future research is required to explore high-dimensional sensitivity analyses, to address technical issues identified, and to examine the generalizability of the methodology to other applications.
Speaker:
Sanyam Paresh Shah, Bachelor of Science in Biomedical Informatics
Arizona State University
Authors:
Sanyam Paresh Shah, Bachelor of Science in Biomedical Informatics - Arizona State University; Tanuj Singh Shekhawat, PhD - Arizona State University; Vi-Anh Hoang, B.S. - Washington University School of Medicine in St. Louis; Erin Chiou, PhD - Arizona State University; Jennifer Brian, PhD - Arizona State University; Dongwen Wang, PhD - Arizona State University;
CDR-Agent: Intelligent Selection and Execution of Clinical Decision Rules Using Large Language Model Agents
2025 Annual Symposium On Demand
Presentation Time: 02:12 PM - 02:24 PM
Abstract Keywords: Clinical Decision Support, Large Language Models (LLMs), Natural Language Processing
Primary Track: Applications
Clinical decision-making is inherently complex and fast-paced, particularly in emergency departments (EDs) where critical, rapid and high-stakes decisions are made. Clinical Decision Rules (CDRs) are standardized evidence-based tools that combine signs, symptoms, and clinical variables into decision trees to make consistent and accurate diagnoses. CDR usage is often hindered by the clinician's cognitive load, limiting their ability to quickly recall and apply the appropriate rules. We introduce CDR-Agent, a novel LLM-based system designed to enhance ED decision-making by autonomously identifying and applying the most appropriate CDRs based on unstructured clinical notes. To validate CDR-Agent, we curated two novel ED datasets: synthetic and CDR-Bench, although CDR-Agent is applicable to non ED clinics. CDR-Agent achieves a 56.3% (synthetic) and 8.7% (CDR-Bench) accuracy gain relative to the standalone LLM baseline in CDR selection, with overall prediction accuracy improvements of 134.0% (synthetic) and 20.4% (CDR-Bench). Moreover, CDR-Agent significantly reduces computational overhead.
Speaker:
Zhen Xiang, PhD
University of Georgia
Authors:
Zhen Xiang, PhD - University of Georgia; Aliyah Hsu, BS - University of California, Berkeley; Austin V. Zane, BS - University of California, Berkeley; Aaron E. Kornblith, MD - University of California, San Francisco; Margaret J. Lin-Martore, Md - University of California, San Francisco; Jasmanpreet C. Kau, md - University of California, San Francisco; Vasuda M. Dokiparthi, MD - University of California, San Francisco; Bo Li, phd - University of Chicago; Bin Yu, phd - University of California, Berkeley;
2025 Annual Symposium On Demand
Presentation Time: 02:12 PM - 02:24 PM
Abstract Keywords: Clinical Decision Support, Large Language Models (LLMs), Natural Language Processing
Primary Track: Applications
Clinical decision-making is inherently complex and fast-paced, particularly in emergency departments (EDs) where critical, rapid and high-stakes decisions are made. Clinical Decision Rules (CDRs) are standardized evidence-based tools that combine signs, symptoms, and clinical variables into decision trees to make consistent and accurate diagnoses. CDR usage is often hindered by the clinician's cognitive load, limiting their ability to quickly recall and apply the appropriate rules. We introduce CDR-Agent, a novel LLM-based system designed to enhance ED decision-making by autonomously identifying and applying the most appropriate CDRs based on unstructured clinical notes. To validate CDR-Agent, we curated two novel ED datasets: synthetic and CDR-Bench, although CDR-Agent is applicable to non ED clinics. CDR-Agent achieves a 56.3% (synthetic) and 8.7% (CDR-Bench) accuracy gain relative to the standalone LLM baseline in CDR selection, with overall prediction accuracy improvements of 134.0% (synthetic) and 20.4% (CDR-Bench). Moreover, CDR-Agent significantly reduces computational overhead.
Speaker:
Zhen Xiang, PhD
University of Georgia
Authors:
Zhen Xiang, PhD - University of Georgia; Aliyah Hsu, BS - University of California, Berkeley; Austin V. Zane, BS - University of California, Berkeley; Aaron E. Kornblith, MD - University of California, San Francisco; Margaret J. Lin-Martore, Md - University of California, San Francisco; Jasmanpreet C. Kau, md - University of California, San Francisco; Vasuda M. Dokiparthi, MD - University of California, San Francisco; Bo Li, phd - University of Chicago; Bin Yu, phd - University of California, Berkeley;
Decision Making During Outbreaks: Assessing the Data, Modeling, Analytics, and Other Decision-Support Needs of Governors and Their Health Advisors
2025 Annual Symposium On Demand
Presentation Time: 02:24 PM - 02:36 PM
Abstract Keywords: Surveys and Needs Analysis, Public Health, Data Modernization, Qualitative Methods, Governance
Primary Track: Policy
Programmatic Theme: Public Health Informatics
Decision-making during infectious disease emergencies requires elected leaders to address complex challenges. During COVID-19, Governors made urgent decisions on business operations, mask mandates, and resource allocation. The Center for Outbreak Response Innovation (CORI) conducted a needs assessment in partnership with the National Governors Association Center for Best Practices (NGA) to understand critical gubernatorial decisions during outbreaks and identify data, modeling, analytics, and decision support needs to improve future decision-making capabilities during outbreak responses.
Speaker:
Haley Farrie, MPH
Johns Hopkins Center for Outbreak Response Innovation
Authors:
Elizabeth Campbell, MS, MSPH, PhD - Johns Hopkins Bloomberg School of Public Health; Hannah Goodtree, MPH - Johns Hopkins Center for Outbreak Response Innovation; Oluremilekun Oyefolu, MD, MPH - Johns Hopkins Center for Outbreak Response Innovation; Crystal Watson, DrPH, MPH - Johns Hopkins Center for Outbreak Response Innovation;
2025 Annual Symposium On Demand
Presentation Time: 02:24 PM - 02:36 PM
Abstract Keywords: Surveys and Needs Analysis, Public Health, Data Modernization, Qualitative Methods, Governance
Primary Track: Policy
Programmatic Theme: Public Health Informatics
Decision-making during infectious disease emergencies requires elected leaders to address complex challenges. During COVID-19, Governors made urgent decisions on business operations, mask mandates, and resource allocation. The Center for Outbreak Response Innovation (CORI) conducted a needs assessment in partnership with the National Governors Association Center for Best Practices (NGA) to understand critical gubernatorial decisions during outbreaks and identify data, modeling, analytics, and decision support needs to improve future decision-making capabilities during outbreak responses.
Speaker:
Haley Farrie, MPH
Johns Hopkins Center for Outbreak Response Innovation
Authors:
Elizabeth Campbell, MS, MSPH, PhD - Johns Hopkins Bloomberg School of Public Health; Hannah Goodtree, MPH - Johns Hopkins Center for Outbreak Response Innovation; Oluremilekun Oyefolu, MD, MPH - Johns Hopkins Center for Outbreak Response Innovation; Crystal Watson, DrPH, MPH - Johns Hopkins Center for Outbreak Response Innovation;
Is SHAP explanation sufficient for healthcare professionals’ decision-making?
2025 Annual Symposium On Demand
Presentation Time: 02:36 PM - 02:48 PM
Abstract Keywords: Clinical Decision Support, Artificial Intelligence, Information Visualization
Primary Track: Foundations
Programmatic Theme: Clinical Informatics
Explainable artificial intelligence AI (XAI) improves acceptance and trust with explanations, but the effectiveness of different methods remains uncertain. We compared the acceptance, trust, satisfaction, and usability of various explanatory methods among clinicians. We also explored the factors associated with acceptance levels for each item using trust, satisfaction, and usability score questionnaires. We found that a clinical explanation improves clinician acceptance more than presenting only results or results with SHAP.
Speaker:
Sujeong Hur, PhD
AvoMD Inc
Authors:
Yura Lee - Asan Medical Center; Joongheum Park, MD - AvoMD; Yeong Jeong Jeon, MD/PhD - Samsung Medical Center; Jong Ho Cho, MD/PhD - Samsung Medical Center; Duck Cho, MD/PhD - Samsung Medical Center; Dobin Lim, MS - Soongsil University; Wonil Hwang, PhD - Soongsil University; Won Chul Cha - SUNGKYUNKWAN UNIVERSITY; Junsang Yoo - SAIHST; Sujeong Hur, PhD - AvoMD Inc;
2025 Annual Symposium On Demand
Presentation Time: 02:36 PM - 02:48 PM
Abstract Keywords: Clinical Decision Support, Artificial Intelligence, Information Visualization
Primary Track: Foundations
Programmatic Theme: Clinical Informatics
Explainable artificial intelligence AI (XAI) improves acceptance and trust with explanations, but the effectiveness of different methods remains uncertain. We compared the acceptance, trust, satisfaction, and usability of various explanatory methods among clinicians. We also explored the factors associated with acceptance levels for each item using trust, satisfaction, and usability score questionnaires. We found that a clinical explanation improves clinician acceptance more than presenting only results or results with SHAP.
Speaker:
Sujeong Hur, PhD
AvoMD Inc
Authors:
Yura Lee - Asan Medical Center; Joongheum Park, MD - AvoMD; Yeong Jeong Jeon, MD/PhD - Samsung Medical Center; Jong Ho Cho, MD/PhD - Samsung Medical Center; Duck Cho, MD/PhD - Samsung Medical Center; Dobin Lim, MS - Soongsil University; Wonil Hwang, PhD - Soongsil University; Won Chul Cha - SUNGKYUNKWAN UNIVERSITY; Junsang Yoo - SAIHST; Sujeong Hur, PhD - AvoMD Inc;
CPGPrompt: Translating Clinical Guidelines into LLM-Executable Decision Support – A Pilot Study
2025 Annual Symposium On Demand
Presentation Time: 02:48 PM - 03:00 PM
Abstract Keywords: Clinical Guidelines, Large Language Models (LLMs), Clinical Decision Support
Primary Track: Applications
Programmatic Theme: Clinical Informatics
We propose CPGPrompt, an auto-prompting system that translates Clinical Practice Guidelines (CPGs) into a Large Language Model (LLM)-executable format, enhancing interpretable clinical decision-making while facilitating the efficient implementation of CPGs in primary care settings. Using headache management as a case study, we demonstrate that CPGPrompt successfully guides the LLM to make accurate high-level clinical decisions, highlighting its potential to improve transparent and guideline-compliant AI-assisted healthcare.
Speaker:
Yifan Peng, PhD
Weill Cornell Medicine; Dept of Population Health Sciences; Div of Health Informatics
Authors:
Ruiqi Deng, Master’s Student, Information Science, Cornell Tech - Cornell Tech; Xizhi Wu, Master of Science - University of Pittsburgh; Tony Wang, Master's Student - Cornell University; Estefanie Garduno Rapp, MD - UT Southwestern Medical Center; Qian Yang, PhD - Cornell University; Yanshan Wang, PhD - University of Pittsburgh; Justin Rousseau, MD, MMSc - University of Texas Southwestern Medical Center; Yifan Peng, PhD - Weill Cornell Medicine; Dept of Population Health Sciences; Div of Health Informatics;
2025 Annual Symposium On Demand
Presentation Time: 02:48 PM - 03:00 PM
Abstract Keywords: Clinical Guidelines, Large Language Models (LLMs), Clinical Decision Support
Primary Track: Applications
Programmatic Theme: Clinical Informatics
We propose CPGPrompt, an auto-prompting system that translates Clinical Practice Guidelines (CPGs) into a Large Language Model (LLM)-executable format, enhancing interpretable clinical decision-making while facilitating the efficient implementation of CPGs in primary care settings. Using headache management as a case study, we demonstrate that CPGPrompt successfully guides the LLM to make accurate high-level clinical decisions, highlighting its potential to improve transparent and guideline-compliant AI-assisted healthcare.
Speaker:
Yifan Peng, PhD
Weill Cornell Medicine; Dept of Population Health Sciences; Div of Health Informatics
Authors:
Ruiqi Deng, Master’s Student, Information Science, Cornell Tech - Cornell Tech; Xizhi Wu, Master of Science - University of Pittsburgh; Tony Wang, Master's Student - Cornell University; Estefanie Garduno Rapp, MD - UT Southwestern Medical Center; Qian Yang, PhD - Cornell University; Yanshan Wang, PhD - University of Pittsburgh; Justin Rousseau, MD, MMSc - University of Texas Southwestern Medical Center; Yifan Peng, PhD - Weill Cornell Medicine; Dept of Population Health Sciences; Div of Health Informatics;
Optimizing Order Sets in Clinical Decision Support with an LLM-Powered Multi-Agent System and Expert Value Alignment
2025 Annual Symposium On Demand
Presentation Time: 03:00 PM - 03:12 PM
Abstract Keywords: Clinical Decision Support, Large Language Models (LLMs), Artificial Intelligence
Primary Track: Applications
We developed and evaluated an LLM-powered multi-agent system to optimize clinical decision support order sets. The system, comprising five specialized agents, generated suggestions that were rated by physicians on accuracy, usefulness, feasibility, and impact. 44 out of 96 suggestions (46%) aligned with historical ordering patterns. The median useful suggestions was 2. After alignment, Cohen’s Kappa improved from 0.06 (poor) to 0.41 (moderate). Leveraging multi-agent systems provides a systematic and scalable approach to optimizing order sets,
Speaker:
Siru Liu, PhD
Vanderbilt University Medical Center
Authors:
Sean Huang, MD - Vanderbilt University; Allison McCoy, PhD, ACHIP, FACMI, FAMIA - Vanderbilt University Medical Center; Aileen Wright, MD - Vanderbilt; Sara Horst, MD MPH; Adam Wright, PhD - Vanderbilt University Medical Center;
2025 Annual Symposium On Demand
Presentation Time: 03:00 PM - 03:12 PM
Abstract Keywords: Clinical Decision Support, Large Language Models (LLMs), Artificial Intelligence
Primary Track: Applications
We developed and evaluated an LLM-powered multi-agent system to optimize clinical decision support order sets. The system, comprising five specialized agents, generated suggestions that were rated by physicians on accuracy, usefulness, feasibility, and impact. 44 out of 96 suggestions (46%) aligned with historical ordering patterns. The median useful suggestions was 2. After alignment, Cohen’s Kappa improved from 0.06 (poor) to 0.41 (moderate). Leveraging multi-agent systems provides a systematic and scalable approach to optimizing order sets,
Speaker:
Siru Liu, PhD
Vanderbilt University Medical Center
Authors:
Sean Huang, MD - Vanderbilt University; Allison McCoy, PhD, ACHIP, FACMI, FAMIA - Vanderbilt University Medical Center; Aileen Wright, MD - Vanderbilt; Sara Horst, MD MPH; Adam Wright, PhD - Vanderbilt University Medical Center;