Times are displayed in (UTC-08:00) Pacific Time (US & Canada) Change
11/12/2024 |
8:30 AM – 10:00 AM |
Golden Gate 1-2
S64: AI in Clinical Workflows - The Flow Show
Presentation Type: Oral
Session Chair:
Blanca Himes
Description
An onsite recording of this session will be included in the Symposium OnDemand offering.
Care Development Diagrams to Investigate Potential Interventions to Reach Trafficked Individuals in Emergency Departments
Presentation Time: 08:30 AM - 08:45 AM
Abstract Keywords: Qualitative Methods, Evaluation, Workflow
Primary Track: Applications
Programmatic Theme: Clinical Informatics
We sought to emphasize the points in care crucial to identifying and providing support to trafficked patients. We did this by investigating the current people, processes, technologies, and information flow throughout patient care in emergency care settings. We found that trafficked or potentially trafficked patients interact with a diverse network of people when visiting the ED. In addition, there is opportunity to improve identification in waiting room areas and how professionals provide resources to patients.
Speaker(s):
Michelle Gomez
Vanderbilt University
Author(s):
Michelle Gomez - Vanderbilt University; Kim Unertl, PhD - Vanderbilt University Medical Center;
Presentation Time: 08:30 AM - 08:45 AM
Abstract Keywords: Qualitative Methods, Evaluation, Workflow
Primary Track: Applications
Programmatic Theme: Clinical Informatics
We sought to emphasize the points in care crucial to identifying and providing support to trafficked patients. We did this by investigating the current people, processes, technologies, and information flow throughout patient care in emergency care settings. We found that trafficked or potentially trafficked patients interact with a diverse network of people when visiting the ED. In addition, there is opportunity to improve identification in waiting room areas and how professionals provide resources to patients.
Speaker(s):
Michelle Gomez
Vanderbilt University
Author(s):
Michelle Gomez - Vanderbilt University; Kim Unertl, PhD - Vanderbilt University Medical Center;
Integrating AI into Clinical Workflows: A Simulation Study on Implementing AI-aided Same-day Diagnostic Testing Following an Abnormal Screening Mammogram
Presentation Time: 08:45 AM - 09:00 AM
Abstract Keywords: Informatics Implementation, Workflow, Cancer Prevention
Primary Track: Applications
Programmatic Theme: Clinical Informatics
Artificial intelligence (AI) shows promise in clinical tasks, yet its integration into workflows remains underexplored. This study proposes an AI-aided same-day diagnostic imaging workup to reduce recall rates following abnormal screening mammograms and alleviate patient anxiety while waiting for the diagnostic examinations. Using discrete simulation, we found minimal disruption to the workflow (a 4% reduction in daily patient volume or a 2% increase in operating time) under specific conditions: operation from 9 am to 12 pm with all radiologists managing all patient types (screenings, diagnostics, and biopsies). Costs specific to the AI-aided same-day diagnostic workup include AI software expenses and potential losses from unused pre-reserved slots for same-day diagnostic workups. These simulation findings will inform the implementation of the AI-aided workup at our institution, with future research focusing on its potential benefits, including improved patient satisfaction, reduced anxiety, lower recall rates, and shorter time to cancer diagnoses and treatment.
Speaker(s):
William Hsu, PhD
University of California, Los Angeles
Author(s):
Anne Hoyt, M.D.; Vladimir Manuel, MD - University of California, Los Angeles; Moira Inkelas, MPH, PhD - University of California, Los Angeles; Cleo Maehara, MD, MMSc - University of California, Los Angeles; Mehmet Ulvi Saygi Ayvaci, PhD - University of Texas at Dallas; Mehmet Eren Ahsen, PhD - University of Illinois at Urbana-Champaign; William Hsu, PhD - University of California, Los Angeles;
Presentation Time: 08:45 AM - 09:00 AM
Abstract Keywords: Informatics Implementation, Workflow, Cancer Prevention
Primary Track: Applications
Programmatic Theme: Clinical Informatics
Artificial intelligence (AI) shows promise in clinical tasks, yet its integration into workflows remains underexplored. This study proposes an AI-aided same-day diagnostic imaging workup to reduce recall rates following abnormal screening mammograms and alleviate patient anxiety while waiting for the diagnostic examinations. Using discrete simulation, we found minimal disruption to the workflow (a 4% reduction in daily patient volume or a 2% increase in operating time) under specific conditions: operation from 9 am to 12 pm with all radiologists managing all patient types (screenings, diagnostics, and biopsies). Costs specific to the AI-aided same-day diagnostic workup include AI software expenses and potential losses from unused pre-reserved slots for same-day diagnostic workups. These simulation findings will inform the implementation of the AI-aided workup at our institution, with future research focusing on its potential benefits, including improved patient satisfaction, reduced anxiety, lower recall rates, and shorter time to cancer diagnoses and treatment.
Speaker(s):
William Hsu, PhD
University of California, Los Angeles
Author(s):
Anne Hoyt, M.D.; Vladimir Manuel, MD - University of California, Los Angeles; Moira Inkelas, MPH, PhD - University of California, Los Angeles; Cleo Maehara, MD, MMSc - University of California, Los Angeles; Mehmet Ulvi Saygi Ayvaci, PhD - University of Texas at Dallas; Mehmet Eren Ahsen, PhD - University of Illinois at Urbana-Champaign; William Hsu, PhD - University of California, Los Angeles;
Use of a Digital Handoff Tool to Support Team Coordination
Presentation Time: 09:00 AM - 09:15 AM
Abstract Keywords: Transitions of Care, Workflow, Patient Safety
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics
Handoff tools embedded in the electronic health record (EHR) are critical to promoting continuity of care during shift change. In an analysis of hospital medicine providers' use of such a tool across a large academic hospital, we find significant variation in when and how this tool is used. We characterize interdependence between daytime documentation and nightshift behavior, signifying the importance of optimizing use of this tool in practice to achieve consistent, high-quality handoffs.
Speaker(s):
Andrew Olson, MD
University of Minnesota Medical School Twin Cities
Author(s):
Dori Cross, PhD - University of Minnesota School of Public Health; Josh Weiner, B.A. - University of Minnesota; Genevieve Melton-Meaux, MD, PhD - University of Minnesota; Andrew Olson - University of Minnesota Medical School Twin Cities;
Presentation Time: 09:00 AM - 09:15 AM
Abstract Keywords: Transitions of Care, Workflow, Patient Safety
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics
Handoff tools embedded in the electronic health record (EHR) are critical to promoting continuity of care during shift change. In an analysis of hospital medicine providers' use of such a tool across a large academic hospital, we find significant variation in when and how this tool is used. We characterize interdependence between daytime documentation and nightshift behavior, signifying the importance of optimizing use of this tool in practice to achieve consistent, high-quality handoffs.
Speaker(s):
Andrew Olson, MD
University of Minnesota Medical School Twin Cities
Author(s):
Dori Cross, PhD - University of Minnesota School of Public Health; Josh Weiner, B.A. - University of Minnesota; Genevieve Melton-Meaux, MD, PhD - University of Minnesota; Andrew Olson - University of Minnesota Medical School Twin Cities;
How Team Structures Impact Primary Care Physicians' EHR Time
Presentation Time: 09:15 AM - 09:30 AM
Abstract Keywords: Workflow, Qualitative Methods, Healthcare Quality
Primary Track: Foundations
Programmatic Theme: Clinical Research Informatics
Primary care physicians (PCP) spend the most time in the electronic health record (EHR) of any specialty, which is associated with PCP burnout. We used mixed methods to explore the variation in clinical teams across 14 primary care sites and characterize the influence of team structure on PCP EHR time. Our quantitative data showed having set teams is associated with less EHR time, while the qualitative data highlighted the need for consistent staffing.
Speaker(s):
Estelle Martin
Author(s):
Lisa Rotenstein, MD, MBA, MSc - UCSF; Estelle Martin; Christine Iannaccone, MPH - Brigham and Women's Hospital; John Lewis, MD - Brigham and Women's Faulkner Hospital; Lance Rachelefsky, MS - Brigham and Women's Hospital; Richard Gitomer, MD - MDlive; Christine Sinsky, MD - American Medical Association; Erin Sullivan, PhD - Harvard Medical School;
Presentation Time: 09:15 AM - 09:30 AM
Abstract Keywords: Workflow, Qualitative Methods, Healthcare Quality
Primary Track: Foundations
Programmatic Theme: Clinical Research Informatics
Primary care physicians (PCP) spend the most time in the electronic health record (EHR) of any specialty, which is associated with PCP burnout. We used mixed methods to explore the variation in clinical teams across 14 primary care sites and characterize the influence of team structure on PCP EHR time. Our quantitative data showed having set teams is associated with less EHR time, while the qualitative data highlighted the need for consistent staffing.
Speaker(s):
Estelle Martin
Author(s):
Lisa Rotenstein, MD, MBA, MSc - UCSF; Estelle Martin; Christine Iannaccone, MPH - Brigham and Women's Hospital; John Lewis, MD - Brigham and Women's Faulkner Hospital; Lance Rachelefsky, MS - Brigham and Women's Hospital; Richard Gitomer, MD - MDlive; Christine Sinsky, MD - American Medical Association; Erin Sullivan, PhD - Harvard Medical School;
Transforming Healthcare Workflows with Robotic Process Automation (RPA): Insights from Champions and Providers
Presentation Time: 09:30 AM - 09:45 AM
Abstract Keywords: Qualitative Methods, Administrative Systems, Workflow, Informatics Implementation, Information Retrieval
Primary Track: Applications
Programmatic Theme: Clinical Informatics
This study explores the integration of Robotic Process Automation (RPA) in Electronic Health Record systems to enhance healthcare workflows, particularly the First Contact Provider (FCP) initiative. Qualitative analysis reveals improved efficiency and FCP protocol adherence post-RPA implementation. Challenges like communication gaps and alert fatigue stress the need for pre-implementation preparation and stakeholder engagement. The study highlights RPA's broader impact on healthcare practices and suggests future exploration of integrating generative artificial intelligence for further enhancements.
Speaker(s):
Tiffany Martinez, BA
NYU Grossman School of Medicine
Author(s):
Tiffany Martinez, BA - NYU Grossman School of Medicine; Katerina Andreadis, MS - NYU Grossman School of Medicine; Christopher Sonne, MD - NYU Grossman School of Medicine; Ulka Kothari, MD - NYU Langone Medical Center; Thomas Roncoli, BA - NYU Langone Health; Ajay Mansukhani, BA - NYU Langone Health; Hardev Randhawa, BA - NYU Langone Health; Jonah Feldman, MD, FACP - NYU Langone Health;
Presentation Time: 09:30 AM - 09:45 AM
Abstract Keywords: Qualitative Methods, Administrative Systems, Workflow, Informatics Implementation, Information Retrieval
Primary Track: Applications
Programmatic Theme: Clinical Informatics
This study explores the integration of Robotic Process Automation (RPA) in Electronic Health Record systems to enhance healthcare workflows, particularly the First Contact Provider (FCP) initiative. Qualitative analysis reveals improved efficiency and FCP protocol adherence post-RPA implementation. Challenges like communication gaps and alert fatigue stress the need for pre-implementation preparation and stakeholder engagement. The study highlights RPA's broader impact on healthcare practices and suggests future exploration of integrating generative artificial intelligence for further enhancements.
Speaker(s):
Tiffany Martinez, BA
NYU Grossman School of Medicine
Author(s):
Tiffany Martinez, BA - NYU Grossman School of Medicine; Katerina Andreadis, MS - NYU Grossman School of Medicine; Christopher Sonne, MD - NYU Grossman School of Medicine; Ulka Kothari, MD - NYU Langone Medical Center; Thomas Roncoli, BA - NYU Langone Health; Ajay Mansukhani, BA - NYU Langone Health; Hardev Randhawa, BA - NYU Langone Health; Jonah Feldman, MD, FACP - NYU Langone Health;
Glaucoma Clinical Decision Making Workflow
Presentation Time: 09:45 AM - 10:00 AM
Abstract Keywords: Workflow, Chronic Care Management, Clinical Decision Support
Primary Track: Applications
Implementing clinical decision support (CDS) systems for chronic diseases is challenging because the workflows for chronic conditions are often complex, with large amounts of longitudinal data collected from multiple sources. An
accurate understanding of complex workflows may increase the likelihood of successful CDS implementation. Glaucoma care is an example of a complex workflow with large amounts of data from multiple sources that are collected over time. We conducted a qualitative study using cognitive task analysis (CTA) and ethnographic observations to create a detailed conceptual model of glaucoma clinical decision making workflow to will support glaucoma CDS development and implementation in the future. We conducted 17 CTA interviews and ethnographic observations. From the CTA interviews and ethnographic observations, we identified key challenges to glaucoma CDS implementation that will need to be addressed for future CDS implementation: (1) Glaucoma data is longitudinal and so integrated temporal data views may improve clinical decision making;3,4 (2) Standards-based interoperability between the various imaging and EHR platforms was an emergent issue from the cognitive task analysis that could be addressed with CDS; (3) Clinicians identified the need to account for unique patient circumstances including emergencies with contingencies as important aspects of the workflow and future CDS will need to account for this; and (4) Facilitation of incoming and outgoing patient referrals is a glaucoma workflow challenge that could be addressed with interoperable, standards-based CDS. The model of glaucoma clinical decision-making workflow will support glaucoma CDS development and implementation in the future.
Speaker(s):
Brian Stagg, MD, MS
University of Utah
Author(s):
Presentation Time: 09:45 AM - 10:00 AM
Abstract Keywords: Workflow, Chronic Care Management, Clinical Decision Support
Primary Track: Applications
Implementing clinical decision support (CDS) systems for chronic diseases is challenging because the workflows for chronic conditions are often complex, with large amounts of longitudinal data collected from multiple sources. An
accurate understanding of complex workflows may increase the likelihood of successful CDS implementation. Glaucoma care is an example of a complex workflow with large amounts of data from multiple sources that are collected over time. We conducted a qualitative study using cognitive task analysis (CTA) and ethnographic observations to create a detailed conceptual model of glaucoma clinical decision making workflow to will support glaucoma CDS development and implementation in the future. We conducted 17 CTA interviews and ethnographic observations. From the CTA interviews and ethnographic observations, we identified key challenges to glaucoma CDS implementation that will need to be addressed for future CDS implementation: (1) Glaucoma data is longitudinal and so integrated temporal data views may improve clinical decision making;3,4 (2) Standards-based interoperability between the various imaging and EHR platforms was an emergent issue from the cognitive task analysis that could be addressed with CDS; (3) Clinicians identified the need to account for unique patient circumstances including emergencies with contingencies as important aspects of the workflow and future CDS will need to account for this; and (4) Facilitation of incoming and outgoing patient referrals is a glaucoma workflow challenge that could be addressed with interoperable, standards-based CDS. The model of glaucoma clinical decision-making workflow will support glaucoma CDS development and implementation in the future.
Speaker(s):
Brian Stagg, MD, MS
University of Utah
Author(s):