Custom CSS
double-click to edit, do not edit in source
5/19/2026 |
11:15 AM – 12:30 PM |
Mt. Sopris A - Grand Hyatt Denver, Lobby Level
CI21: Sensors, Signals, and Safety (Oral Presentations)
Presentation Type: Oral Presentations
Session Credits: 1.25
Personalized and Context-Aware Transformer Models for Predicting Post-Intervention Physiological Responses from Wearable Sensor Data
Presentation Type: Oral Presentation - Student
Presentation Time: 11:15 AM - 11:27 AM
Abstract Keywords: Wearable Health Technology, Analytical Artificial Intelligence: ML, Digital Pathology, Imaging AI, Predictive Analytics, Governance, Health Data Science
Primary Track: Big Data for Health
Consumer wearables enable continuous measurement of physiological data related to stress and recovery, but turning these streams into actionable, personalized stress-management recommendations remains a challenge. In practice, users often do not know how a given intervention, defined as an activity intended to reduce stress, will affect heart rate (HR), heart rate variability (HRV), or inter-beat intervals (BBI) over the next 15 to 120 minutes. We present a framework that predicts post-intervention trajectories and the direction of change for these physiological indicators across time windows. Our methodology combines a Transformer model for multi-horizon trajectories of percent change relative to a pre-intervention baseline, directional calls (positive, negative, or neutral) at each horizon, and an empirical study using wearable sensor data overlaid with user-tagged events and interventions. This proof of concept shows that personalized post-intervention prediction is feasible. We encourage future integration into stress-management tools for personalized intervention recommendations tailored to each person’s day.
Speaker(s):
Esther Brown, Student
Harvard University
Author(s):
Esther Brown, Student - Harvard University;
Finale Doshi-Velez, PhD - Harvard;
Victoria Dean, PhD - Princeton;
Esther
Brown,
Student - Harvard University
Evaluation of Bedside Monitor Integration Usage and Data Impact
Presentation Type: Oral Presentation - Regular
Presentation Time: 11:27 AM - 11:39 AM
Abstract Keywords: Workforce Automation, Communication, and Workflow Efficiency, Health Data Science, Quality Informatics and Lean, Diagnostics, Clinical Decision Support and Care Pathways, Change Management
Primary Track: Implementing Real-World Change, Digital Engagement, and Connected Health
Biomedical device integration (BMDI) enables automated vital sign documentation from monitors to electronic health records. We evaluated BMDI utilization following implementation across medical-surgical units. While 92% of admissions used BMDI, in observation-level analysis only 19% of blood pressures, 48% of oxygen saturations, and 50% of pulse rates were collected via integration. BMDI-collected observations demonstrated less digit preference but greater timing regularity than manual entries, raising data comparability questions for secondary data use.
Speaker(s):
Thomas McCoy, MD
Mass General Hospital
Author(s):
Thomas McCoy, MD - Mass General Hospital;
Sara Golas, MA - Partners HealthCare Connected Health Innovation;
Thomas
McCoy,
MD - Mass General Hospital
Tiny Doses, Big Impact: Improving Provider and Parent Understanding of Tylenol and Motrin Dosing
Presentation Type: Oral Presentation - Regular
Presentation Time: 11:39 AM - 11:51 AM
Abstract Keywords: Precision Medicine, Multi-Omics, and Pharmacology Integration, Clinical Decision Support and Care Pathways, Human Factors and Usability, Clinician Well-Being
Primary Track: Implementing Real-World Change, Digital Engagement, and Connected Health
Accurate dosing of over-the-counter (OTC) medications such as acetaminophen (Tylenol) and ibuprofen (Motrin) is essential for safe and effective pediatric care, yet dosing confusion remains common among parents and even healthcare providers. This session explores strategies to enhance parent and provider education and promote health literacy around OTC medication use using pictographic, patient-specific, age- and weight based dosing guidance.
Speaker(s):
John Grisham, MD
Nationwide Children's Hospital
Author(s):
John Grisham, MD - Nationwide Children's Hospital;
Emily Sentman, MD - Nationwide Children's Hospital;
Laura Rust, MD MPH - Nationwide Children's Hospital;
John
Grisham,
MD - Nationwide Children's Hospital
SEIPS 101: EHR Integration of a NICU Emergency Code Sheet Is Associated with Improved Safety, Usability, and Efficiency
Presentation Type: Oral Presentation - Regular
Presentation Time: 11:51 AM - 12:03 PM
Abstract Keywords: Human Factors and Usability, Change Management, Outcomes Improvement and Equity, Education and Training, Clinician Well-Being, Leadership and Strategy
Primary Track: Advancing Wellness for Providers and Community with Consideration of Human Factors
Through the application of the SEIPS 101 model, an EHR-integrated emergency code sheet was implemented in the Children’s Hospital of Philadelphia neonatal intensive care unit. Integration significantly improved usability, safety, and efficiency compared to a previous Excel-based non-EHR workflow. These findings highlight how human factors principles and EHR integration can enhance emergency medication preparation at the bedside in pediatric care.
Speaker(s):
Alex Ruan, MD
Children's Hospital of Philadelphia
Author(s):
Osvaldo Mercado, MD - Children's Hospital of Philadelphia;
Lauren Heimall, MSN - Children's Hospital of Philadelphia;
Anna O'Brien, PharmD - Children's Hospital of Philadelphia;
Janine Cockerham, MSN - Children's Hospital of Philadelphia;
Matthew Coyle, BS, MPH - Children's Hospital of Philadelphia;
Stan Krajewski, BBA, MIS - Children's Hospital of Philadelphia;
Leah Carr, MD - Children's Hospital of Philadelphia;
Alex
Ruan,
MD - Children's Hospital of Philadelphia
Enhanced Operating Room Cleaning Utilizing Automation
Presentation Type: Oral Presentation - Regular
Presentation Time: 12:03 PM - 12:15 PM
Abstract Keywords: Workforce Automation, Communication, and Workflow Efficiency, Human Factors and Usability, Change Management, Innovation Partnerships, Implementation Science, and Learning Health Systems
Primary Track: Implementing Real-World Change, Digital Engagement, and Connected Health
Operating rooms (ORs) are high-value hospital spaces where many organizations seek to improve efficiency gains. OR cleaning is one efficiency opportunity where robotic process automation (RPA) can facilitate timely requests for cleaning. We automated OR cleaning requests via RPA and saw a significant, 7.8% reduction in mean cleaning times. RPA offers an opportunity to tailor targeted cleaning requests while reducing the burden on clinicians to remember and initiate the request.
Speaker(s):
John Will, MPA
NYU Langone Health
Author(s):
John Will, MPA - NYU Langone Health;
Andrew Munfakh, MHSA - NYU Langone Health;
Jonathan Austrian, MD - NYU Langone Health;
Paul Testa, MD, JD, MPH - NYU Langone Health;
Jonah Feldman, MD, FACP - NYU Langone Health;
John
Will,
MPA - NYU Langone Health
Federated AI Monitoring Service (FAMOS): An in Silico Feasibility Study
Presentation Type: Oral Presentation - Regular
Presentation Time: 12:15 PM - 12:27 PM
Abstract Keywords: Analytical Artificial Intelligence: ML, Digital Pathology, Imaging AI, Predictive Analytics, Governance, Infrastructure and Cloud Computing, Human Factors and Usability, Data Privacy, Cybersecurity, Reliability, and Security
Primary Track: Implementing Real-World Change, Digital Engagement, and Connected Health
The long-term safety, reliability, and real-world effectiveness of radiology AI in clinical settings depend on socio-technical factors, highlighting the need for continuous oversight. We propose a real-time post-deployment monitoring approach to track changes in input data quality, AI inference distribution and user behaviour, allowing for proactive risk identification, and supporting the safe and responsible integration of AI into healthcare.
Speaker(s):
Haris Shuaib, MPhys MSc
Newton's Tree
Author(s):
Aysha Luis, MBBS BSc FRCR - Newton’s Tree, London, United Kingdom; Barts Health NHS Trust, London, United Kingdom; King’s College London, United Kingdom;
Andrew Scarsbrook, BMedSci BMBS FRCR - Leeds Teaching Hospitals NHS Trust, United Kingdom; University of Leeds, United Kingdom;
Jesus Perdomo Lampignano, BSc MBChB - Greater Glasgow and Clyde, United Kingdom; University of Glasgow, United Kingdom;
Matt Clark, BSc MSc - Leeds Teaching Hospitals NHS Trust, United Kingdom;
Bob Wheller, BSc MSc - Leeds Teaching Hospitals NHS Trust, United Kingdom;
Jack Baldwin, MPhys MSc PhD - Leeds Teaching Hospitals NHS Trust, United Kingdom;
James Cairns, MBBS FRCR - Leeds Teaching Hospitals NHS Trust, United Kingdom;
Simran Desi, MBBS Bsc PGCert Health Research FRCR - Leeds Teaching Hospitals NHS Trust, United Kingdom;
Mark Hall, MBChB FRCR DipMedEd - Greater Glasgow and Clyde, United Kingdom;
David Lowe, MBChB BMSc MSc MD FRCEM FHEA FFCI - Greater Glasgow and Clyde, United Kingdom; University of Glasgow, United Kingdom;
Haris Shuaib, MPhys MSc - Newton’s Tree, United Kingdom; King’s College London, United Kingdom;
Haris
Shuaib,
MPhys MSc - Newton's Tree
