Mapping Documentation Burden: Analyzing Centrality and Clusters among Flowsheet Measures and Templates Through Network Analysis

2025 Annual Symposium On Demand

Presentation Time: 03:30 PM - 03:42 PM

Abstract Keywords: Documentation Burden, Information Visualization, Nursing Informatics, Workflow, Quantitative Methods
Primary Track: Applications
Programmatic Theme: Clinical Informatics

This study applied network analysis (NA) to identify documentation burden in nursing flowsheets, quantifying and visualizing the interconnectedness of nursing flowsheet templates and measures. By analyzing centrality metrics and edge weights, we highlighted an outdated flowsheet structure and the need for a modern data structure. Using centrality metrics, we identified key templates and measures contributing to documentation burden, including highly repetitive nodes, central hubs, and intermediary nodes that facilitated communication in the network. Our findings showed that certain templates and measures exhibited consistently high centralities across multiple metrics, indicating opportunities for streamlining documentation structures. We also analyzed the communities in both networks to reveal the functional clusters of template and measure documentation. These insights provided a data-driven approach to understand documentation burden and inform opportunities to optimize documentation structures, particularly with increasing ambient technology integrations.

Speaker:
Pinyue Wang, Bachelor of Business Administration
Columbia University Department of Biomedical Informatics

Authors:
Pinyue Wang, Bachelor of Business Administration - Columbia University Department of Biomedical Informatics; Amy Finnegan, PhD - Duke Global Health Institute; Po-Yin Yen, PhD, RN - Washington University in St. Louis; Sarah Rossetti, RN, PhD - Columbia University Department of Biomedical Informatics;

---

A Comprehensive Approach for Assessing the Impact of Ambient Documentation

2025 Annual Symposium On Demand

Presentation Time: 03:42 PM - 03:54 PM

Abstract Keywords: Documentation Burden, Artificial Intelligence, Clinical Decision Support
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Workforce challenges are a significant issue facing many healthcare organizations. One variable contributing to this market dynamic is provider burnout, which remains high and is largely driven by administrative demands that continue to increase. Healthcare organizations are rapidly adopting enabling digital capabilities, such as generative artificial intelligence (AI) technologies, that have the potential to decrease administrative burden. One such tool is ambient documentation, which aims to make clinical documentation workflows smarter and more efficient. In September 2024, ambient documentation became the first broad clinical use of generative AI at Geisinger, when the technology was deployed to 100 ambulatory providers. This paper outlines Geisinger’s evaluation and implementation approach to ambient documentation and the impact the technology has made on administrative burden, provider burnout, and patient experience.

Speaker:
Cory Siegrist, M.B.A.
Geisinger

Authors:
Benjamin Hohmuth, MD, MPH - Geisinger Health; David Vawdrey, PhD - Geisinger; Seneca Harberger, MD - Geisinger; Spencer Tavares, DO - Geisinger Medical Center; Cory Siegrist, MBA - Geisinger Health System; Rebecca Stametz, DEd, MPH - Geisinger; Kimberly Obert, BS - Geisinger;

---

In pursuit of the alert fatigue: an assessment of drug alert burden at a large academic medical center

2025 Annual Symposium On Demand

Presentation Time: 03:54 PM - 04:06 PM

Abstract Keywords: Clinical Decision Support, Documentation Burden, Workflow
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Introduction: Despite extensive literature on alert fatigue, gaps remain in understanding its impact. We examined drug alert volume and override rates across provider roles to inform future research.
Methods: We retrospectively analyzed drug allergy alerts (DAA) and drug-drug interaction (DDI) alerts in 2023 at a large academic medical center. Alert volume and override rates were compared across providers with prescribing authority.
Results: Among 1,799 providers, 196,225 alerts were generated with an average of 0.42 alerts per clinician day. Advanced practice providers (APPs) received significantly more alerts per day than residents or attending physicians. Most providers (88%) saw fewer than one alert daily. Override rates increased with higher alert burden (98.6% for >5 alerts/day vs. 94.5% for 1–5 and 92.6% for <1; p<0.001).
Conclusion: Alert fatigue may not be observed in all cases when analyzed at the provider level. Future research should explore other alert characteristics, measurements, and provider’s perceptions.

Speaker:
Jakir Hossain Bhuiyan Masud, PhD
University of Alabama at Birmingham

Authors:
James Cimino, MD, FACMI, FACP, FAMIA, FIAHSI - Department of Biomedical Informatics and Data Science, Heersink School of Medicine, University of Alabama at Birmingham; Tiago Colicchio, PhD., MBA - University of Alabama at Birmingham;

---

Evaluating the Quality and Safety of Clinical Notes Generated by Ambient Digital Scribe Platforms using Simulated Ambulatory Encounters

2025 Annual Symposium On Demand

Presentation Time: 04:06 PM - 04:18 PM

Abstract Keywords: Documentation Burden, Large Language Models (LLMs), Evaluation, Healthcare Quality, Patient Safety, Standards, Artificial Intelligence
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Ambient digital scribe (ADS) platforms have become increasingly utilized for clinical documentation in the ambulatory setting despite little data regarding their performance. We assessed the accuracy, quality, and safety of output generated by five ADS platforms using simulated ambulatory encounters. Significant performance variability was observed across platforms and cases, indicating a need for standardized evaluation to facilitate consumer decision-making.

Speaker:
Taylor Anderson, MD
Stanford Healthcare

Authors:
Vishnu Mohan, MD, MBI, FACP, FAMIA - Oregon Health & Science University; David Dorr, MD, MS, FACMI, FAMIA, FIAHSI - Oregon Health & Science University; Jeffrey Gold, MD - Oregon Heatlh & Science University;

---

A Linguistic Analysis of Clinical Notes Created with and without Ambient Listening Technology

2025 Annual Symposium On Demand

Presentation Time: 04:18 PM - 04:30 PM

Abstract Keywords: Natural Language Processing, Documentation Burden, Healthcare Quality, Artificial Intelligence
Primary Track: Applications

Ambient listening technology is being adopted to reduce clinician burnout and documentation burden. We examine notes created with and without ambient technology at multiple levels of linguistic analysis including lexical, syntactic, semantic, and pragmatic to explore how ambient documentation differs from traditional note creation methods. Ambient notes are longer with more diverse vocabularies, may include more uncertainty and less stigmatizing language, and may capture more of the patient's perspective compared to nonambient notes.

Speaker:
Suzanne Blackley, MA
Mass General Brigham

Authors:
Yiming Li, PhD - Harvard Medical School/Brigham and Women's Hospital; John Lian, BS - Brigham and Women's Hospital; Jacqueline You, MD - Mass General Brigham; Amanda Centi, PhD - Mass General Brigham; Rebecca Mishuris, MD, MS, MPH - Mass General Brigham; Li Zhou, MD, PhD, FACMI, FIAHSI, FAMIA - Brigham and Women's Hospital, Harvard Medical School;

---

Towards Automated Evaluation of Clinical Documentation Summarization Quality

2025 Annual Symposium On Demand

Presentation Time: 04:30 PM - 04:42 PM

Abstract Keywords: Evaluation, Large Language Models (LLMs), Natural Language Processing
Primary Track: Foundations
Programmatic Theme: Clinical Informatics

Large language models (LLMs) hold promise for streamlining clinical summarization, yet ensuring quality is critical. In this study, we explore the utility of existing automated metrics towards capturing different quality criteria including and beyond faithfulness and propose distilled evaluation metrics. We focus on the task of automated summarization of a hospital admission, specifically drafting the Brief Hospital Course section of a discharge summary.

Speaker:
James Baker, BA
Columbia University

Authors:
Chao Pang - Columbia University; Yu-Hsiang Lo, MD - NewYork-Presbyterian/Columbia University Irving Medical Center; Jason Zucker, MD - NewYork-Presbyterian / Columbia University Irving Medical Center; Karthik Natarajan, PhD - Columbia University Dept of Biomedical Informatics; Noémie Elhadad, PhD - Columbia University;

---