Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Legal Guidelines for Documentation01:06

Legal Guidelines for Documentation

2.6K
The legal guidelines for nursing documentation are essential for ensuring accurate, professional, and ethical recording of patient care. The guidelines are discussed here:
2.6K
Ethical Standards II01:23

Ethical Standards II

1.4K
Ethical standards are the backbone of nursing practice, guiding nurses as they interact with patients, families, and colleagues. These standards are crucial for providing safe, empathetic care centered on the patient's needs.
Nurses are entrusted with upholding various ethical principles and standards. Nurses forge solid therapeutic relationships using trust, empathy, autonomy, confidentiality, and professional competence.
Confidentiality is crucial, embodying respect for individual privacy...
1.4K
Guidelines and Strategies for Safe Computer Charting01:18

Guidelines and Strategies for Safe Computer Charting

3.3K
The guidelines and strategies provided by the American Nurses Association (ANA) and the Canadian Nurses Association (CNA) offer essential principles for ensuring safe and secure computer charting systems in healthcare settings. Let's break down each recommendation:
Maintain Confidentiality and Security:
3.3K
Ethical Standards I01:25

Ethical Standards I

1.7K
The American Nurses Association (ANA) created and implemented the first nationally accepted Code of Ethics for Nurses with Interpretive Statements. The Code of Ethics is a living document regularly updated by the ANA and establishes an ethical standard that is non-negotiable for nurses in all roles and settings.
The Code of Ethics provisions outline the nurse's duty to the patient, the healthcare team, the profession, and society. The Code's fundamental principles include advocacy,...
1.7K
Purpose of Health Records I01:11

Purpose of Health Records I

2.0K
The vital purpose of health records is to provide a complete and accurate account of a patient's medical history, including communication, diagnostic and therapeutic orders, care planning, research, and quality review.
Here's a breakdown of how health records serve these purposes:
2.0K
Documentation in Long-Term and Home Healthcare Setting01:29

Documentation in Long-Term and Home Healthcare Setting

1.7K
Documentation in long-term care facilities and home healthcare settings is crucial for ensuring continuous, coordinated, and comprehensive care for patients. Each setting has its specific documentation processes and tools:
Long-Term Care Facilities
1.7K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Using a Plasma Focused Ion Beam System to Characterise the Porosity Through the Oxide Scale Formed on a Martensitic 9Cr-1Mo Steel Exposed to CO<sub>2</sub>.

High temperature corrosion of materials·2026
Same author

A rapid evidence review of evaluation techniques for large language models in legal use cases: trends, gaps, and recommendations for future research.

AI & society·2026
Same author

Clinical Summaries of Social Media Timelines for Mental Health Monitoring: Human Versus Large Language Model Comparative Evaluation Study.

JMIR formative research·2026
Same author

Machine learning integration of serial blood biomarkers enhances cognitive decline prediction in early Parkinson's disease.

NPJ Parkinson's disease·2026
Same author

Biofilm growth is insufficient to retain large buoyant microplastics in constructed wetlands.

Journal of hazardous materials·2026
Same author

Visual content and thematic analyses of images shared on social media before and after episodes of self-harm in a UK clinical youth sample.

BMJ open·2026

Related Experiment Video

Updated: Apr 17, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

8.3K

Evaluating privacy leakages in LLM-driven ambient clinical documentation.

Jenny Chim1, Jonathan Pearson2, Dan Schofield2

  • 1School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom.

Frontiers in Digital Health
|April 16, 2026
PubMed
Summary

AI ambient scribing tools risk leaking sensitive third-party data in clinical notes. While privacy instructions help, they aren't fully effective, necessitating privacy-by-design approaches for safe AI deployment in healthcare.

Keywords:
ambient scribingclinical documentationevaluationlarge language modelsnatural language processingprivacy

More Related Videos

Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data
11:21

Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data

Published on: July 27, 2018

9.0K
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

16.7K

Related Experiment Videos

Last Updated: Apr 17, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

8.3K
Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data
11:21

Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data

Published on: July 27, 2018

9.0K
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

16.7K

Area of Science:

  • Artificial Intelligence
  • Healthcare Technology
  • Data Privacy

Background:

  • Automated documentation tools, including AI-enabled ambient scribing, are increasingly used in healthcare.
  • These tools transcribe patient-provider conversations and generate clinical notes using automatic speech recognition (ASR) and Large Language Models (LLMs).
  • Ensuring appropriate data recording and contextual privacy is crucial for safe deployment, presenting a challenge beyond standard PII leakage.

Purpose of the Study:

  • To operationalize and evaluate privacy leakage as the inappropriate inclusion of third-party personal information in LLM-generated clinical notes.
  • To construct a benchmark dataset for evaluating privacy in AI-generated clinical notes.
  • To assess the performance of various LLMs in generating privacy-preserving clinical notes.

Main Methods:

  • Developed a benchmark by enriching patient metadata and injecting third-party personal information into transcripts.
  • Evaluated open-weight (LLaMA, Mixtral) and proprietary (Claude) LLMs on note generation with varied privacy prompts.
  • Operationalized privacy leakage as the inappropriate inclusion of third-party data in clinical notes.

Main Results:

  • All evaluated LLMs leaked third-party information into generated clinical notes.
  • Privacy instructions reduced leakage but were neither complete nor robust.
  • Models sometimes generated privacy-infringing notes even when identifying inappropriate information; separate generation and privacy editing steps showed potential.
  • Contextual specificity in privacy definitions improved leakage reduction.

Conclusions:

  • No single mitigation strategy completely eliminated third-party data leakage.
  • Combining multiple mitigation approaches yielded the most significant reductions in privacy leakage.
  • Emphasizes the need for privacy-by-design principles in AI systems and robust evaluation strategies for emerging healthcare technologies.