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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

25
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
25

You might also read

Related Articles

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

Sort by
Same author

Examining Public Awareness of Ageist Terms on Twitter: Content Analysis.

JMIR aging·2023
Same author

Explainable Artificial Intelligence for Predictive Modeling in Healthcare.

Journal of healthcare informatics research·2022
Same author

Topics and Sentiments of Public Concerns Regarding COVID-19 Vaccines: Social Media Trend Analysis.

Journal of medical Internet research·2021
Same author

The Exchange of Informational Support in Online Health Communities at the Onset of the COVID-19 Pandemic: Content Analysis.

JMIRx med·2021
Same author

Identifying Self-Management Support Needs for Pregnant Women With Opioid Misuse in Online Health Communities: Mixed Methods Analysis of Web Posts.

Journal of medical Internet research·2021
Same author

What Are People Concerned About During the Pandemic? Detecting Evolving Topics about COVID-19 from Twitter.

Journal of healthcare informatics research·2021

Related Experiment Video

Updated: May 9, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

461

Enhancing Patient-Physician Communication: Simulating African American Vernacular English in Medical Diagnostics with

Yeawon Lee1, Chia-Hsuan Chang2, Christopher C Yang1

  • 1Drexel University, Philadelphia, PA 19104 USA.

Journal of Healthcare Informatics Research
|May 1, 2025
PubMed
Summary

Large language models can replicate African American Vernacular English (AAVE) in simulated clinical settings. Prompting with demographic and linguistic cues improves AAVE replication but reveals model biases, necessitating further refinement for culturally sensitive healthcare communication.

Keywords:
Communication trainingHealth disparitiesLarge language modelPatient simulationPatient-physician communication gap

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

599

Related Experiment Videos

Last Updated: May 9, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

461
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

599

Area of Science:

  • Computational Linguistics
  • Artificial Intelligence in Healthcare
  • Health Disparities Research

Background:

  • Effective physician-patient communication is vital for reducing health disparities.
  • Linguistic variations, such as African American Vernacular English (AAVE), can create communication barriers.
  • These barriers negatively impact patient care and health outcomes.

Purpose of the Study:

  • To investigate the capability of large language models (LLMs), GPT-4 and Llama 3.3, to replicate AAVE.
  • To assess the potential of LLMs in enhancing cultural sensitivity in simulated clinical dialogues.
  • To evaluate the impact of different prompting strategies on AAVE replication.

Main Methods:

  • Four prompt types (BaseP, DemoP, LingP, CompP) were tested using simulated clinical case scenarios from the United States Medical Licensing Examination (USMLE).
  • Statistical analyses, including ANOVA, were performed on the LLM outputs to compare prompt effectiveness.
  • AAVE feature counts were analyzed to quantify the models' replication accuracy.

Main Results:

  • Prompt type significantly influenced AAVE replication in both GPT-4 and Llama 3.3.
  • The combined prompt (CompP), integrating demographic and linguistic cues, yielded the highest AAVE feature counts.
  • Both models exhibited biases, with demographic mentions alone triggering informal language, indicating potential stereotypes.

Conclusions:

  • LLMs show promise for developing culturally sensitive healthcare communication tools.
  • Prompt engineering significantly impacts AAVE replication, with combined cues being most effective.
  • Ongoing refinement is crucial to mitigate model biases and accurately represent linguistic diversity in healthcare AI.