Related Experiment Video
Updated: Jun 21, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Large Language Model-Based Responses to Patients' In-Basket Messages.
William R Small1, Batia Wiesenfeld2, Beatrix Brandfield-Harvey1
1NYU Grossman School of Medicine, New York, New York.
Generative artificial intelligence (GenAI) drafts for patient messages were rated as useful and more empathetic by primary care physicians (PCPs) than human responses. However, GenAI drafts had lower readability, posing a challenge for patients with limited health or English literacy.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Clinical Communication
Background:
- Virtual patient-physician communication has surged, impacting primary care physician (PCP) well-being.
- Generative artificial intelligence (GenAI) offers potential to alleviate health care professional (HCP) workload and enhance communication quality.
Purpose of the Study:
- To evaluate PCPs' perceptions of GenAI-drafted patient messages.
- To analyze linguistic features of GenAI drafts related to equity and empathy.
- To compare GenAI drafts with human-generated responses in primary care settings.
Main Methods:
- A cross-sectional quality improvement study at NYU Langone Health.
- PCPs rated GenAI drafts and HCP-generated responses on information content, communication quality, and usability.
- Computational linguistics assessed differences in empathy, personalization, and professionalism.
Main Results:
- GenAI drafts received favorable ratings, comparable to HCP responses in information content and usability.
- GenAI responses were rated higher for communication style and perceived empathy.
- GenAI drafts exhibited more subjective and positive language but lower readability compared to HCP responses.
Conclusions:
- GenAI chatbots show promise in improving patient-HCP communication by conveying information effectively and empathetically.
- Readability of GenAI drafts is a concern, potentially limiting accessibility for patients with low health or English literacy.
- Further research is needed to optimize GenAI for equitable and accessible clinical communication.
More Related Videos
Related Concept Videos
Barriers to Effective Communication II
Cultural barriers:
Differences in values, beliefs, religion, knowledge, and tradition can significantly impact communication. Awareness of nonverbal cues is critical, especially when conversing with a patient from a different culture. What appears appropriate in one culture may be inappropriate in another.
Semantic barriers:
As a result of their tendency to use...
Methods of Documentation VI: Case Management Model
For example, a patient with a chronic...
Types of Reports III: Telephone and Verbal Reports
Here's an overview of each type:
Telephone Orders
SBAR II: Application of SBAR
SBAR Report from a Nurse to a Health Care Provider
S: "Hello, Dr. Smith. This is Jane, RN, from the Med Surg unit. I am calling to tell you about Ms. White in Room 210, who is experiencing increased pain and redness at her incision site. Her recent...
Modeling in Therapy
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
Models of Health Promotion and Illness Prevention I
The health belief model (HBM) attempts to predict health-related behavior in specific belief patterns. According to the HBM, a person's...

