Related Experiment Video
Updated: Jun 26, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Improving Readability and Automating Content Analysis of Plastic Surgery Webpages With ChatGPT
James E Fanning1, Maria J Escobar-Domingo1, Jose Foppiani1
1Division of Plastic and Reconstructive Surgery, Department of Surgery, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts.
This study shows that ChatGPT can improve online plastic surgery information readability. While ChatGPT 3.5 had high omission rates and ChatGPT 4.0 had high hallucination rates, iterative prompt design is key for optimizing AI in medical content analysis.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Plastic Surgery Content Analysis
Background:
- Online health information quality and readability are often suboptimal, impacting patient understanding.
- Manual evaluation of medical content is inefficient and prone to errors.
- This study explores automating content analysis and improving readability of plastic surgery webpages using ChatGPT.
Purpose of the Study:
- To automate content analysis of plastic surgery webpages using ChatGPT.
- To improve the readability of online plastic surgery information.
- To evaluate the performance of ChatGPT 3.5 and 4.0 in these tasks.
Main Methods:
- Screened Google search results for "breast implant size factors" and "breast implant size decision".
- Utilized ChatGPT 3.5 and 4.0 with general and specific prompts to analyze and rewrite webpage content.
- Classified ChatGPT content analysis outputs (hallucination, accuracy, omission) against human benchmarks and compared readability scores.
Main Results:
- Significant readability improvements were achieved with ChatGPT 3.5 using specific prompts (P ≤ 0.05).
- ChatGPT 4.0 did not yield further readability improvements.
- ChatGPT 4.0 showed increased accuracy and decreased omission rates compared to ChatGPT 3.5, but had higher hallucination rates.
Conclusions:
- ChatGPT presents an innovative method for enhancing online medical information quality in plastic surgery.
- Automation of content analysis is constrained by ChatGPT 3.5's omissions and ChatGPT 4.0's hallucinations.
- Iterative prompt engineering is crucial for optimizing ChatGPT performance in medical research and content generation.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
04:19A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
Published on: May 10, 2022
Related Concept Videos
Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
Guidelines and Strategies for Safe Computer Charting
Maintain Confidentiality and Security:
Health Information Technology and Healthcare Information System
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include: