Related Experiment Video
Updated: Sep 12, 2025

Author Spotlight: Enhancing Success of Ultrasound-Guided Neuraxial Anesthesia in Cases with Difficult Anatomy
Published on: January 31, 2025
A Patient-Focused Comparative Analysis of Large Language Models for Epidural Analgesia Education
Akshar P Patel1, Stanley Joseph1, Ashna Bhardwaj1
1From the Medical College of Georgia, Augusta University, Augusta, Georgia.
This study compared two AI chatbots for patient education on epidural analgesia. MediSearch offered more reliable information, while ChatGPT provided easier-to-understand explanations, revealing a trade-off between accuracy and readability.
Area of Science:
- Medical Education
- Artificial Intelligence in Healthcare
- Obstetrics
Background:
- Patient education on epidural analgesia is crucial for informed consent and managing expectations.
- Current educational methods may not adequately address patient concerns regarding risks and benefits.
- Large language models (LLMs) present a potential avenue for improving patient information delivery.
Purpose of the Study:
- To evaluate the effectiveness of two LLMs, ChatGPT and MediSearch, in educating patients about epidural analgesia.
- To compare the reliability and readability of responses generated by these AI tools.
Main Methods:
- 100 patient-focused questions regarding epidural analgesia were formulated using the Rothwell System.
- Responses from ChatGPT and MediSearch were assessed using DISCERN reliability scores.
- Readability was measured using Flesch-Kincaid Grade Level and Coleman-Liau Index.
Main Results:
- MediSearch demonstrated significantly higher reliability scores compared to ChatGPT (P < .0001).
- ChatGPT achieved superior readability, indicated by lower Flesch-Kincaid Grade Level and Coleman-Liau Index scores (P =.0013).
- An imbalance was observed between the reliability and readability of the two LLMs.
Conclusions:
- While both LLMs show potential for patient education, neither optimally balances reliability and readability for epidural analgesia information.
- Healthcare providers should be aware of these differing strengths when considering AI tools for patient education.
- Further development is needed to enhance AI-generated medical information for both accuracy and accessibility.
Related Concept Videos
Local Anesthetics: Clinical Application as Epidural Anesthesia
Since epidural anesthetics can be infused through an epidural catheter, all types of drugs, including short-acting ones, can be administered. Chloroprocaine and lidocaine are examples of short and long-duration anesthetics, respectively. Bupivacaine...
Local Anesthetics: Clinical Application as Spinal Anesthesia
Analgesia and Pain Management
Local Anesthetics: Clinical Application as Intravenous Regional Anesthesia
One of the advantages of...
Local Anesthetics: Differential Sensitivity of Nerve Fibers
Local Anesthetics: Clinical Application as Surface, Infiltration, and Conduction Block Anesthesia

