Search research articles

Related Concept Videos

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Home
Artificial Intelligence-generated Responses To Frequently Asked Questions On Coccydynia: Evaluating The Accuracy And Consistency Of Gpt-4o's Performance.

Home
Artificial Intelligence-generated Responses To Frequently Asked Questions On Coccydynia: Evaluating The Accuracy And Consistency Of Gpt-4o's Performance.

Related Experiment Video

Author Spotlight: Fu's Subcutaneous Needling for Knee Osteoarthritis Pain

Author Spotlight: Fu's Subcutaneous Needling for Knee Osteoarthritis Pain

Published on: March 24, 2023

Artificial intelligence-generated responses to frequently asked questions on coccydynia: Evaluating the accuracy and

Aslinur Keles¹, Ozge Gulsum Illeez¹, Berkay Erbagci¹

¹Department of Physical Medicine and Rehabilitation, Health Science University, Fatih Sultan Mehmet Training and Research Hospital, İstanbul, Türkiye.

Archives of Rheumatology

|April 23, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Keywords:

Artificial intelligence ChatGPT-4o coccydynia coccyx pain large language models.

More Related Videos

Isokinetic Robotic Device to Improve Test-Retest and Inter-Rater Reliability for Stretch Reflex Measurements in Stroke Patients with Spasticity

Isokinetic Robotic Device to Improve Test-Retest and Inter-Rater Reliability for Stretch Reflex Measurements in Stroke Patients with Spasticity

Published on: June 12, 2019

Dynamic Quantitative Sensory Testing to Characterize Central Pain Processing

Dynamic Quantitative Sensory Testing to Characterize Central Pain Processing

Published on: February 16, 2017

Related Experiment Videos

Author Spotlight: Fu's Subcutaneous Needling for Knee Osteoarthritis Pain

Author Spotlight: Fu's Subcutaneous Needling for Knee Osteoarthritis Pain

Published on: March 24, 2023

Isokinetic Robotic Device to Improve Test-Retest and Inter-Rater Reliability for Stretch Reflex Measurements in Stroke Patients with Spasticity

Isokinetic Robotic Device to Improve Test-Retest and Inter-Rater Reliability for Stretch Reflex Measurements in Stroke Patients with Spasticity

Published on: June 12, 2019

Dynamic Quantitative Sensory Testing to Characterize Central Pain Processing

Dynamic Quantitative Sensory Testing to Characterize Central Pain Processing

Published on: February 16, 2017

GPT-4o provides mostly accurate coccydynia information but shows inconsistencies in repeated queries. While useful for patient education, it requires human oversight for specialized clinical knowledge.

Area of Science:

Artificial Intelligence in Medicine
Medical Informatics
Natural Language Processing

Background:

Patient-centered questions regarding coccydynia are common.
Assessing the accuracy and consistency of AI-generated medical information is crucial for patient safety and education.

Purpose of the Study:

To evaluate the accuracy and consistency of GPT-4o's responses to frequently asked questions about coccydynia.
To determine the reliability of AI chatbots for providing medical information to patients.

Main Methods:

Collected patient-centered coccydynia questions from various online sources.
Evaluated GPT-4o responses for accuracy and completeness by two physiatrists.
Assessed response consistency across multiple queries and reviewers using statistical analysis.

Main Results:

45.7% of GPT-4o responses were correct and comprehensive; 49.4% were correct but incomplete.
No responses were completely incorrect, but 75% differed between query rounds.
Interreviewer agreement was substantial (kappa=0.67).

Conclusions:

GPT-4o demonstrates potential for accurate coccydynia information dissemination.
Response variability highlights the need for human oversight in clinical applications.
AI chatbots can serve as a supplementary tool for patient education on coccydynia.