The performance of AI in medical examinations: an exploration of ChatGPT in ultrasound medical education

Dao-Rong Hong, Chun-Yan Huang · 2024

Read The performance of AI in medical examinations: an exploration of ChatGPT in ultrasound medical education by Dao-Rong Hong, Chun-Yan Huang (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11573551.txt.

Description

Dao-Rong Hong and Chun-Yan Huang test how well two versions of ChatGPT answer a Chinese licensing style exam in ultrasound medicine, in a study from 2024. Teachers are asking whether such chatbots can support training in image heavy specialties. A national qualification exam offers a hard, standardized yardstick.

One hundred bank questions were used, seventy single answer and thirty multiple answer, spanning basic, clinical, and professional topics. The older model scored about thirty six percent on single answer items and thirty percent on the rest. The newer model jumped to about sixty one and fifty percent. Both did best on basic knowledge and worst on professional practice questions. The authors weigh what that gap means for using chatbots as study aids.

Catalog record

CREATORDao-Rong Hong, Chun-Yan Huang
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE13 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11573551

Browse the full library · About the Tower of Babel