AI-simulated clinical consultations: Assessing the potential of ChatGPT to support medical training

Arpita Saggar, Vania Dimitrova, Duygu Sarikaya, David Hogg, Jonathan C Darling · 2026

Read AI-simulated clinical consultations: Assessing the potential of ChatGPT to support medical training by Arpita Saggar, Vania Dimitrova, Duygu Sarikaya, David Hogg, Jonathan C Darling (2026) 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/PMC13311969.txt.

Description

Arpita Saggar and colleagues offer a 2026 study on whether ChatGPT can act out clinical exam scenarios for medical training. Real practice exams cost much time and money to stage.

Four child-health scenarios from mock exams were run with separate ChatGPT agents as patient, doctor, and examiner. The patient and doctor agents talked in writing, and the examiner agent marked the exchange. Clinicians and patients judged the dialogues. The patient agent stayed in character and showed feeling well; the doctor agent communicated clearly but slipped into jargon and repetition. The examiner agent's marks correlated well with human marks, and support for training use was moderate.

Catalog record

CREATORArpita Saggar, Vania Dimitrova, Duygu Sarikaya, David Hogg, Jonathan C Darling
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE28186
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13311969

Browse the full library · About the Tower of Babel