Harnessing ChatGPT dialogues to address claustrophobia in MRI - A radiographers' education perspective

G R Bonfitto; A Roletto; M Savardi; S V Fasulo; D Catania; A Signoroni

doi:10.1016/j.radi.2024.02.015

Harnessing ChatGPT dialogues to address claustrophobia in MRI - A radiographers' education perspective

Radiography (Lond). 2024 Feb 29;30(3):737-744. doi: 10.1016/j.radi.2024.02.015. Online ahead of print.

Authors

G R Bonfitto¹, A Roletto², M Savardi³, S V Fasulo⁴, D Catania⁵, A Signoroni⁶

Affiliations

¹ Department of Information Engineering, University of Brescia, Via Branze 38, 25123 Brescia, Italy; IRCCS Ospedale San Raffaele, Via Olgettina 60, 20132 Milano, Italy. Electronic address: giuseppe.bonfitto@unibs.it.
² Department of Mechanical and Industrial Engineering, Università degli Studi di Brescia, Via Branze 38, 25123 Brescia, Italy; IRCCS Ospedale San Raffaele, Via Olgettina 60, 20132 Milano, Italy. Electronic address: andrea.roletto@unibs.it.
³ Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia, Viale Europa 11, 25121, Brescia, Italy. Electronic address: mattia.savardi@unibs.it.
⁴ IRCCS Ospedale San Raffaele, Via Olgettina 60, 20132 Milano, Italy. Electronic address: fasulo.simone@hsr.it.
⁵ IRCCS Ospedale San Raffaele, Via Olgettina 60, 20132 Milano, Italy. Electronic address: catania.diego@hsr.it.
⁶ Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia, Viale Europa 11, 25121, Brescia, Italy. Electronic address: alberto.signoroni@unibs.it.

PMID: 38428198
DOI: 10.1016/j.radi.2024.02.015

Abstract

Introduction: The healthcare sector invests significantly in communication skills training, but not always with satisfactory results. Recently, generative Large Language Models, have shown promising results in medical education. This study aims to use ChatGPT to simulate radiographer-patient conversations about the critical moment of claustrophobia management during MRI, exploring how Artificial Intelligence can improve radiographers' communication skills.

Methods: This study exploits specifically designed prompts on ChatGPT-3.5 and ChatGPT-4 to generate simulated conversations between virtual claustrophobic patients and six radiographers with varying levels of work experience focusing on their differences in model size and language generation capabilities. Success rates and responses were analysed. The methods of radiographers in convincing virtual patients to undergo MRI despite claustrophobia were also evaluated.

Results: A total of 60 simulations were conducted, achieving a success rate of 96.7% (58/60). ChatGPT-3.5 exhibited errors in 40% (12/30) of the simulations, while ChatGPT-4 showed no errors. In terms of radiographers' communication during the simulations, out of 164 responses, 70.2% (115/164) were categorized as "Supportive Instructions," followed by "Music Therapy" at 18.3% (30/164). Experts mainly used "Supportive Instructions" (82.2%, 51/62) and "Breathing Techniques" (9.7%, 6/62). Intermediate participants favoured "Music Therapy" (26%, 13/50), while Beginner participants frequently utilized "Mild Sedation" (15.4%, 8/52).

Conclusion: The simulation of clinical scenarios via ChatGPT proves valuable in assessing and testing radiographers' communication skills, especially in managing claustrophobic patients during MRI. This pilot study highlights the potential of ChatGPT in preclinical training, recognizing different training needs at different levels of professional experience.

Implications for practice: This study is relevant in radiography practice, where AI is increasingly widespread, as it explores a new way to improve the training of radiographers.

Keywords: ChatGPT; Claustrophobia; Generative AI; Magnetic resonance imaging; Simulation: radiographer.