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

• DOI: 10.1016/j.radi.2024.02.015
• Publication Date: 2024-02-29T10:59:19Z
• Authors: G.R. Bonfitto; A. Roletto; M. Savardi; S.V. Fasulo; D. Catania; A. Signoroni
• Keywords: Male; Patient Simulation; Phobic Disorders; Artificial Intelligence; Communication; ChatGPT; Claustrophobia; Generative AI; Magnetic resonance imaging; Simulation: radiographer; Humans; Female; Magnetic Resonance Imaging

IntroductionThe healthcare sector invests significantly in communication skills training, but not always with satisfactory results. Recently, generative Large Language Models, have shown promising results medical education. This study aims to use ChatGPT simulate radiographer-patient conversations about the critical moment of claustrophobia management during MRI, exploring how Artificial Intelligence can improve radiographers' skills.MethodsThis exploits specifically designed prompts on ChatGPT-3.5 and ChatGPT-4 generate simulated between virtual claustrophobic patients six radiographers varying levels work experience focusing their differences model size language generation capabilities. Success rates responses were analysed. The methods convincing undergo MRI despite also evaluated.ResultsA total 60 simulations conducted, achieving a success rate 96.7% (58/60). exhibited errors 40% (12/30) simulations, while showed no errors.In terms out 164 responses, 70.2% (115/164) categorized as "Supportive Instructions," followed by "Music Therapy" at 18.3% (30/164). Experts mainly used Instructions" (82.2%, 51/62) "Breathing Techniques" (9.7%, 6/62). Intermediate participants favoured (26%, 13/50), Beginner frequently utilized "Mild Sedation" (15.4%, 8/52).ConclusionThe simulation clinical scenarios via proves valuable assessing testing skills, especially managing MRI. pilot highlights potential preclinical recognizing different training needs professional experience.Implications for practiceThis is relevant radiography practice, where AI increasingly widespread, it explores new way radiographers.