Harnessing ChatGPT dialogues to address claustrophobia in MRI - A radiographers' education perspective
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".