Journal of Nuclear Medicine · 2023 · 55 citations · 4 references
MedicineOncologyRadiologyClinical Decision SupportDiagnostic ReasoningOncologic Nuclear MedicineCancer Diagnosis EducationCancer Treatment PlanningDiagnostic CommunicationDiscussing Treatment OptionsMedical Technology AssessmentOncologic Imaging ProtocolsDiagnostic OncologyFollow-up QuestionsHodgkin Lymphoma ImagingLung Cancer StagingPatient Interview QuestionsPatient-oriented Clinical QuestionsTreatment Decision-making CommunicationTreatment Staging
We evaluated whether the artificial intelligence chatbot ChatGPT can adequately answer patient questions related to [<sup>18</sup>F]FDG PET/CT in common clinical indications before and after scanning. <b>Methods:</b> Thirteen questions regarding [<sup>18</sup>F]FDG PET/CT were submitted to ChatGPT. ChatGPT was also asked to explain 6 PET/CT reports (lung cancer, Hodgkin lymphoma) and answer 6 follow-up questions (e.g., on tumor stage or recommended treatment). To be rated “useful” or “appropriate,” a response had to be adequate by the standards of the nuclear medicine staff. Inconsistency was assessed by regenerating responses. <b>Results:</b> Responses were rated “appropriate” for 92% of 25 tasks and “useful” for 96%. Considerable inconsistencies were found between regenerated responses for 16% of tasks. Responses to 83% of sensitive questions (e.g., staging/treatment options) were rated “empathetic.” <b>Conclusion:</b> ChatGPT might adequately substitute for advice given to patients by nuclear medicine staff in the investigated settings. Improving the consistency of ChatGPT would further increase reliability.
4