Abstract
To investigate the applicability of ChatGPT, in answering conceptual and non-conceptual questions related to urodynamic quality control, including trace analysis and report interpretation. Utilizing a structured questioning approach, the study employs ChatGPT3.5 and ChatGPT4.0. Questions are mainly divided into conceptual questions and non-conceptual questions related to urodynamic quality control, and trace analysis. Evaluation criteria include alignment with the "Good Urodynamic Practice" guideline and literature. ChatGPT excels in delivering hierarchical responses to conceptual questions, providing comprehensive insights in a structured format. Challenges arise in offering specific references to published literature, with a 50% accuracy rate in 10 basic conceptual questions. For non-conceptual urodynamic quality control questions, ChatGPT achieves a 50% accuracy rate, accurately addressing various aspects. However, in both cases, we found no statistically significant difference in accuracy rate between conceptual questions and non-conceptual questions. However, challenges persist when questions are linked to recent literature, leading to misunderstandings and inaccurate responses. Regarding urodynamics trace interpretation, ChatGPT states its inability to directly analyze images, emphasizing reliance on qualified healthcare professionals for detailed clinical analysis. This study preliminarily demonstrates ChatGPT's limited performance in answering conceptual and non-conceptual questions related to urodynamic quality control, without finding significant differences between the two kinds of questions. Additionally, ChatGPT's capability to process image data for urodynamic trace analysis is non-existent. The study suggests that ChatGPT only has the potential to serve as an "electronic dictionary" to aid urodynamic operators, but it should be noted that this study cannot prove ChatGPT's ability to change the overall quality of urodynamic examinations.