UniSA Allied Health & Human Performance, University of South Australia, Adelaide, SA, Australia
Jones Radiology, Eastwood, SA, Australia.
J Educ Eval Health Prof. 2024;21:29. doi: 10.3352/jeehp.2024.21.29. Epub 2024 Oct 31.
This study investigated the performance of ChatGPT-4.0o in evaluating the quality of positioning in radiographic images. Thirty radiographs depicting a variety of knee, elbow, ankle, hand, pelvis, and shoulder projections were produced using anthropomorphic phantoms and uploaded to ChatGPT-4.0o. The model was prompted to provide a solution to identify any positioning errors with justification and offer improvements. A panel of radiographers assessed the solutions for radiographic quality based on established positioning criteria, with a grading scale of 1–5. In only 20% of projections, ChatGPT-4.0o correctly recognized all errors with justifications and offered correct suggestions for improvement. The most commonly occurring score was 3 (9 cases, 30%), wherein the model recognized at least 1 specific error and provided a correct improvement. The mean score was 2.9. Overall, low accuracy was demonstrated, with most projections receiving only partially correct solutions. The findings reinforce the importance of robust radiography education and clinical experience.
本研究旨在评估 ChatGPT-4.0o 在评估放射影像定位质量方面的性能。使用人体模型制作了 30 张膝关节、肘关节、踝关节、手部、骨盆和肩部投照的射线照片，并将其上传至 ChatGPT-4.0o。模型被提示提供一种解决方案，以识别任何定位错误，并提供改进建议。一组放射技师根据既定的定位标准，使用 1-5 的评分量表对放射质量的解决方案进行评估。在仅 20%的投影中，ChatGPT-4.0o 正确识别所有错误，并提供了正确的改进建议。最常见的分数是 3（9 例，30%），其中模型识别出至少 1 个特定错误，并提供了正确的改进建议。平均得分为 2.9。总体而言，准确性较低，大多数投影仅获得部分正确的解决方案。研究结果强调了强大的放射学教育和临床经验的重要性。
