Gulati Vaibhav, Roy Shambo Guha, Moawad Ahmed, Garcia Daniela, Babu Aparna, Poot Jeffrey D, Teytelboym Oleg M
Department of Radiology, Mercy Catholic Medical Center, Darby, Pennsylvania.
Department of Radiology, Mercy Catholic Medical Center, Darby, Pennsylvania; Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts.
J Am Coll Radiol. 2024 Dec;21(12):1888-1895. doi: 10.1016/j.jacr.2024.05.009. Epub 2024 Jun 14.
To explore the capabilities of Chat Generative Pre-trained Transformer (ChatGPT) for the purpose of simplifying and translating radiology reports into Spanish, Hindi, and Russian languages, with comparisons to its performance in simplifying to the English language.
Fifty deidentified abdomen-pelvis CT reports were fed to ChatGPT (4.0), instructing it to simplify and translate the report. The processed reports were rated on factual correctness (category 1), potential harmful errors (category 2), completeness (category 3), and explanation of medical terms (category 4). The translated versions were also rated on the quality of translation (category 5). The scores in each category were compared between the translated versions and each translated version was compared with the English version in the first four categories. The original reports and the simplified English reports were rated on the Flesch Reading Ease Score and the Flesch Kincaid Grade Level.
The Spanish translation outperformed the Hindi and Russian version significantly in categories 1 and 3 (P < .05). All translated versions performed significantly worse compared with the English version in category 4 (P < .001). Notably, the Hindi translated version performed significantly worse in all four categories (P < .05). The Russian translated version was also significantly worse in category 3 (P < .05). In the first three categories, the Spanish translation, and in the first two categories, the Russian translation demonstrated no statistically significant difference from the English version. No statistically significant difference was observed in the Flesch Reading Ease Score and Flesch Kincaid Grade Level of the simplified English reports. Typographical errors in the original reports negatively affected the translation.
ChatGPT demonstrates potential ability in translating reports and communicating pertinent clinical information with limited errors. More training and tailoring are required for languages that are not as commonly used in medical literature. Large language models can be used for translating and simplifying radiology reports, potentially improving access to health care and helping reduce health care costs.
探讨聊天生成预训练变换器（ChatGPT）将放射学报告简化并翻译成西班牙语、印地语和俄语的能力，并将其在简化为英语方面的表现与之进行比较。
将50份去识别化的腹部-骨盆CT报告输入ChatGPT（4.0），指示其简化并翻译报告。对处理后的报告在事实准确性（类别1）、潜在有害错误（类别2）、完整性（类别3）和医学术语解释（类别4）方面进行评分。翻译版本还在翻译质量（类别5）方面进行评分。比较各翻译版本在每个类别的得分，并将每个翻译版本在前四个类别中与英语版本进行比较。根据弗莱什易读性分数和弗莱什金凯德年级水平对原始报告和简化后的英语报告进行评分。
西班牙语翻译在类别1和类别3中显著优于印地语和俄语版本（P < 0.05）。在类别4中，所有翻译版本与英语版本相比表现明显更差（P < 0.001）。值得注意的是，印地语翻译版本在所有四个类别中表现明显更差（P < 0.05）。俄语翻译版本在类别3中也明显更差（P < 0.05）。在前三个类别中，西班牙语翻译，在前两个类别中，俄语翻译与英语版本相比无统计学显著差异。简化后的英语报告在弗莱什易读性分数和弗莱什金凯德年级水平上未观察到统计学显著差异。原始报告中的排版错误对翻译有负面影响。
ChatGPT在翻译报告和以有限错误传达相关临床信息方面显示出潜在能力。对于医学文献中不常用的语言，需要更多的训练和调整。大语言模型可用于翻译和简化放射学报告，有可能改善医疗保健的可及性并有助于降低医疗保健成本。
