Heilmeyer Felix, Böhringer Daniel, Reinhard Thomas, Arens Sebastian, Lyssenko Lisa, Haverkamp Christian
Institute of Digitalization in Medicine, Faculty of Medicine and Medical Center, University of Freiburg, Breisacher Straße 153, Freiburg im Breisgau, 79110, Germany, 49 27039392.
Eye Center, Faculty of Medicine and Medical Center, University of Freiburg, Freiburg im Breisgau, Germany.
JMIR Med Inform. 2024 Aug 28;12:e59617. doi: 10.2196/59617.
The use of large language models (LLMs) as writing assistance for medical professionals is a promising approach to reduce the time required for documentation, but there may be practical, ethical, and legal challenges in many jurisdictions complicating the use of the most powerful commercial LLM solutions.
In this study, we assessed the feasibility of using nonproprietary LLMs of the GPT variety as writing assistance for medical professionals in an on-premise setting with restricted compute resources, generating German medical text.
We trained four 7-billion-parameter models with 3 different architectures for our task and evaluated their performance using a powerful commercial LLM, namely Anthropic's Claude-v2, as a rater. Based on this, we selected the best-performing model and evaluated its practical usability with 2 independent human raters on real-world data.
In the automated evaluation with Claude-v2, BLOOM-CLP-German, a model trained from scratch on the German text, achieved the best results. In the manual evaluation by human experts, 95 (93.1%) of the 102 reports generated by that model were evaluated as usable as is or with only minor changes by both human raters.
The results show that even with restricted compute resources, it is possible to generate medical texts that are suitable for documentation in routine clinical practice. However, the target language should be considered in the model selection when processing non-English text.
使用大语言模型（LLMs）作为医学专业人员的写作辅助工具是一种有望减少文档撰写所需时间的方法，但在许多司法管辖区可能存在实际、伦理和法律挑战，使最强大的商业大语言模型解决方案的使用变得复杂。
在本研究中，我们评估了在计算资源受限的本地环境中，使用GPT系列的非专有大语言模型作为医学专业人员的写作辅助工具以生成德语医学文本的可行性。
我们针对我们的任务训练了四个具有3种不同架构的70亿参数模型，并使用一个强大的商业大语言模型，即Anthropic公司的Claude-v2作为评估者来评估它们的性能。基于此，我们选择了性能最佳的模型，并与2名独立的人类评估者一起在真实世界数据上评估其实际可用性。
在使用Claude-v2进行的自动评估中，从零开始在德语文本上训练的模型BLOOM-CLP-德语取得了最佳结果。在人类专家的人工评估中，该模型生成的102份报告中有95份（93.1%）被两名人类评估者评为原样可用或只需进行微小修改即可使用。
结果表明，即使计算资源受限，也有可能生成适用于常规临床实践文档记录的医学文本。然而，在处理非英语文本时，模型选择应考虑目标语言。
