This study aims to leverage state of the art language models to automate
generating the "Brief Hospital Course" and "Discharge Instructions" sections of
Discharge Summaries from the MIMIC-IV dataset, reducing clinicians'
administrative workload. We investigate how automation can improve
documentation accuracy, alleviate clinician burnout, and enhance operational
efficacy in healthcare facilities. This research was conducted within our
participation in the Shared Task Discharge Me! at BioNLP @ ACL 2024. Various
strategies were employed, including few-shot learning, instruction tuning, and
Dynamic Expert Selection (DES), to develop models capable of generating the
required text sections. Notably, utilizing an additional clinical
domain-specific dataset demonstrated substantial potential to enhance clinical
language processing. The DES method, which optimizes the selection of text
outputs from multiple predictions, proved to be especially effective. It
achieved the highest overall score of 0.332 in the competition, surpassing
single-model outputs. This finding suggests that advanced deep learning methods
in combination with DES can effectively automate parts of electronic health
record documentation. These advancements could enhance patient care by freeing
clinician time for patient interactions. The integration of text selection
strategies represents a promising avenue for further research.

本研究旨在利用最先进的语言模型对 MIMIC-IV 数据集中的 “病历简况” 和 “出院指示” 部分进行自动生成，以减轻临床医生的行政工作负担。我们研究了自动化如何提高文档准确性、缓解临床医生过劳并提升医疗机构的运营效率。在本次 BioNLP @ ACL 2024 的共享任务 Discharge Me! 中，我们采用了各种策略，包括少样本学习、指令调优和动态专家选择 (DES)，以开发能够生成所需文本部分的模型。值得注意的是，利用额外的临床领域特定数据集展示了提升临床语言处理的巨大潜力。DES 方法通过优化从多个预测中选择文本输出的方式，证明其特别有效。在比赛中，DES 方法获得了最高的综合得分为 0.332，超过了单一模型的输出。这一发现表明，先进的深度学习方法与 DES 结合，可以有效地自动化电子病历的部分文档化。这些进展有望通过释放临床医生的时间用于病人互动，提升患者护理水平。文本选择策略的整合代表了进一步研究的有希望途径。

WisPerMed 在 “出院我！” 中通过大型语言模型、动态专家选择和引导技术在 MIMIC-IV 中推进医疗文本生成

WisPerMed at "Discharge Me!": Advancing Text Generation in Healthcare  with Large Language Models, Dynamic Expert Selection, and Priming Techniques  on MIMIC-IV

Clinical language processing has received a lot of attention in recent years,
resulting in new models or methods for disease phenotyping, mortality
prediction, and other tasks. Unfortunately, many of these approaches are tested
under different experimental settings (e.g., data sources, training and testing
splits, metrics, evaluation criteria, etc.) making it difficult to compare
approaches and determine state-of-the-art. To address these issues and
facilitate reproducibility and comparison, we present the Clinical Language
Understanding Evaluation (CLUE) benchmark with a set of four clinical language
understanding tasks, standard training, development, validation and testing
sets derived from MIMIC data, as well as a software toolkit. It is our hope
that these data will enable direct comparison between approaches, improve
reproducibility, and reduce the barrier-to-entry for developing novel models or
methods for these clinical language understanding tasks.

本文介绍了 Clinical Language Understanding Evaluation (CLUE) 基准测试，它通过提供一组基于 MIMIC 数据的四个临床语言理解任务、标准的训练、开发、验证和测试集，以及一个软件工具包去解决临床语言处理面临的实验设置不一等问题，能够直接比较不同方法之间的性能差异，提高可重复性，并降低开发新模型或方法的门槛。