School of Computer Science and Mathematics, Kingston University London, UK.
Nuffield Department of Primary Care Health Sciences, University of Oxford, UK.
Stud Health Technol Inform. 2024 Aug 22;316:746-750. doi: 10.3233/SHTI240521.
Computer-mediated clinical consultation, involving clinicians, electronic health record (EHR) systems, and patients, yield rich narrative data. Despite advancements in Natural Language Processing (NLP), these narratives remain underutilised. Free text recording in EHRs allows expressivity, complements structured data from clinical coding systems, and facilitates collaborative care. Large language models (LLMs) excel in understanding and generating natural language, enabling complex dialogue processing. Integrating LLM tools into consultations could harness the untapped potential of free text to identify patient safety concerns, support diagnosis and provide content to enhance clinical-patient interactions. Tailoring LLMs for specific consultation tasks through pre-training and fine-tuning is viable. This paper outlines approaches for adopting LLMs in primary care and suggests that using fine-tuned LLMs with prompt engineering could enhance computer-mediated clinical consultation cost-effectively.
计算机介导的临床咨询涉及临床医生、电子健康记录 (EHR) 系统和患者，产生丰富的叙述性数据。尽管自然语言处理 (NLP) 取得了进展，但这些叙述性数据仍未得到充分利用。EHR 中的自由文本记录允许表达性，补充来自临床编码系统的结构化数据，并促进协作式护理。大型语言模型 (LLM) 在理解和生成自然语言方面表现出色，能够处理复杂的对话。将 LLM 工具集成到咨询中可以利用自由文本的未开发潜力来识别患者安全问题，支持诊断并提供内容以增强医患互动。通过预训练和微调为特定的咨询任务定制 LLM 是可行的。本文概述了在初级保健中采用 LLM 的方法，并提出使用经过微调的 LLM 和提示工程可以有效地提高计算机介导的临床咨询的成本效益。
