用医院数据微调的大模型，能更准预测疾病和风险。
Large Language Models for Medical Forecasting -- Foresight 2
- 用MIMIC-III文本构建患者时间线，再微调模型理解临床记录。
- 预测新疾病时准确率提升至P/R 0.69/0.62，优于此前最优。
- 小模型在专有数据上胜过大模型，适合医疗风险预测场景。
Foresight 2（FS2）是一种在医院数据上微调的大语言模型，用于建模患者时间线（GitHub 'removed for anon'）。它能理解患者的临床笔记，并预测多种生物医学任务中的SNOMED编码，包括诊断建议、风险预测以及治疗和用药推荐。FS2首先在MIMIC-III数据集的自由文本部分进行训练，通过提取生物医学概念并构建上下文相关的患者时间线，随后在此基础上进行微调。结果表明，在预测下一个新生物医学概念的任务中，其性能显著优于先前最先进方法（精确率/召回率：0.73/0.66 vs 0.52/0.32），在预测下一个新疾病任务中也取得类似提升（0.69/0.62 vs 0.46/0.25）。此外，在风险预测任务中，与GPT-4-turbo及多个开源生物医学LLM对比，FS2表现更优（P@5: 0.90 vs 0.65）。这表明将医院数据融入大模型的重要性，并显示在高质量专业数据上微调的小模型可超越更大模型。
原文摘要 · Abstract (English)
Foresight 2 (FS2) is a large language model fine-tuned on hospital data for modelling patient timelines (GitHub 'removed for anon'). It can understand patients' clinical notes and predict SNOMED codes for a wide range of biomedical use cases, including diagnosis suggestions, risk forecasting, and procedure and medication recommendations. FS2 is trained on the free text portion of the MIMIC-III dataset, firstly through extracting biomedical concepts and then creating contextualised patient timelines, upon which the model is then fine-tuned. The results show significant improvement over the previous state-of-the-art for the next new biomedical concept prediction (P/R - 0.73/0.66 vs 0.52/0.32) and a similar improvement specifically for the next new disorder prediction (P/R - 0.69/0.62 vs 0.46/0.25). Finally, on the task of risk forecast, we compare our model to GPT-4-turbo (and a range of open-source biomedical LLMs) and show that FS2 performs significantly better on such tasks (P@5 - 0.90 vs 0.65). This highlights the need to incorporate hospital data into LLMs and shows that small models outperform much larger ones when fine-tuned on high-quality, specialised data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。