用基础模型识别病历中关键异常事件，提升预后预测能力。
Quantifying surprise in clinical care: Detecting highly informative events in electronic health records with foundation models
- 基于患者全程住院数据，动态识别高信息量事件
- 标记事件可显著提升预后预测准确率，部分低信息事件可删减
- 助力解释基于基础模型的预后模型决策
我们提出一种基于基础模型的方法，用于识别电子健康记录中的高信息量词元和事件。该方法综合考虑患者整个住院期间的上下文数据，能够发现规则系统视为正常但实际具有重要临床意义的异常事件。实验表明，模型标记的事件对预测后续患者结局具有显著价值；同时，部分被识别为信息量低的事件可安全删除。此外，我们展示了信息量指标如何帮助解释基于基础模型表示训练的预后模型的预测结果。
原文摘要 · Abstract (English)
We present a foundation model-derived method to identify highly informative tokens and events in electronic health records. Our approach considers incoming data in the entire context of a patient's hospitalization and so can flag anomalous events that rule-based approaches would consider within a normal range. We demonstrate that the events our model flags are significant for predicting downstream patient outcomes and that a fraction of events identified as carrying little information can safely be dropped. Additionally, we show how informativeness can help interpret the predictions of prognostic models trained on foundation model-derived representations.
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。