发表机构
University of Kansas（堪萨斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RASPER提出一种奖励对齐的临床笔记摘要生成方法，通过强化学习优化下游预测任务，保留患者特定证据，在MIMIC-III和MIMIC-IV上提升再入院预测和药物推荐性能。
AI 中文摘要
电子健康记录（EHR）中的非结构化出院笔记通常携带与结构化医疗代码互补的信号，包含标准化队列级代码无法捕获的患者特定证据。然而，笔记中的这些证据常常埋藏在冗长、嘈杂的文本中，这些文本并非有意针对任何特定临床预测而撰写。摘要生成是一种明显的缓解方法，但通用摘要针对流畅性而非结局进行优化，常常遗漏决定性证据，同时保留看似合理但无信息量的细节。为此，我们提出RASPER，一种用于EHR预测的奖励对齐摘要生成器，它直接针对下游临床任务优化笔记摘要。RASPER采用可调基于LLM的摘要生成器从出院笔记中提取任务相关证据，并通过来自预测反馈的强化学习进行训练，使用从下游预测器损失导出的奖励。为使摘要生成器有据可依，一个纵向编码器将结构化代码转换为软提示，将每位患者的临床背景纳入笔记摘要。通过奖励所得多模态预测的质量，RASPER鼓励摘要生成器保留与结构化代码捕获信息互补而非重复的患者特定证据。RASPER在MIMIC-III和MIMIC-IV上的再入院预测和药物推荐任务中均持续优于强基线。
英文摘要
Unstructured discharge notes in Electronic Health Records (EHRs) often carry signal complementary to structured medical codes, holding patient-specific evidence that standardized cohort-level codes alone cannot capture. However, this evidence in notes is frequently buried in lengthy, noisy text that is not intentionally written with any specific clinical prediction in mind. Summarization is an obvious mitigation, but generic summaries, tuned for fluency rather than the outcome, routinely omit decisive evidence while retaining plausible but uninformative detail. To this end, we propose RASPER, a Reward-Aligned Summarizer for Prediction in EHR, that optimizes note summarization directly against the downstream clinical task. RASPER employs a tunable LLM-based summarizer to extract task-relevant evidence from discharge notes and trains it via reinforcement learning from prediction feedback, using a reward derived from the downstream predictor's loss. To ground the summarizer, a longitudinal encoder converts structured codes into soft prompts that incorporate each patient's clinical context into note summarization. By rewarding the quality of the resulting multimodal prediction, RASPER encourages the summarizer to retain patient-specific evidence that complements, rather than duplicates, information captured by structured codes. RASPER consistently outperforms strong baselines on both readmission prediction and medication recommendation across MIMIC-III and MIMIC-IV.
CommentsAccepted to EMNLP 2026 Main Conference
