用AI从海量医学文献中自动找出有效行为干预措施
Identifying Evidence-Based Nudges in Biomedical Literature with Large Language Models
- 构建多阶段流程：先筛选后用大模型分类提取关键信息
- 最高达72%召回率，高精度模式实现100%准确无误
- 适合医疗决策支持系统，提升干预方案的证据可信度
我们提出一种可扩展的智能系统，从非结构化生物医学文献中识别并提取基于证据的行为干预措施。这类干预措施通过微妙、非强制的方式影响行为而不限制选择，在提高药物依从性等健康结果方面表现显著。然而，从PubMed超过800万篇论文中识别这些内容存在瓶颈。本系统采用新型多阶段流程：首先通过关键词、TF-IDF、余弦相似度及‘干预术语奖励’进行混合过滤，将文档缩减至约8.1万候选；其次使用量化版OpenScholar（LLaMA 3.1 8B）单次处理完成论文分类与结构化字段提取（如干预类型、目标行为），并通过JSON模式验证。在197篇标注测试集上评估四种配置，最佳设置（标题/摘要/引言）获得67.0% F1和72.0%召回率，适用于发现新干预；高精度变体采用自洽机制（7次随机推理）达100%精确率，召回率为12%，适用于高可信场景。该系统已集成至Agile Nudge+平台，用于以同行评审证据为基础生成干预策略。本工作展示了可解释、领域特定的检索管道在证据整合与个性化医疗中的应用。
原文摘要 · Abstract (English)
We present a scalable, AI-powered system that identifies and extracts evidence-based behavioral nudges from unstructured biomedical literature. Nudges are subtle, non-coercive interventions that influence behavior without limiting choice, showing strong impact on health outcomes like medication adherence. However, identifying these interventions from PubMed's 8 million+ articles is a bottleneck. Our system uses a novel multi-stage pipeline: first, hybrid filtering (keywords, TF-IDF, cosine similarity, and a "nudge-term bonus") reduces the corpus to about 81,000 candidates. Second, we use OpenScholar (quantized LLaMA 3.1 8B) to classify papers and extract structured fields like nudge type and target behavior in a single pass, validated against a JSON schema. We evaluated four configurations on a labeled test set (N=197). The best setup (Title/Abstract/Intro) achieved a 67.0% F1 score and 72.0% recall, ideal for discovery. A high-precision variant using self-consistency (7 randomized passes) achieved 100% precision with 12% recall, demonstrating a tunable trade-off for high-trust use cases. This system is being integrated into Agile Nudge+, a real-world platform, to ground LLM-generated interventions in peer-reviewed evidence. This work demonstrates interpretable, domain-specific retrieval pipelines for evidence synthesis and personalized healthcare.
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。