利用大语言模型在生物医学文献中识别基于证据的助推
Identifying Evidence-Based Nudges in Biomedical Literature with Large Language Models
AI总结：
利用大语言模型在生物医学文献中识别基于证据的助推，通过多阶段流程实现高效提取和验证。
摘要：
我们提出了一种可扩展的、由人工智能驱动的系统，用于从非结构化生物医学文献中识别和提取基于证据的行为助推。助推是微妙的、非强制性的干预措施，影响行为而不限制选择，对健康结果如药物依从性有很强的影响。然而，从PubMed的800万篇文章中识别这些干预措施是一个瓶颈。我们的系统使用了一个新的多阶段流程：首先，混合过滤（关键词、TF-IDF、余弦相似度和一个“助推术语奖金”）将语料库减少到约81,000个候选者。其次，我们使用OpenScholar（量化LLaMA 3.1 8B）对论文进行分类，并在单次通过中提取结构化字段，如助推类型和目标行为，这已通过JSON模式验证。我们对四个配置在标记测试集（N=197）上进行了评估。最佳设置（标题/摘要/引言）实现了67.0%的F1分数和72.0%的召回率，适用于发现。一个使用自我一致性（7次随机通过）的高精度变体实现了100%的精度和12%的召回率，展示了在高信任使用案例中可调节的权衡。该系统正在集成到Agile Nudge+平台中，以将LLM生成的干预措施基于同行评审的证据。这项工作展示了可解释的、领域特定的检索流程，用于证据综合和个性化医疗。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
