用多智能体系统从零散病历中提取肿瘤信息，提升结构化数据生成效率与准确性。
From Analytics to Tumor Boards: An Evidence-Linked Multi-Agent Workflow for Oncology Feature Extraction
- 构建可配置的多智能体工作流，分离规则定义与模型执行，实现分步精准提取。
- 在40例患者1126个字段上，准确率82.6%，召回率87.5%，F1达85.0%。
- 适合临床研究与癌症注册系统，显著降低人工标注负担（原需27.2分钟/例）。
临床相关的肿瘤学信息分散在异构、纵向的病历文档中，导致信息提取负担重，且需精确追溯样本、肿瘤、生物标志物及时间点。人工癌注册抽象平均耗时27.2分钟/例，亟需可扩展的方法，在保留临床上下文的同时将非结构化文档转化为结构化数据。本文评估了可配置的尼姆布林德多智能体系统（nMAS），该系统从碎片化肿瘤学文档中提取328项临床相关属性，涵盖报告元数据、诊断、分期及癌症类型特异性信息。nMAS将临床医生定义的字段规范与模型执行解耦，结合复杂度感知提取、报告级整合与源文件验证机制。回顾性评估包含40名患者的230份去标识化文档及418对经医生审核的文档-字段对，共1126个非空参考值。评估聚焦于临床医生确认存在的字段，而非全量标注全部328项。nMAS实现值级别加权精度82.6%、召回率87.5%、F1为85.0%，优于独立实现的UMA风格MiniMax M2.5对比方法（F1 66.4%）。结果表明，基于源文件锚定的可配置提取工作流可有效将碎片化肿瘤文档转化为可复用的结构化数据。
原文摘要 · Abstract (English)
Clinically relevant oncology information is distributed across heterogeneous, longitudinal documentation, creating substantial abstraction burden and requiring accurate attribution across specimens, tumors, biomarkers, and time points, while manual cancer-registry abstraction can require 27.2 minutes per case, highlighting the need for scalable methods that preserve clinical context while converting documentation into structured data. We evaluate the Nimblemind Multi-Agent System (nMAS), a configurable oncology information-extraction workflow which extracts clinically relevant structured fields from fragmented oncology documentation. The extraction task uses a clinician-informed schema of 328 attributes spanning report metadata, diagnosis, staging, and cancer-type-specific information. nMAS separates clinician-defined field specifications from model execution and combines complexity-aware extraction, report-level consolidation, and source-grounded validation. The retrospective evaluation included 230 de-identified oncology documents from 40 patients and 418 clinician-reviewed document-field pairs containing 1,126 non-empty reference values. Evaluation focused on fields identified by clinicians as present in the source documents rather than exhaustively annotating all 328 schema fields. nMAS achieved a rank-weighted value-level precision of 82.6%, recall of 87.5%, and F1 of 85.0%, compared with an F1 of 66.4% for an independently implemented UMA-style MiniMax M2.5 comparator. These findings support the feasibility of using a configurable, source-grounded extraction workflow to convert fragmented oncology documentation into reusable structured 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。