AI系统自动筛选乳腺癌临床试验资格，准确率超98%。
AI-assisted workflow enables rapid, high-fidelity breast cancer clinical trial eligibility prescreening
- 用大模型+知识库实现从病历文本自动判断患者是否符合试验条件。
- 在近9万份病历中自动处理61.9%，准确率达98.6%。
- 帮医生节省筛查时间，人均成本仅0.96美元，适合医院临床团队使用。
临床试验在癌症诊疗与研究中至关重要，但参与率长期偏低。我们开发了MSK-MATCH（纪念斯隆-凯特琳多智能体试验协调枢纽），一个基于大语言模型与精炼肿瘤学试验知识库的AI系统，通过检索增强架构对所有预测提供基于原文的解释。在包含731名患者、6项乳腺癌试验、共计88,518份临床文档的回顾性数据集中，该系统自动解决了61.9%的案例，并将38.1%的案例转交人工复核。该AI辅助流程在患者级资格判定上实现了98.6%的准确率、98.4%的敏感性和98.7%的特异性，表现不逊于或优于纯人工与纯AI方案。对于需人工复核的病例，利用AI生成的解释预填筛选表，使筛查时间从平均20分钟降至43秒，单例患者-试验配对平均成本为0.96美元。
原文摘要 · Abstract (English)
Clinical trials play an important role in cancer care and research, yet participation rates remain low. We developed MSK-MATCH (Memorial Sloan Kettering Multi-Agent Trial Coordination Hub), an AI system for automated eligibility screening from clinical text. MSK-MATCH integrates a large language model with a curated oncology trial knowledge base and retrieval-augmented architecture providing explanations for all AI predictions grounded in source text. In a retrospective dataset of 88,518 clinical documents from 731 patients across six breast cancer trials, MSK-MATCH automatically resolved 61.9% of cases and triaged 38.1% for human review. This AI-assisted workflow achieved 98.6% accuracy, 98.4% sensitivity, and 98.7% specificity for patient-level eligibility classification, matching or exceeding performance of the human-only and AI-only comparisons. For the triaged cases requiring manual review, prepopulating eligibility screens with AI-generated explanations reduced screening time from 20 minutes to 43 seconds at an average cost of $0.96 per patient-trial pair.
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。