文献速递胸部肿瘤

人工智能自动处理多中心肺癌非结构化健康记录

Next-generation multicenter studies: using artificial intelligence to automatically process unstructured health records of patients with lung cancer across multiple institutions.
PubMed 文献 · Ann Oncol · 2025-12-15

在法国LUCC联盟10家中心开展多中心研究,比较微调大语言模型与人工从非结构化健康记录中提取31个变量的准确性。测试队列311例,AI提取错误率7.0%低于人工14.2%(P<0.001),机构间方差更低,混合人工复核低置信度输出可进一步降低错误率。

要点

  • AI提取错误率7.0%,显著低于人工提取的14.2%(P<0.001)。
  • AI提取的机构间方差为0.12%,低于人工的0.39%。
  • 对30%低置信度AI输出进行人工复核,错误率降至4.4%。

核心结论

  • 在多中心环境下,AI管道比人工提取错误率更低且一致性更高,支持AI赋能的大规模真实世界数据研究可行性。

研究设计与样本

  • 法国LUCC联盟多中心研究,对10家中心肺癌患者去标识化PDF格式非结构化健康记录应用微调大语言模型提取31个变量。
  • AI提取覆盖10 327例患者,测试队列纳入311例,以多源一致值为金标准,分歧病例由盲法专家裁定。

主要发现

  • 28个单一正确答案变量共8708个数据点,AI错误率7.0%,人工抽象错误率14.2%(P<0.001)。
  • 三个多选题变量F1-score:基因改变0.97 vs 0.86,合并症0.86 vs 0.76,转移部位0.71 vs 0.69。
  • 机构间方差AI为0.12%,人工为0.39%。
  • 对30%低置信度AI输出进行针对性人工复核的混合方法,错误率进一步降至4.4%。
  • 基于AI提取数据的生存分析与金标准高度一致,中位总生存和无进展生存相似。

临床怎么用

  • 可考虑将微调大语言模型用于多中心肺癌真实世界数据的自动提取,以降低人工抽象负担和机构间差异。
  • 对低置信度AI输出进行针对性人工复核的混合工作流可进一步降低错误率。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Manual abstraction of real-world data (RWD) from unstructured health records (HRs) remains resource intensive, error prone, and highly variable across institutions. Large language models (LLMs) offer a scalable alternative, but their performance in multicenter oncology settings is not fully validated. PATIENTS AND METHODS: We conducted a multicenter study within the French Large & Unified Cancer Cohort (LUCC) consortium to compare the accuracy of artificial intelligence (AI)-based data extraction against manual abstraction by clinical research professionals. A fine-tuned LLM was applied to de-identified unstructured HRs in PDF format to extract 31 variables from lung cancer patients across 10 centers. Ground truth was defined as concordant values across sources, with discrepant cases adjudicated by a blinded expert. The primary endpoint was the extraction error rates. Secondary endpoints included per-variable performance, interinstitutional variability, F1-score for multiple-choice variables, added value of hybrid AI-human workflows, and survival analyses. RESULTS: Among 10 327 patients with AI-based extraction, 311 were included in the test cohort. Across 8708 datapoints for 28 variables with only one correct answer, the LLM achieved a 7.0% error rate, outperforming manual abstraction (14.2%, P <0.001). The F1-scores of three multiple-choice variables were superior (gene alterations 0.97 versus 0.86, comorbidities 0.86 versus 0.76, metastatic sites 0.71 versus 0.69). Interinstitutional variance was lower with AI (0.12% versus 0.39%). A hybrid approach with targeted human review of 30% of low-confidence AI outputs further decreased error rates to 4.4%. Survival analyses based on AI-extracted data closely matched ground truth, with similar median overall and progression-free survival. CONCLUSIONS: In a multicenter setting, our AI pipeline yielded lower error rates and greater consistency than manual abstraction. These findings support the feasibility of next-generation, AI-enabled multicenter studies to generate high-quality RWD at scale, with potential applicability in prospective clinical trials.

来源:Ann Oncol,查看原文。版权归原作者所有。

引用

  1. Aldea M, Zullo L, Levrat V, et al. Next-generation multicenter studies: using artificial intelligence to automatically process unstructured health records of patients with lung cancer across multiple institutions. Ann Oncol. 2025. PMID: 41407195. doi:10.1016/j.annonc.2025.12.006

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。