文献速递医学人工智能与信息学基础与转化研究真实世界研究与卫生经济

可解释AI决策支持工具在NSCLC中的临床可用性及多模态模型评估

Clinical usability of an explainable AI decision support tool and evaluation of multimodal models in NSCLC.
PubMed 文献 · Nat Med · 2026-09-13

I3LUNG是迄今最大规模国际真实世界多模态AI研究,纳入2396例NSCLC患者。研究整合临床、血液、CT、数字病理和基因组数据构建机器学习与深度学习模型,血液-only模型在测试集AUC最高0.77,外部验证AUC 0.55-0.72,AI模型显著优于PD-L1、ECOG PS、NLR、LDH和LIPI评分。可解释AI工具使专家和非专家医生的预测均得到改善。

要点

  • 血液-only AI模型在测试集AUC最高0.77,外部验证降至0.55-0.72。
  • AI模型在独立测试集中显著优于PD-L1、ECOG PS、NLR、LDH和LIPI。
  • 可解释AI工具可提升肺科专家与非专家医生的预测能力。

核心结论

  • I3LUNG项目证明AI工具具有临床可用性,可解释AI能改善医生预测。
  • 血液-only模型表现稳定,多模态融合的增量获益尚不确定。

研究设计与样本

  • 国际、真实世界、多模态、基于AI的研究,纳入2396例NSCLC患者。
  • 整合临床、血液、CT、数字病理和基因组数据,构建MLEF和DLIF模型。
  • 在独立测试集和外部验证集中评估模型性能。
  • 开展临床可用性研究,评估可解释AI工具对医生预测的影响。

主要发现

  • 机器学习和深度学习血液-only模型在测试集AUC最高0.77。
  • 外部验证AUC范围0.55-0.72,性能下降可能反映人群差异。
  • AI模型在独立测试集中显著优于PD-L1、ECOG PS、NLR、LDH和LIPI评分。
  • 可解释AI血液-only工具使肺科专家和非专家医生的预测均得到改善。
  • 多模态融合(血液+CT+数字病理)与更高性能相关,但增量获益在测试集和外部验证中未体现。

临床怎么用

  • 可解释AI决策支持工具可辅助NSCLC免疫治疗选择,提升医生预测能力。
  • 血液-only模型可作为跨结局的稳定预测工具,多模态融合需进一步验证。

局限性

  • 外部验证性能下降,可能反映人群差异。
  • 多模态融合的增量获益尚不确定,未在测试集和外部验证中转化。

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

Despite a decade in, immunotherapy (IO) treatment selection in non-small cell lung cancer (NSCLC) remains largely guided by subgroup analyses and imperfect programmed death ligand 1 (PD-L1) and clinical scores. To our knowledge, I3LUNG ( NCT05537922 ) is currently the largest international, real-world, multimodal, artificial intelligence (AI)-based study, enrolling 2,396 patients. We integrated real-world clinical and blood (CB) data, computed tomography (CT) images, digital pathology (DP), and genomics into machine learning early fusion (MLEF) and deep learning intermediate fusion (DLIF) models. Machine learning (ML) and deep learning (DL) CB-only models achieved consistent performance across outcomes with area under the curve (AUC) up to 0.77 in the test (TEST) set. Performance drop in external validation (EXVAL) likely reflects population differences (AUC range: 0.55-0.72). AI models significantly surpassed PD-L1, Eastern Cooperative Oncology Group performance status (ECOG PS), neutrophil-to-lymphocyte ratio (NLR), lactate dehydrogenase (LDH) and Lung Immune Prognostic Index (LIPI) score in the independent TEST set. The clinical usability study showed that lung expert and nonexpert physicians improved their prediction with the explainable AI (XAI) ML CB-only based tool. Although multimodal integration with MLEF (CB+CT+DP) was associated with higher performance, its incremental benefit remains uncertain, not translated in TEST and EXVAL. The I3LUNG project is a pioneering framework showing the clinical usefulness of AI tools. A prospective validation of the decision support system (both CB and multimodal) is currently undergoing in more than 2,000 patients.

来源:Nat Med,查看原文。版权归原作者所有。

引用

  1. Prelaj A, Miskovic V, Sacco M, et al. Clinical usability of an explainable AI decision support tool and evaluation of multimodal models in NSCLC. Nat Med. 2026. PMID: 42733093. doi:10.1038/s41591-026-04488-2

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。