• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

使用多模态真实世界数据和可解释人工智能解码泛癌治疗结果

Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence.

作者信息

Keyl Julius, Keyl Philipp, Montavon Grégoire, Hosch René, Brehmer Alexander, Mochmann Liliana, Jurmeister Philipp, Dernbach Gabriel, Kim Moon, Koitka Sven, Bauer Sebastian, Bechrakis Nikolaos, Forsting Michael, Führer-Sakel Dagmar, Glas Martin, Grünwald Viktor, Hadaschik Boris, Haubold Johannes, Herrmann Ken, Kasper Stefan, Kimmig Rainer, Lang Stephan, Rassaf Tienush, Roesch Alexander, Schadendorf Dirk, Siveke Jens T, Stuschke Martin, Sure Ulrich, Totzeck Matthias, Welt Anja, Wiesweg Marcel, Baba Hideo A, Nensa Felix, Egger Jan, Müller Klaus-Robert, Schuler Martin, Klauschen Frederick, Kleesiek Jens

机构信息

Institute for Artificial Intelligence in Medicine, University Hospital Essen (AöR), Essen, Germany.

Institute of Pathology, University Hospital Essen (AöR), Essen, Germany.

出版信息

Nat Cancer. 2025 Feb;6(2):307-322. doi: 10.1038/s43018-024-00891-1. Epub 2025 Jan 30.

DOI:10.1038/s43018-024-00891-1
PMID:39885364
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11864985/
Abstract

Despite advances in precision oncology, clinical decision-making still relies on limited variables and expert knowledge. To address this limitation, we combined multimodal real-world data and explainable artificial intelligence (xAI) to introduce AI-derived (AID) markers for clinical decision support. We used xAI to decode the outcome of 15,726 patients across 38 solid cancer entities based on 350 markers, including clinical records, image-derived body compositions, and mutational tumor profiles. xAI determined the prognostic contribution of each clinical marker at the patient level and identified 114 key markers that accounted for 90% of the neural network's decision process. Moreover, xAI enabled us to uncover 1,373 prognostic interactions between markers. Our approach was validated in an independent cohort of 3,288 patients with lung cancer from a US nationwide electronic health record-derived database. These results show the potential of xAI to transform the assessment of clinical variables and enable personalized, data-driven cancer care.

摘要

尽管精准肿瘤学取得了进展，但临床决策仍依赖于有限的变量和专家知识。为了解决这一局限性，我们将多模式真实世界数据与可解释人工智能（xAI）相结合，引入人工智能衍生（AID）标志物以支持临床决策。我们使用xAI根据350个标志物对38种实体癌的15726例患者的预后进行解码，这些标志物包括临床记录、图像衍生的身体成分和肿瘤突变谱。xAI在患者层面确定了每个临床标志物的预后贡献，并识别出114个关键标志物，这些标志物占神经网络决策过程的90%。此外，xAI使我们能够发现标志物之间1373种预后相互作用。我们的方法在美国全国电子健康记录衍生数据库中3288例肺癌患者的独立队列中得到了验证。这些结果显示了xAI在改变临床变量评估及实现个性化、数据驱动的癌症治疗方面的潜力。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/e07c9ab0903b/43018_2024_891_Fig17_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/759ca680fb65/43018_2024_891_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/b7141bfc75fd/43018_2024_891_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/adabaf0f373b/43018_2024_891_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/e7876ed56f16/43018_2024_891_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/890502809abe/43018_2024_891_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/bfdbdc4e5112/43018_2024_891_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/331e79c887e0/43018_2024_891_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/7ec81aca1222/43018_2024_891_Fig8_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/f994b6b27a82/43018_2024_891_Fig9_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/1d5dae6cb0b2/43018_2024_891_Fig10_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/809b71c7553f/43018_2024_891_Fig11_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/3e48553e9f29/43018_2024_891_Fig12_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/4da0f4ac175c/43018_2024_891_Fig13_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/65890fa7733a/43018_2024_891_Fig14_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/5f14da305de2/43018_2024_891_Fig15_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/1a81ff618ea6/43018_2024_891_Fig16_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/e07c9ab0903b/43018_2024_891_Fig17_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/759ca680fb65/43018_2024_891_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/b7141bfc75fd/43018_2024_891_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/adabaf0f373b/43018_2024_891_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/e7876ed56f16/43018_2024_891_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/890502809abe/43018_2024_891_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/bfdbdc4e5112/43018_2024_891_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/331e79c887e0/43018_2024_891_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/7ec81aca1222/43018_2024_891_Fig8_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/f994b6b27a82/43018_2024_891_Fig9_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/1d5dae6cb0b2/43018_2024_891_Fig10_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/809b71c7553f/43018_2024_891_Fig11_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/3e48553e9f29/43018_2024_891_Fig12_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/4da0f4ac175c/43018_2024_891_Fig13_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/65890fa7733a/43018_2024_891_Fig14_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/5f14da305de2/43018_2024_891_Fig15_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/1a81ff618ea6/43018_2024_891_Fig16_ESM.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8c3d/11864985/e07c9ab0903b/43018_2024_891_Fig17_ESM.jpg

相似文献

1
Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence.使用多模态真实世界数据和可解释人工智能解码泛癌治疗结果
Nat Cancer. 2025 Feb;6(2):307-322. doi: 10.1038/s43018-024-00891-1. Epub 2025 Jan 30.
2
Decoding the black box: Explainable AI (XAI) for cancer diagnosis, prognosis, and treatment planning-A state-of-the art systematic review.解码黑箱：癌症诊断、预后和治疗计划的可解释人工智能（XAI）——最新系统评价。
Int J Med Inform. 2025 Jan;193:105689. doi: 10.1016/j.ijmedinf.2024.105689. Epub 2024 Nov 4.
3
Effects of explainable artificial intelligence in neurology decision support.可解释人工智能在神经病学决策支持中的作用。
Ann Clin Transl Neurol. 2024 May;11(5):1224-1235. doi: 10.1002/acn3.52036. Epub 2024 Apr 5.
4
Applying Artificial Intelligence to Address the Knowledge Gaps in Cancer Care.应用人工智能解决癌症护理中的知识空白。
Oncologist. 2019 Jun;24(6):772-782. doi: 10.1634/theoncologist.2018-0257. Epub 2018 Nov 16.
5
Artificial intelligence-based biomarkers for treatment decisions in oncology.用于肿瘤治疗决策的基于人工智能的生物标志物
Trends Cancer. 2025 Mar;11(3):232-244. doi: 10.1016/j.trecan.2024.12.001. Epub 2025 Jan 14.
6
Applications of and issues with machine learning in medicine: Bridging the gap with explainable AI.机器学习在医学中的应用及问题：通过可解释人工智能缩小差距。
Biosci Trends. 2025 Jan 14;18(6):497-504. doi: 10.5582/bst.2024.01342. Epub 2024 Dec 8.
7
Integrating Artificial Intelligence-Driven Wearable Technology in Oncology Decision-Making: A Narrative Review.将人工智能驱动的可穿戴技术整合到肿瘤学决策中：一项叙述性综述。
Oncology. 2025;103(1):69-82. doi: 10.1159/000540494. Epub 2024 Jul 25.
8
Predicting gene mutation status via artificial intelligence technologies based on multimodal integration (MMI) to advance precision oncology.基于多模态整合（MMI）的人工智能技术预测基因突变状态，以推进精准肿瘤学。
Semin Cancer Biol. 2023 Jun;91:1-15. doi: 10.1016/j.semcancer.2023.02.006. Epub 2023 Feb 19.
9
Impact of artificial intelligence on prognosis, shared decision-making, and precision medicine for patients with inflammatory bowel disease: a perspective and expert opinion.人工智能对炎症性肠病患者预后、共同决策和精准医学的影响：观点和专家意见。
Ann Med. 2023;55(2):2300670. doi: 10.1080/07853890.2023.2300670. Epub 2024 Jan 1.
10
Do explainable AI (XAI) methods improve the acceptance of AI in clinical practice? An evaluation of XAI methods on Gleason grading.可解释人工智能（XAI）方法能否提高人工智能在临床实践中的接受度？对XAI方法在 Gleason分级中的评估。
J Pathol Clin Res. 2025 Mar;11(2):e70023. doi: 10.1002/2056-4538.70023.

引用本文的文献

1
Multimodal integration strategies for clinical application in oncology.肿瘤学临床应用中的多模态整合策略
Front Pharmacol. 2025 Aug 20;16:1609079. doi: 10.3389/fphar.2025.1609079. eCollection 2025.
2
Inflammation in cardio-oncology and psychological disorders: mechanisms, biomarkers, pain management, and therapeutic strategies.心脏肿瘤学中的炎症与心理障碍：机制、生物标志物、疼痛管理及治疗策略
Ann Med Surg (Lond). 2025 May 20;87(7):4229-4236. doi: 10.1097/MS9.0000000000003412. eCollection 2025 Jul.
3
The use of artificial intelligence in stereotactic ablative body radiotherapy for hepatocellular carcinoma.

本文引用的文献

1
AI-enabled electrocardiography alert intervention and all-cause mortality: a pragmatic randomized clinical trial.人工智能心电图预警干预与全因死亡率：一项实用随机临床试验。
Nat Med. 2024 May;30(5):1461-1470. doi: 10.1038/s41591-024-02961-4. Epub 2024 Apr 29.
2
Toward Explainable Artificial Intelligence for Precision Pathology.迈向精准病理学的可解释人工智能
Annu Rev Pathol. 2024 Jan 24;19:541-570. doi: 10.1146/annurev-pathmechdis-051222-113147. Epub 2023 Oct 23.
3
Single-cell gene regulatory network prediction by explainable AI.
人工智能在肝细胞癌立体定向消融放疗中的应用。
Front Med (Lausanne). 2025 Jun 6;12:1576494. doi: 10.3389/fmed.2025.1576494. eCollection 2025.
4
Exchange of Quantitative Computed Tomography Assessed Body Composition Data Using Fast Healthcare Interoperability Resources as a Necessary Step Toward Interoperable Integration of Opportunistic Screening Into Clinical Practice: Methodological Development Study.使用快速医疗保健互操作性资源交换定量计算机断层扫描评估的身体成分数据，作为将机会性筛查可操作地整合到临床实践中的必要步骤：方法学开发研究
J Med Internet Res. 2025 May 21;27:e68750. doi: 10.2196/68750.
基于可解释 AI 的单细胞基因调控网络预测。
Nucleic Acids Res. 2023 Feb 28;51(4):e20. doi: 10.1093/nar/gkac1212.
4
Deep learning-based assessment of body composition and liver tumour burden for survival modelling in advanced colorectal cancer.基于深度学习的晚期结直肠癌生存模型中体成分和肝肿瘤负担评估。
J Cachexia Sarcopenia Muscle. 2023 Feb;14(1):545-552. doi: 10.1002/jcsm.13158. Epub 2022 Dec 21.
5
Data Integration-Possibilities of Molecular and Clinical Data Fusion on the Example of Thyroid Cancer Diagnostics.数据集成——以甲状腺癌诊断为例的分子与临床数据融合的可能性。
Int J Mol Sci. 2022 Oct 6;23(19):11880. doi: 10.3390/ijms231911880.
6
Artificial intelligence for multimodal data integration in oncology.人工智能在肿瘤学中用于多模态数据整合。
Cancer Cell. 2022 Oct 10;40(10):1095-1110. doi: 10.1016/j.ccell.2022.09.012.
7
Multimodal biomedical AI.多模态生物医学人工智能。
Nat Med. 2022 Sep;28(9):1773-1784. doi: 10.1038/s41591-022-01981-2. Epub 2022 Sep 15.
8
Multimodal survival prediction in advanced pancreatic cancer using machine learning.利用机器学习进行晚期胰腺癌的多模态生存预测。
ESMO Open. 2022 Oct;7(5):100555. doi: 10.1016/j.esmoop.2022.100555. Epub 2022 Aug 18.
9
Pan-cancer integrative histology-genomic analysis via multimodal deep learning.基于多模态深度学习的泛癌综合组织学-基因组分析。
Cancer Cell. 2022 Aug 8;40(8):865-878.e6. doi: 10.1016/j.ccell.2022.07.004.
10
Systematic pan-cancer analysis of mutation-treatment interactions using large real-world clinicogenomics data.利用大型真实临床基因组学数据进行系统泛癌症突变-治疗相互作用分析。
Nat Med. 2022 Aug;28(8):1656-1661. doi: 10.1038/s41591-022-01873-5. Epub 2022 Jun 30.