• 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

用于肾功能不全的晚期心力衰竭患者的人工智能混合生存评估

AI hybrid survival assessment for advanced heart failure patients with renal dysfunction.

作者信息

Zhang Ge, Wang Zeyu, Tong Zhuang, Qin Zhen, Su Chang, Li Demin, Xu Shuai, Li Kaixiang, Zhou Zhaokai, Xu Yudi, Zhang Shiqian, Wu Ruhao, Li Teng, Zheng Youyang, Zhang Jinying, Cheng Ke, Tang Junnan

机构信息

Department of Cardiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, 450052, China.

Henan Province Key Laboratory of Cardiac Injury and Repair, Zhengzhou, Henan, 450052, China.

出版信息

Nat Commun. 2024 Aug 8;15(1):6756. doi: 10.1038/s41467-024-50415-9.

DOI:10.1038/s41467-024-50415-9
PMID:39117613
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11310499/
Abstract

Renal dysfunction (RD) often characterizes the worse course of patients with advanced heart failure (AHF). Many prognosis assessments are hindered by researcher biases, redundant predictors, and lack of clinical applicability. In this study, we enroll 1736 AHF/RD patients, including data from Henan Province Clinical Research Center for Cardiovascular Diseases (which encompasses 11 hospital subcenters), and Beth Israel Deaconess Medical Center. We developed an AI hybrid modeling framework, assembling 12 learners with different feature selection paradigms to expand modeling schemes. The optimized strategy is identified from 132 potential schemes to establish an explainable survival assessment system: AIHFLevel. The conditional inference survival tree determines a probability threshold for prognostic stratification. The evaluation confirmed the system's robustness in discrimination, calibration, generalization, and clinical implications. AIHFLevel outperforms existing models, clinical features, and biomarkers. We also launch an open and user-friendly website www.hf-ai-survival.com , empowering healthcare professionals with enhanced tools for continuous risk monitoring and precise risk profiling.

摘要

肾功能不全（RD）常是晚期心力衰竭（AHF）患者病情恶化的特征。许多预后评估受到研究者偏差、冗余预测指标以及缺乏临床适用性的阻碍。在本研究中，我们纳入了1736例AHF/RD患者，数据来自河南省心血管病临床研究中心（包括11个医院分中心）以及贝斯以色列女执事医疗中心。我们开发了一个人工智能混合建模框架，集合了12个具有不同特征选择范式的学习器以扩展建模方案。从132种潜在方案中确定优化策略，以建立一个可解释的生存评估系统：AIHFLevel。条件推断生存树确定预后分层的概率阈值。评估证实了该系统在区分、校准、泛化和临床意义方面的稳健性。AIHFLevel优于现有模型、临床特征和生物标志物。我们还推出了一个开放且用户友好的网站www.hf-ai-survival.com，为医疗保健专业人员提供增强工具，以进行持续风险监测和精确风险评估。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/1e3eebf086a0/41467_2024_50415_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/c8c2036bdf5d/41467_2024_50415_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/48aa78a29521/41467_2024_50415_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/b48479504dbf/41467_2024_50415_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/cff55c297efa/41467_2024_50415_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/b10d3487456e/41467_2024_50415_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/ce6ae72c05a7/41467_2024_50415_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/1e3eebf086a0/41467_2024_50415_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/c8c2036bdf5d/41467_2024_50415_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/48aa78a29521/41467_2024_50415_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/b48479504dbf/41467_2024_50415_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/cff55c297efa/41467_2024_50415_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/b10d3487456e/41467_2024_50415_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/ce6ae72c05a7/41467_2024_50415_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/10f8/11310499/1e3eebf086a0/41467_2024_50415_Fig7_HTML.jpg

相似文献

1
AI hybrid survival assessment for advanced heart failure patients with renal dysfunction.用于肾功能不全的晚期心力衰竭患者的人工智能混合生存评估
Nat Commun. 2024 Aug 8;15(1):6756. doi: 10.1038/s41467-024-50415-9.
2
Clinical Implications of Serum Albumin Levels in Acute Heart Failure: Insights From DOSE-AHF and ROSE-AHF.急性心力衰竭时血清白蛋白水平的临床意义：来自DOSE-AHF和ROSE-AHF研究的见解
J Card Fail. 2016 Nov;22(11):884-890. doi: 10.1016/j.cardfail.2016.01.015. Epub 2016 Feb 2.
3
A combined-biomarker approach to clinical phenotyping renal dysfunction in heart failure.一种用于心力衰竭患者肾功能不全临床表型分析的联合生物标志物方法。
J Card Fail. 2014 Dec;20(12):912-9. doi: 10.1016/j.cardfail.2014.08.008. Epub 2014 Aug 23.
4
Implications of Alternative Hepatorenal Prognostic Scoring Systems in Acute Heart Failure (from DOSE-AHF and ROSE-AHF).急性心力衰竭中替代肝肾预后评分系统的意义（来自DOSE-AHF和ROSE-AHF研究）
Am J Cardiol. 2017 Jun 15;119(12):2003-2009. doi: 10.1016/j.amjcard.2017.03.031. Epub 2017 Mar 29.
5
Cystatin C in acute heart failure without advanced renal impairment.无晚期肾功能损害的急性心力衰竭患者中的胱抑素C
Am J Med. 2009 Jun;122(6):566-73. doi: 10.1016/j.amjmed.2008.10.042. Epub 2009 Apr 24.
6
Effect of renal function on prognosis in chronic heart failure.肾功能对慢性心力衰竭预后的影响。
Am J Cardiol. 2015 Jan 1;115(1):62-8. doi: 10.1016/j.amjcard.2014.09.055. Epub 2014 Oct 23.
7
Response to cardiac resynchronization therapy in patients with heart failure and renal insufficiency.心力衰竭合并肾功能不全患者对心脏再同步治疗的反应
Pacing Clin Electrophysiol. 2010 Jul;33(7):850-9. doi: 10.1111/j.1540-8159.2010.02705.x. Epub 2010 Feb 19.
8
The PROTECT in-hospital risk model: 7-day outcome in patients hospitalized with acute heart failure and renal dysfunction.PROTECT 院内风险模型：合并急性心力衰竭和肾功能障碍住院患者的 7 天结局。
Eur J Heart Fail. 2012 Jun;14(6):605-12. doi: 10.1093/eurjhf/hfs029. Epub 2012 Apr 25.
9
Machine learning-based model for predicting 1 year mortality of hospitalized patients with heart failure.基于机器学习的模型预测心力衰竭住院患者 1 年死亡率。
ESC Heart Fail. 2021 Oct;8(5):4077-4085. doi: 10.1002/ehf2.13556. Epub 2021 Aug 13.
10
Elevated serum creatinine at baseline predicts poor outcome in patients receiving cardiac resynchronization therapy.基线时血清肌酐升高预示接受心脏再同步治疗的患者预后不良。
Pacing Clin Electrophysiol. 2008 May;31(5):575-9. doi: 10.1111/j.1540-8159.2008.01043.x.

引用本文的文献

1
AI-based Assessment of Risk Factors for Coronary Heart Disease in Patients With Diabetes Mellitus and Construction of a Prediction Model for a Treatment Regimen.基于人工智能评估糖尿病患者冠心病危险因素并构建治疗方案预测模型
Rev Cardiovasc Med. 2025 Jun 25;26(6):36293. doi: 10.31083/RCM36293. eCollection 2025 Jun.
2
A physics-informed and data-driven framework for robotic welding in manufacturing.一种用于制造业中机器人焊接的物理信息与数据驱动框架。
Nat Commun. 2025 May 23;16(1):4807. doi: 10.1038/s41467-025-60164-y.
3
Association of platelet-to-lymphocyte ratio with 1-year all-cause mortality in ICU patients with heart failure.

本文引用的文献

1
Atherosclerotic plaque vulnerability quantification system for clinical and biological interpretability.用于临床和生物学可解释性的动脉粥样硬化斑块易损性量化系统。
iScience. 2023 Aug 9;26(9):107587. doi: 10.1016/j.isci.2023.107587. eCollection 2023 Sep 15.
2
2023 Focused Update of the 2021 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure.《2021年欧洲心脏病学会急性和慢性心力衰竭诊断与治疗指南》2023年聚焦更新
Eur Heart J. 2023 Oct 1;44(37):3627-3639. doi: 10.1093/eurheartj/ehad195.
3
Artificial intelligence and heart failure: A state-of-the-art review.
血小板与淋巴细胞比值与ICU中心力衰竭患者1年全因死亡率的关联
Sci Rep. 2024 Dec 30;14(1):32016. doi: 10.1038/s41598-024-83583-1.
人工智能与心力衰竭：最新综述。
Eur J Heart Fail. 2023 Sep;25(9):1507-1525. doi: 10.1002/ejhf.2994. Epub 2023 Sep 8.
4
Differential expression profiles of plasma exosomal microRNAs in dilated cardiomyopathy with chronic heart failure.扩张型心肌病合并心力衰竭患者血浆外泌体 microRNAs 的差异表达谱。
J Cell Mol Med. 2023 Jul;27(14):1988-2003. doi: 10.1111/jcmm.17789. Epub 2023 May 27.
5
Artificial intelligence and prediction of cardiometabolic disease: Systematic review of model performance and potential benefits in indigenous populations.人工智能与心脏代谢疾病预测：对原住民模型性能及潜在益处的系统评价
Artif Intell Med. 2023 May;139:102534. doi: 10.1016/j.artmed.2023.102534. Epub 2023 Mar 28.
6
Natriuretic peptides: role in the diagnosis and management of heart failure: a scientific statement from the Heart Failure Association of the European Society of Cardiology, Heart Failure Society of America and Japanese Heart Failure Society.利钠肽：在心衰诊断和管理中的作用：欧洲心脏病学会心力衰竭协会、美国心力衰竭学会和日本心力衰竭学会的科学声明。
Eur J Heart Fail. 2023 May;25(5):616-631. doi: 10.1002/ejhf.2848. Epub 2023 Apr 26.
7
Advanced heart failure in adult congenital heart disease: the role of renal dysfunction in management and outcomes.成人先天性心脏病中的晚期心力衰竭：肾功能障碍在管理和预后中的作用。
Eur J Prev Cardiol. 2023 Sep 20;30(13):1335-1342. doi: 10.1093/eurjpc/zwad094.
8
A cardiologist's guide to machine learning in cardiovascular disease prognosis prediction.心脏病学家在心血管疾病预后预测中的机器学习指南。
Basic Res Cardiol. 2023 Mar 20;118(1):10. doi: 10.1007/s00395-023-00982-7.
9
Major cardiovascular events and subsequent risk of kidney failure with replacement therapy: a CKD Prognosis Consortium study.主要心血管事件与后续肾脏替代治疗的衰竭风险：CKD 预后联盟研究。
Eur Heart J. 2023 Apr 1;44(13):1157-1166. doi: 10.1093/eurheartj/ehac825.
10
Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review.基于机器学习的糖尿病预测模型中的心血管并发症：系统评价。
Cardiovasc Diabetol. 2023 Jan 19;22(1):13. doi: 10.1186/s12933-023-01741-7.