• 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

预测主动脉夹层患者住院时间延长风险因素的机器学习模型：一项回顾性临床研究

Machine Learning Model for Predicting Risk Factors of Prolonged Length of Hospital Stay in Patients with Aortic Dissection: a Retrospective Clinical Study.

作者信息

Li Luo, Chen Yihuan, Xie Hui, Zheng Peng, Mu Gaohang, Li Qian, Huang Haoyue, Shen Zhenya

机构信息

Department of Cardiovascular Surgery of the First Affiliated Hospital & Institute for Cardiovascular Science, Soochow University, Suzhou Medical College, Soochow University, 899 Pinghai Road, Jiangsu, 215123, Suzhou, China.

Department of Cardiology, School of Medicine, Zhongda Hospital, Southeast University, 87 Dingjiaqiao, Jiangsu, 210009, Nanjing, China.

出版信息

J Cardiovasc Transl Res. 2025 Feb;18(1):185-197. doi: 10.1007/s12265-024-10565-z. Epub 2024 Oct 10.

DOI:10.1007/s12265-024-10565-z
PMID:39388090
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11885363/
Abstract

The length of hospital stay (LOS) is crucial for assessing medical service quality. This study aimed to develop machine learning models for predicting risk factors of prolonged LOS in patients with aortic dissection (AD). The data of 516 AD patients were obtained from the hospital's medical system, with 111 patients in the prolonged LOS (> 30 days) group based on three quarters of the LOS in the entire cohort. Given the screened variables and prediction models, the XGBoost model demonstrated superior predictive performance in identifying prolonged LOS, due to the highest area under the receiver operating characteristic curve, sensitivity, and F1-score in both subsets. The SHapley Additive exPlanation analysis indicated that high density lipoprotein cholesterol, alanine transaminase, systolic blood pressure, percentage of lymphocyte, and operation time were the top five risk factors associated with prolonged LOS. These findings have a guiding value for the clinical management of patients with AD.

摘要

住院时间（LOS）对于评估医疗服务质量至关重要。本研究旨在开发机器学习模型，以预测主动脉夹层（AD）患者住院时间延长的风险因素。从医院医疗系统中获取了516例AD患者的数据，根据整个队列中四分之三的住院时间，将111例患者纳入住院时间延长（>30天）组。鉴于筛选出的变量和预测模型，XGBoost模型在识别住院时间延长方面表现出卓越的预测性能，因为在两个子集中，其受试者操作特征曲线下面积、敏感性和F1分数均最高。SHapley加性解释分析表明，高密度脂蛋白胆固醇、丙氨酸转氨酶、收缩压、淋巴细胞百分比和手术时间是与住院时间延长相关的前五大风险因素。这些发现对AD患者的临床管理具有指导价值。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/3b642b2d42ac/12265_2024_10565_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/1d5fedadc20d/12265_2024_10565_Figa_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/70f3c162f0bd/12265_2024_10565_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/e36b5dfc6148/12265_2024_10565_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/c99583daa999/12265_2024_10565_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/5d5e3ecb0be6/12265_2024_10565_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/5303034d3bb7/12265_2024_10565_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/b26cd797bbe8/12265_2024_10565_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/3b642b2d42ac/12265_2024_10565_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/1d5fedadc20d/12265_2024_10565_Figa_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/70f3c162f0bd/12265_2024_10565_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/e36b5dfc6148/12265_2024_10565_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/c99583daa999/12265_2024_10565_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/5d5e3ecb0be6/12265_2024_10565_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/5303034d3bb7/12265_2024_10565_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/b26cd797bbe8/12265_2024_10565_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4fde/11885363/3b642b2d42ac/12265_2024_10565_Fig7_HTML.jpg

相似文献

1
Machine Learning Model for Predicting Risk Factors of Prolonged Length of Hospital Stay in Patients with Aortic Dissection: a Retrospective Clinical Study.预测主动脉夹层患者住院时间延长风险因素的机器学习模型：一项回顾性临床研究
J Cardiovasc Transl Res. 2025 Feb;18(1):185-197. doi: 10.1007/s12265-024-10565-z. Epub 2024 Oct 10.
2
Enhanced machine learning models for predicting one-year mortality in individuals suffering from type A aortic dissection.用于预测A型主动脉夹层患者一年死亡率的增强机器学习模型。
J Thorac Cardiovasc Surg. 2025 Apr;169(4):1191-1200.e3. doi: 10.1016/j.jtcvs.2024.09.019. Epub 2024 Sep 18.
3
Relationship between atherogenic index of plasma and length of stay in critically ill patients with atherosclerotic cardiovascular disease: a retrospective cohort study and predictive modeling based on machine learning.血浆致动脉粥样硬化指数与动脉粥样硬化性心血管疾病重症患者住院时间的关系：一项回顾性队列研究及基于机器学习的预测模型
Cardiovasc Diabetol. 2025 Feb 28;24(1):95. doi: 10.1186/s12933-025-02654-3.
4
Machine Learning Model for Risk Prediction of Prolonged Intensive Care Unit in Patients Receiving Intra-aortic Balloon Pump Therapy during Coronary Artery Bypass Graft Surgery.冠状动脉搭桥手术期间接受主动脉内球囊反搏治疗患者重症监护病房延长住院风险预测的机器学习模型
J Cardiovasc Transl Res. 2025 Apr;18(2):341-353. doi: 10.1007/s12265-024-10580-0. Epub 2024 Dec 24.
5
Length of Stay after Thoracic Endovascular Aortic Repair Depends on Indication and Acuity.胸主动脉腔内修复术后的住院时间取决于手术指征和病情严重程度。
Ann Vasc Surg. 2019 Feb;55:157-165. doi: 10.1016/j.avsg.2018.06.027. Epub 2018 Sep 11.
6
Can EuroSCORE II predict the mortality and length of intensive care unit stay after total aortic arch replacement with stented elephant trunk implantation for DeBakey type I aortic dissection?欧洲心脏手术风险评估系统II（EuroSCORE II）能否预测采用带支架象鼻植入术治疗DeBakey I型主动脉夹层的全主动脉弓置换术后的死亡率及重症监护病房住院时间？
Thorac Cardiovasc Surg. 2013 Oct;61(7):564-8. doi: 10.1055/s-0033-1348197. Epub 2013 Jun 17.
7
Is obstructive sleep apnoea associated with hypoxaemia and prolonged ICU stay after type A aortic dissection repair? A retrospective study in Chinese population.阻塞性睡眠呼吸暂停与 A 型主动脉夹层修复术后低氧血症和 ICU 住院时间延长有关吗？中国人群的回顾性研究。
BMC Cardiovasc Disord. 2021 Sep 6;21(1):421. doi: 10.1186/s12872-021-02226-9.
8
A Predictive Model for Determining Patients Not Requiring Prolonged Hospital Length of Stay After Elective Primary Total Hip Arthroplasty.择期初次全髋关节置换术后无需延长住院时间的患者预测模型。
Anesth Analg. 2019 Jul;129(1):43-50. doi: 10.1213/ANE.0000000000003798.
9
Prediction of Distal Aortic Enlargement after Proximal Repair of Aortic Dissection Using Machine Learning.使用机器学习预测主动脉夹层近端修复后的远端主动脉扩张。
Ann Vasc Surg. 2021 Aug;75:332-340. doi: 10.1016/j.avsg.2021.02.039. Epub 2021 Apr 3.
10
Prognostic prediction of long-term survival in patients with type A aortic dissection undergoing surgical repair: development of a novel prognostic index.接受手术修复的A型主动脉夹层患者长期生存的预后预测：一种新型预后指数的开发
BMC Cardiovasc Disord. 2025 Feb 13;25(1):99. doi: 10.1186/s12872-025-04552-8.

引用本文的文献

1
The potential role of amino acids in myopia: inspiration from metabolomics.氨基酸在近视中的潜在作用：来自代谢组学的启示
Metabolomics. 2024 Dec 15;21(1):6. doi: 10.1007/s11306-024-02207-x.

本文引用的文献

1
Assessment of the Relationship Between Liver Enzymes and Cardiovascular Disease: A Study in Bangladeshi Adults.评估肝酶与心血管疾病的关系：孟加拉国成年人的研究。
Endocrinol Diabetes Metab. 2024 Mar;7(2):e00481. doi: 10.1002/edm2.481.
2
Elevated AST/ALT (De Ritis) Ratio is a Risk Factor of Drainage Volume after Aortic Arch Surgery.天冬氨酸转氨酶/丙氨酸转氨酶（德瑞蒂斯）比值升高是主动脉弓手术后引流量的危险因素。
Heart Surg Forum. 2023 Dec 18;26(6):E755-E763. doi: 10.59958/hsf.6933.
3
Association of the low-density lipoprotein cholesterol to high-density lipoprotein cholesterol ratio and major adverse cardiac and cerebrovascular events in patients with coronary heart disease undergoing percutaneous coronary intervention: a cohort study.
低密度脂蛋白胆固醇与高密度脂蛋白胆固醇比值与经皮冠状动脉介入治疗的冠心病患者主要不良心脏和脑血管事件的关系：一项队列研究。
Curr Med Res Opin. 2023 Sep;39(9):1175-1181. doi: 10.1080/03007995.2023.2246889. Epub 2023 Aug 24.
4
Very high HDL-C (high-density lipoprotein cholesterol) is associated with increased cardiovascular risk in patients with NSTEMI (non-ST-segment elevation myocardial infarction) undergoing PCI (percutaneous coronary intervention).极高的高密度脂蛋白胆固醇（HDL-C）与接受经皮冠状动脉介入治疗（PCI）的 NSTEMI（非 ST 段抬高型心肌梗死）患者的心血管风险增加相关。
BMC Cardiovasc Disord. 2023 Jul 17;23(1):357. doi: 10.1186/s12872-023-03383-9.
5
Causal effect of hypertension and blood pressure on aortic diseases: evidence from Mendelian randomization.高血压和血压对主动脉疾病的因果影响：来自孟德尔随机化的证据。
Hypertens Res. 2023 Sep;46(9):2203-2212. doi: 10.1038/s41440-023-01351-6. Epub 2023 Jul 13.
6
A Model-Agnostic Feature Attribution Approach to Magnetoencephalography Predictions Based on Shapley Value.基于 Shapley 值的脑磁图预测的模型不可知特征归因方法。
IEEE J Biomed Health Inform. 2023 May;27(5):2524-2535. doi: 10.1109/JBHI.2023.3248139. Epub 2023 May 4.
7
Pediatric Primary Hypertension: An Underrecognized Condition: A Scientific Statement From the American Heart Association.儿科原发性高血压：一种未被充分认识的疾病：美国心脏协会的科学声明。
Hypertension. 2023 Jun;80(6):e101-e111. doi: 10.1161/HYP.0000000000000228. Epub 2023 Mar 30.
8
Perioperative individualized hemodynamic optimization according to baseline mean arterial pressure in cardiac surgery patients: Rationale and design of the OPTIPAM randomized trial.心脏手术患者根据基线平均动脉压进行围手术期个体化血流动力学优化：OP-TIPAM 随机试验的原理和设计。
Am Heart J. 2023 Jul;261:10-20. doi: 10.1016/j.ahj.2023.03.005. Epub 2023 Mar 18.
9
Leukocyte cell population data in patients with cardiac surgery and cardiopulmonary bypass: A potential readily available tool to monitor immunity.心脏手术和体外循环患者的白细胞细胞群体数据：监测免疫的潜在现成工具。
Front Immunol. 2023 Jan 19;13:1101937. doi: 10.3389/fimmu.2022.1101937. eCollection 2022.
10
The prognostic value of elevated neutrophil-lymphocyte ratio for cardiac surgery-associated acute kidney injury: A systematic review and meta-analysis.中性粒细胞与淋巴细胞比值升高对心脏手术相关急性肾损伤的预后价值：系统评价和荟萃分析。
Acta Anaesthesiol Scand. 2023 Feb;67(2):131-141. doi: 10.1111/aas.14170. Epub 2022 Nov 25.