• 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

基于急诊脑出血手术患者肺部并发症术后预测的多种机器学习方法

Multiple Machine Learning Approaches Based on Postoperative Prediction of Pulmonary Complications in Patients With Emergency Cerebral Hemorrhage Surgery.

作者信息

Jing Xiaolei, Wang Xueqi, Zhuang Hongxia, Fang Xiang, Xu Hao

机构信息

Division of Life Sciences and Medicine, Department of Neurosurgery, The First Affiliated Hospital of USTC, University of Science and Technology of China, Hefei, China.

Division of Life Sciences and Medicine, Department of Neurology, The First Affiliated Hospital of USTC, University of Science and Technology of China, Hefei, China.

出版信息

Front Surg. 2022 Jan 18;8:797872. doi: 10.3389/fsurg.2021.797872. eCollection 2021.

DOI:10.3389/fsurg.2021.797872
PMID:35127804
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8812295/
Abstract

OBJECTIVE

This study aimed to create a prediction model of postoperative pulmonary complications for the patients with emergency cerebral hemorrhage surgery.

METHODS

Patients with hemorrhage surgery who underwent cerebral hemorrhage surgery were included and divided into two groups: patients with or without pulmonary complications. Patient characteristics, previous history, laboratory tests, and interventions were collected. Univariate and multivariate logistic regressions were used to predict postoperative pulmonary infection. Multiple machine learning approaches have been used to compare their importance in predicting factors, namely K-nearest neighbor (KNN), stochastic gradient descent (SGD), support vector classification (SVC), random forest (RF), and logistics regression (LR), as they are the most successful and widely used models for clinical data.

RESULTS

Three hundred and fifty four patients with emergency cerebral hemorrhage surgery between January 1, 2017 and December 31, 2020 were included in the study. 53.7% (190/354) of the patients developed postoperative pulmonary complications (PPC). Stepwise logistic regression analysis revealed four independent predictive factors associated with pulmonary complications, including current smoker, lymphocyte count, clotting time, and ASA score. In addition, the RF model had an ideal predictive performance.

CONCLUSIONS

According to our result, current smoker, lymphocyte count, clotting time, and ASA score were independent risks of pulmonary complications. Machine learning approaches can also provide more evidence in the prediction of pulmonary complications.

摘要

目的

本研究旨在建立急诊脑出血手术患者术后肺部并发症的预测模型。

方法

纳入接受脑出血手术的患者，分为两组：有或无肺部并发症的患者。收集患者特征、既往史、实验室检查和干预措施。采用单因素和多因素逻辑回归预测术后肺部感染。使用多种机器学习方法比较它们在预测因素中的重要性，即K近邻（KNN）、随机梯度下降（SGD）、支持向量分类（SVC）、随机森林（RF）和逻辑回归（LR），因为它们是临床数据中最成功且应用最广泛的模型。

结果

本研究纳入了2017年1月1日至2020年12月31日期间354例急诊脑出血手术患者。53.7%（190/354）的患者发生了术后肺部并发症（PPC）。逐步逻辑回归分析显示与肺部并发症相关的4个独立预测因素，包括当前吸烟者、淋巴细胞计数、凝血时间和美国麻醉医师协会（ASA）评分。此外，RF模型具有理想的预测性能。

结论

根据我们的结果，当前吸烟者、淋巴细胞计数、凝血时间和ASA评分是肺部并发症的独立风险因素。机器学习方法也可为肺部并发症的预测提供更多证据。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/b59f8d9f8fdf/fsurg-08-797872-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/8c95a86e0305/fsurg-08-797872-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/52af0f0d9552/fsurg-08-797872-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/4d64bc2b9d23/fsurg-08-797872-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/0715afad14fb/fsurg-08-797872-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/b59f8d9f8fdf/fsurg-08-797872-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/8c95a86e0305/fsurg-08-797872-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/52af0f0d9552/fsurg-08-797872-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/4d64bc2b9d23/fsurg-08-797872-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/0715afad14fb/fsurg-08-797872-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5c4d/8812295/b59f8d9f8fdf/fsurg-08-797872-g0005.jpg

相似文献

1
Multiple Machine Learning Approaches Based on Postoperative Prediction of Pulmonary Complications in Patients With Emergency Cerebral Hemorrhage Surgery.基于急诊脑出血手术患者肺部并发症术后预测的多种机器学习方法
Front Surg. 2022 Jan 18;8:797872. doi: 10.3389/fsurg.2021.797872. eCollection 2021.
2
Performance Analysis of Conventional Machine Learning Algorithms for Identification of Chronic Kidney Disease in Type 1 Diabetes Mellitus Patients.用于识别1型糖尿病患者慢性肾病的传统机器学习算法的性能分析
Diagnostics (Basel). 2021 Dec 3;11(12):2267. doi: 10.3390/diagnostics11122267.
3
Predicting 1-Year Mortality after Hip Fracture Surgery: An Evaluation of Multiple Machine Learning Approaches.预测髋部骨折手术后1年死亡率：多种机器学习方法的评估
J Pers Med. 2021 Jul 27;11(8):727. doi: 10.3390/jpm11080727.
4
A machine learning approach to predict early outcomes after pituitary adenoma surgery.一种用于预测垂体腺瘤手术后早期结果的机器学习方法。
Neurosurg Focus. 2018 Nov 1;45(5):E8. doi: 10.3171/2018.8.FOCUS18268.
5
Development and performance assessment of novel machine learning models to predict pneumonia after liver transplantation.新型机器学习模型的开发和性能评估，以预测肝移植后的肺炎。
Respir Res. 2021 Mar 31;22(1):94. doi: 10.1186/s12931-021-01690-3.
6
Prediction of the development of acute kidney injury following cardiac surgery by machine learning.机器学习预测心脏手术后急性肾损伤的发生。
Crit Care. 2020 Jul 31;24(1):478. doi: 10.1186/s13054-020-03179-9.
7
Prediction of pulmonary pressure after Glenn shunts by computed tomography-based machine learning models.基于计算机断层扫描的机器学习模型预测 Glenn 分流术后的肺压。
Eur Radiol. 2020 Mar;30(3):1369-1377. doi: 10.1007/s00330-019-06502-3. Epub 2019 Nov 8.
8
The statistical importance of P-POSSUM scores for predicting mortality after emergency laparotomy in geriatric patients.老年患者急诊剖腹手术后，P-POSSUM 评分预测死亡率的统计学意义。
BMC Med Inform Decis Mak. 2020 May 7;20(1):86. doi: 10.1186/s12911-020-1100-9.
9
Predicting Surgical Complications in Adult Patients Undergoing Anterior Cervical Discectomy and Fusion Using Machine Learning.使用机器学习预测接受前路颈椎间盘切除融合术的成年患者的手术并发症
Neurospine. 2018 Dec;15(4):329-337. doi: 10.14245/ns.1836248.124. Epub 2018 Dec 17.
10
Machine learning models for predicting critical illness risk in hospitalized patients with COVID-19 pneumonia.用于预测新冠肺炎肺炎住院患者危重症风险的机器学习模型
J Thorac Dis. 2021 Feb;13(2):1215-1229. doi: 10.21037/jtd-20-2580.

引用本文的文献

1
Identification of Major Bleeding Events in Postoperative Patients With Malignant Tumors in Chinese Electronic Medical Records: Algorithm Development and Validation.中文电子病历中恶性肿瘤术后患者主要出血事件的识别：算法开发与验证
JMIR Form Res. 2025 May 1;9:e66189. doi: 10.2196/66189.

本文引用的文献

1
Convolutional neural networks for brain tumour segmentation.用于脑肿瘤分割的卷积神经网络。
Insights Imaging. 2020 Jun 8;11(1):77. doi: 10.1186/s13244-020-00869-4.
2
Predicting outcome in patients with moderate to severe traumatic brain injury using electroencephalography.使用脑电图预测中重度创伤性脑损伤患者的预后。
Crit Care. 2019 Dec 11;23(1):401. doi: 10.1186/s13054-019-2656-6.
3
Machine learning-based dynamic mortality prediction after traumatic brain injury.基于机器学习的创伤性脑损伤后动态死亡率预测。
Sci Rep. 2019 Nov 27;9(1):17672. doi: 10.1038/s41598-019-53889-6.
4
Machine Learning to Predict In-Hospital Morbidity and Mortality after Traumatic Brain Injury.机器学习预测创伤性脑损伤后的住院期间发病率和死亡率。
J Neurotrauma. 2020 Jan 1;37(1):202-210. doi: 10.1089/neu.2018.6276. Epub 2019 Sep 18.
5
A retrospective study of the effect of fibrinogen levels during fresh frozen plasma transfusion in patients with traumatic brain injury.一项关于创伤性脑损伤患者输注新鲜冰冻血浆过程中纤维蛋白原水平影响的回顾性研究。
Acta Neurochir (Wien). 2019 Sep;161(9):1943-1953. doi: 10.1007/s00701-019-04010-3. Epub 2019 Jul 15.
6
Machine-learning analysis outperforms conventional statistical models and CT classification systems in predicting 6-month outcomes in pediatric patients sustaining traumatic brain injury.机器学习分析在预测外伤性脑损伤患儿 6 个月结局方面优于传统统计学模型和 CT 分类系统。
Neurosurg Focus. 2018 Nov 1;45(5):E2. doi: 10.3171/2018.8.FOCUS17773.
7
Effects of Positive End-Expiratory Pressure on the Risk of Postoperative Pulmonary Complications in Patients Undergoing Elective Craniotomy.呼气末正压对择期开颅手术患者术后肺部并发症风险的影响。
World Neurosurg. 2018 Apr;112:e39-e49. doi: 10.1016/j.wneu.2017.12.014. Epub 2017 Dec 16.
8
Evolution of Prophylaxis Protocols for Venous Thromboembolism in Neurosurgery: Results from a Prospective Comparative Study on Low-Molecular-Weight Heparin, Elastic Stockings, and Intermittent Pneumatic Compression Devices.神经外科静脉血栓栓塞预防方案的演变：一项关于低分子量肝素、弹力袜和间歇性气动压缩装置的前瞻性对比研究结果
World Neurosurg. 2018 Jan;109:e510-e516. doi: 10.1016/j.wneu.2017.10.012. Epub 2017 Oct 13.
9
Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review.机器学习与神经外科手术结果预测：系统综述。
World Neurosurg. 2018 Jan;109:476-486.e1. doi: 10.1016/j.wneu.2017.09.149. Epub 2017 Oct 3.
10
ROC Curve Analysis in the Presence of Imperfect Reference Standards.存在不完美参考标准时的ROC曲线分析。
Stat Biosci. 2017 Jun;9(1):91-104. doi: 10.1007/s12561-016-9159-7. Epub 2016 Jul 19.