利用支持向量机预测重症监护室患者死亡风险的研究

邓鹏; 陈芋文; 李雨捷; 杨智勇; 钟坤华; 张矩; 鲁开智; 易斌

doi:10.16016/j.2097-0927.202206112

您当前的位置：

首页 >

文章列表页 >

利用支持向量机预测重症监护室患者死亡风险的研究

临床医学 | 更新时间：2026-01-09

- 利用支持向量机预测重症监护室患者死亡风险的研究
- Prediction of in-hospital mortality risk in intensive care unit with support vector machine
- 陆军军医大学学报 2022年44卷第17期页码：1764-1769
- 作者机构：
  
  1.400038 重庆，陆军军医大学(第三军医大学)第一附属医院麻醉科
  2.400714 重庆，中国科学院重庆绿色智能技术研究院
  3.610041 成都，中国科学院成都计算机应用研究所
- 作者简介：
  
  [易斌，E-mail: yibin1974@163.comYI Bin, E-mail: yibin1974@163.com
- 基金信息：
  
  国家自然科学基金(81870422);国家重点研发计划(2018YFC0116702)
- DOI：10.16016/j.2097-0927.202206112
  中图分类号： R195.1;R319;R459.9
- 收稿：2022-06-18，
  
  修回：2022-08-02，
  
  纸质出版：2022-09-15
- 稿件说明：
移动端阅览
邓鹏, 陈芋文, 李雨捷, 等. 利用支持向量机预测重症监护室患者死亡风险的研究[J]. 陆军军医大学学报, 2022,44(17):1764-1769.

Peng DENG, Yuwen CHEN, Yujie LI, et al. Prediction of in-hospital mortality risk in intensive care unit with support vector machine[J]. Journal of Army Medical University, 2022, 44(17): 1764-1769.
邓鹏, 陈芋文, 李雨捷, 等. 利用支持向量机预测重症监护室患者死亡风险的研究[J]. 陆军军医大学学报, 2022,44(17):1764-1769. DOI： 10.16016/j.2097-0927.202206112.

Peng DENG, Yuwen CHEN, Yujie LI, et al. Prediction of in-hospital mortality risk in intensive care unit with support vector machine[J]. Journal of Army Medical University, 2022, 44(17): 1764-1769. DOI： 10.16016/j.2097-0927.202206112.

摘要

目的

探讨支持向量机(Support Vector Machine，SVM)方法在预测重症监护室(ICU)患者入院后死亡率方面的应用。

方法

纳入MIMIC Ⅲ数据库18 094例ICU住院患者，将总数据集(

=18 094)随机分为训练集(

=12 666，70%)和测试集(

=5 428，30%)。基于Python平台，采用支持向量机(SVM)学习算法，利用LASSO特征选择结果，建立预测重症监护室患者入院后死亡率的模型。并使用测试集进行模型评估。

结果

基于SVM算法构建ICU患者入院后24 h和48 h死亡率预测模型的AUC分别为0.805 1(0.793 6-0.816 6)和0.811 7(0.799 9-0.824)，敏感性分别为0.751 3和0.737 2，特异性分别为0.713 0和0.742 9。

结论

基于支持向量机算法建立的预测重症监护室患者死亡率模型预测效果较好，具有较高准确率。

Abstract

Objective

To explore the application of support vector machine (SVM) in predicting the mortality risk after intensive care unit (ICU) admission.

Methods

A total of 18 094 ICU inpatients from MIMIC Ⅲ dataset were enrolled in the study. The total data set (

=18 094) was randomly divided into training data set (

=12 666

70%) and test data set (

=5 428

30%). Based on the Python

the machine learning algorithm

SVM

was used to establish a prediction model of the mortality risk after ICU admission with the results of LASSO feature selection. The efficacy of model was evaluated using the test data set.

Results

The areas under the receiver operating characteristic (AUCROC) curves of the SVM-based model for predicting the mortality risk in 24 h and 48 h after ICU admission were 0.805 1 (0.793 6~0.816 6) and 0.811 7 (0.799 9~0.824)

with sensitivities of 0.751 3 and 0.737 2

and specificities of 0.713 0 and 0.742 9

respectively.

Conclusion

The SVM-based model for predicting the mortality risk after ICU admission has a satisfactory result and high accuracy.

关键词

Keywords

references

WEIGL W, ADAMSKI J, GORYNSKI P, et al . ICU mortality and variables associated with ICU survival in Poland: a nationwide database study[J ] . Eur J Anaesthesiol, 2018, 35(12): 949-954. DOI: 10.1097/EJA.0000000000000889.

WEIGL W, ADAMSKI J, GORYNSKI P, et al . Mortality rate is higher in Polish intensive care units than in other European countries[J ] . Intens Care Med, 2017, 43(9): 1430-1432. DOI: 10.1007/s00134-017-4804-2.

TOPOL E J. High-performance medicine: the convergence of human and artificial intelligence[J]. Nat Med, 2019, 25(1): 44-56. DOI: 10.1038/s41591-018-0300-7.

RAVIZZA S, HUSCHTO T, ADAMOV A, et al . Predicting the early risk of chronic kidney disease in patients with diabetes using real-world data[J ] . Nat Med, 2019, 25(1): 57-59. DOI: 10.1038/s41591-018-0239-8.

HE J X, BAXTER S L, XU J, et al . The practical implementation of artificial intelligence technologies in medicine[J ] . Nat Med, 2019, 25(1): 30-36. DOI: 10.1038/s41591-018-0307-0.

ESTEVA A, ROBICQUET A, RAMSUNDAR B, et al . A guide to deep learning in healthcare[J ] . Nat Med, 2019, 25(1): 24-29. DOI: 10.1038/s41591-018-0316-z.

JOHNSON A E W, POLLARD T J, SHEN L, et al . MIMIC-Ⅲ, a freely accessible critical care database[J ] . Sci Data, 2016, 3: 160035. DOI: 10.1038/sdata.2016.35.

BENKE K, BENKE G. Artificial intelligence and big data in public health[J]. Int J Environ Res Public Health, 2018, 15(12): E2796. DOI: 10.3390/ijerph15122796.

蔺轲, 谢俊卿, 胡永华, 等. 支持向量机在ICU急性肾损伤患者住院死亡风险预测中的应用[J]. 北京大学学报(医学版), 2018, 50(2): 239-244. DOI: 10.3969/j.issn.1671-167X.2018.02.007.

LIN K, XIE J Q, HU Y H, et al . Application of support vector machine in predicting in-hospital mortality risk of patients with acute kidney injury in ICU[J ] . J Peking Univ Heal Sci, 2018, 50(2): 239-244. DOI: 10.3969/j.issn.1671-167X.2018.02.007.

YU R X, ZHENG Y L, ZHANG R K, et al . Using a multi-task recurrent neural network with attention mechanisms to predict hospital mortality of patients[J ] . IEEE J Biomed Health Inform, 2020, 24(2): 4 86-492. DOI: 10.1109/JBHI.2019.2916667.

陈进. 中医的数学建模[J]. 数理医药学杂志, 2002, 15(6): 489-491.

CHEN J. Mathematical modeling of traditional Chinese medicine[J]. J Math Med, 2002, 15(6): 489-491.

许明东, 马晓聪, 温宗良, 等. 支持向量机在高血压病中医证候诊断中的应用[J]. 中华中医药杂志, 2017, 32(6): 2497-2500.

XU M D, MA X C, WEN Z L, et al . Application of support vector machine in the diagnosis of hypertension in TCM syndrome[J ] . China J Tradit Chin Med Pharm, 2017, 32(6): 2497-2500.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于胸部CT图像的肺炎深度学习分类预测模型

双源CT虚拟平扫技术联合人工智能在急性颅内出血诊断中的应用价值

ICU住院期间体质量变化与死亡率的相关性研究

基于贝叶斯网络算法建立全膝关节置换术后认知功能障碍风险预测模型

围手术期大数据的应用与展望