Prediction of in-hospital mortality risk in intensive care unit with support vector machine
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 (n=18 094) was randomly divided into training...
Main Authors: | , |
---|---|
Format: | Article |
Language: | zho |
Published: |
Editorial Office of Journal of Army Medical University
2022-09-01
|
Series: | 陆军军医大学学报 |
Subjects: | |
Online Access: | http://aammt.tmmu.edu.cn/Upload/rhtml/202206112.htm |
_version_ | 1811210684362391552 |
---|---|
author | DENG Peng CHEN Yuwen CHEN Yuwen CHEN Yuwen |
author_facet | DENG Peng CHEN Yuwen CHEN Yuwen CHEN Yuwen |
author_sort | DENG Peng |
collection | DOAJ |
description | 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 (n=18 094) was randomly divided into training data set (n=12 666, 70%) and test data set (n=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.
|
first_indexed | 2024-04-12T04:59:01Z |
format | Article |
id | doaj.art-32abe36d3f174ff09778b370ec992511 |
institution | Directory Open Access Journal |
issn | 2097-0927 |
language | zho |
last_indexed | 2024-04-12T04:59:01Z |
publishDate | 2022-09-01 |
publisher | Editorial Office of Journal of Army Medical University |
record_format | Article |
series | 陆军军医大学学报 |
spelling | doaj.art-32abe36d3f174ff09778b370ec9925112022-12-22T03:47:02ZzhoEditorial Office of Journal of Army Medical University陆军军医大学学报2097-09272022-09-0144171764176910.16016/j.2097-0927.202206112Prediction of in-hospital mortality risk in intensive care unit with support vector machineDENG Peng0CHEN Yuwen1CHEN Yuwen2CHEN Yuwen3Department of Anesthesiology, First Affiliated Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038 Department of Anesthesiology, First Affiliated Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, 400714Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, Sichuan Province, 610041, ChinaObjective 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 (n=18 094) was randomly divided into training data set (n=12 666, 70%) and test data set (n=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. http://aammt.tmmu.edu.cn/Upload/rhtml/202206112.htmsupport vector machineartificial intelligenceprediction modein-hospital mortality riskintensive care unit |
spellingShingle | DENG Peng CHEN Yuwen CHEN Yuwen CHEN Yuwen Prediction of in-hospital mortality risk in intensive care unit with support vector machine 陆军军医大学学报 support vector machine artificial intelligence prediction mode in-hospital mortality risk intensive care unit |
title | Prediction of in-hospital mortality risk in intensive care unit with support vector machine |
title_full | Prediction of in-hospital mortality risk in intensive care unit with support vector machine |
title_fullStr | Prediction of in-hospital mortality risk in intensive care unit with support vector machine |
title_full_unstemmed | Prediction of in-hospital mortality risk in intensive care unit with support vector machine |
title_short | Prediction of in-hospital mortality risk in intensive care unit with support vector machine |
title_sort | prediction of in hospital mortality risk in intensive care unit with support vector machine |
topic | support vector machine artificial intelligence prediction mode in-hospital mortality risk intensive care unit |
url | http://aammt.tmmu.edu.cn/Upload/rhtml/202206112.htm |
work_keys_str_mv | AT dengpeng predictionofinhospitalmortalityriskinintensivecareunitwithsupportvectormachine AT chenyuwen predictionofinhospitalmortalityriskinintensivecareunitwithsupportvectormachine AT chenyuwen predictionofinhospitalmortalityriskinintensivecareunitwithsupportvectormachine AT chenyuwen predictionofinhospitalmortalityriskinintensivecareunitwithsupportvectormachine |