The predictors of death within 1 year in acute ischemic stroke patients based on machine learning
ObjectiveTo explore the predictors of death in acute ischemic stroke (AIS) patients within 1 year based on machine learning (ML) algorithms.MethodsThis study retrospectively analyzed the clinical data of patients hospitalized and diagnosed with AIS in the Second Affiliated Hospital of Xuzhou Medical...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-02-01
|
Series: | Frontiers in Neurology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1092534/full |
_version_ | 1797896211192086528 |
---|---|
author | Kai Wang Kai Wang Longyuan Gu Wencai Liu Chan Xu Chengliang Yin Haiyan Liu Haiyan Liu Liangqun Rong Liangqun Rong Wenle Li Wenle Li Xiu'e Wei Xiu'e Wei |
author_facet | Kai Wang Kai Wang Longyuan Gu Wencai Liu Chan Xu Chengliang Yin Haiyan Liu Haiyan Liu Liangqun Rong Liangqun Rong Wenle Li Wenle Li Xiu'e Wei Xiu'e Wei |
author_sort | Kai Wang |
collection | DOAJ |
description | ObjectiveTo explore the predictors of death in acute ischemic stroke (AIS) patients within 1 year based on machine learning (ML) algorithms.MethodsThis study retrospectively analyzed the clinical data of patients hospitalized and diagnosed with AIS in the Second Affiliated Hospital of Xuzhou Medical University between August 2017 and July 2019. The patients were randomly divided into training and validation sets at a ratio of 7:3, and the clinical characteristic variables of the patients were screened using univariate and multivariate logistics regression. Six ML algorithms, including logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGB), random forest (RF), decision tree (DT), and naive Bayes classifier (NBC), were applied to develop models to predict death in AIS patients within 1 year. During training, a 10-fold cross-validation approach was used to validate the training set internally, and the models were interpreted using important ranking and the SHapley Additive exPlanations (SHAP) principle. The validation set was used to externally validate the models. Ultimately, the highest-performing model was selected to build a web-based calculator.ResultsMultivariate logistic regression analysis revealed that C-reactive protein (CRP), homocysteine (HCY) levels, stroke severity (SS), and the number of stroke lesions (NOS) were independent risk factors for death within 1 year in patients with AIS. The area under the curve value of the XGB model was 0.846, which was the highest among the six ML algorithms. Therefore, we built an ML network calculator (https://mlmedicine-de-stroke-de-stroke-m5pijk.streamlitapp.com/) based on XGB to predict death in AIS patients within 1 year.ConclusionsThe network calculator based on the XGB model developed in this study can help clinicians make more personalized and rational clinical decisions. |
first_indexed | 2024-04-10T07:39:08Z |
format | Article |
id | doaj.art-96f24d793e6049708330dfd69b182ff4 |
institution | Directory Open Access Journal |
issn | 1664-2295 |
language | English |
last_indexed | 2024-04-10T07:39:08Z |
publishDate | 2023-02-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neurology |
spelling | doaj.art-96f24d793e6049708330dfd69b182ff42023-02-23T12:14:50ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-02-011410.3389/fneur.2023.10925341092534The predictors of death within 1 year in acute ischemic stroke patients based on machine learningKai Wang0Kai Wang1Longyuan Gu2Wencai Liu3Chan Xu4Chengliang Yin5Haiyan Liu6Haiyan Liu7Liangqun Rong8Liangqun Rong9Wenle Li10Wenle Li11Xiu'e Wei12Xiu'e Wei13Department of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaKey Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Neurosurgery, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Orthopaedic Surgery, The First Affiliated Hospital of Nanchang University, Nanchang, ChinaDepartment of Dermatology, Xianyang Central Hospital, Xianyang, ChinaFaculty of Medicine, Macau University of Science and Technology, Taipa, Macao SAR, ChinaDepartment of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaKey Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaKey Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaKey Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaThe State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics and Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, ChinaDepartment of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaKey Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaObjectiveTo explore the predictors of death in acute ischemic stroke (AIS) patients within 1 year based on machine learning (ML) algorithms.MethodsThis study retrospectively analyzed the clinical data of patients hospitalized and diagnosed with AIS in the Second Affiliated Hospital of Xuzhou Medical University between August 2017 and July 2019. The patients were randomly divided into training and validation sets at a ratio of 7:3, and the clinical characteristic variables of the patients were screened using univariate and multivariate logistics regression. Six ML algorithms, including logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGB), random forest (RF), decision tree (DT), and naive Bayes classifier (NBC), were applied to develop models to predict death in AIS patients within 1 year. During training, a 10-fold cross-validation approach was used to validate the training set internally, and the models were interpreted using important ranking and the SHapley Additive exPlanations (SHAP) principle. The validation set was used to externally validate the models. Ultimately, the highest-performing model was selected to build a web-based calculator.ResultsMultivariate logistic regression analysis revealed that C-reactive protein (CRP), homocysteine (HCY) levels, stroke severity (SS), and the number of stroke lesions (NOS) were independent risk factors for death within 1 year in patients with AIS. The area under the curve value of the XGB model was 0.846, which was the highest among the six ML algorithms. Therefore, we built an ML network calculator (https://mlmedicine-de-stroke-de-stroke-m5pijk.streamlitapp.com/) based on XGB to predict death in AIS patients within 1 year.ConclusionsThe network calculator based on the XGB model developed in this study can help clinicians make more personalized and rational clinical decisions.https://www.frontiersin.org/articles/10.3389/fneur.2023.1092534/fullischemic strokebiomarkersmachine learningprediction modelweb calculator |
spellingShingle | Kai Wang Kai Wang Longyuan Gu Wencai Liu Chan Xu Chengliang Yin Haiyan Liu Haiyan Liu Liangqun Rong Liangqun Rong Wenle Li Wenle Li Xiu'e Wei Xiu'e Wei The predictors of death within 1 year in acute ischemic stroke patients based on machine learning Frontiers in Neurology ischemic stroke biomarkers machine learning prediction model web calculator |
title | The predictors of death within 1 year in acute ischemic stroke patients based on machine learning |
title_full | The predictors of death within 1 year in acute ischemic stroke patients based on machine learning |
title_fullStr | The predictors of death within 1 year in acute ischemic stroke patients based on machine learning |
title_full_unstemmed | The predictors of death within 1 year in acute ischemic stroke patients based on machine learning |
title_short | The predictors of death within 1 year in acute ischemic stroke patients based on machine learning |
title_sort | predictors of death within 1 year in acute ischemic stroke patients based on machine learning |
topic | ischemic stroke biomarkers machine learning prediction model web calculator |
url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1092534/full |
work_keys_str_mv | AT kaiwang thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT kaiwang thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT longyuangu thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT wencailiu thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT chanxu thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT chengliangyin thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT haiyanliu thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT haiyanliu thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT liangqunrong thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT liangqunrong thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT wenleli thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT wenleli thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT xiuewei thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT xiuewei thepredictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT kaiwang predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT kaiwang predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT longyuangu predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT wencailiu predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT chanxu predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT chengliangyin predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT haiyanliu predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT haiyanliu predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT liangqunrong predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT liangqunrong predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT wenleli predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT wenleli predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT xiuewei predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning AT xiuewei predictorsofdeathwithin1yearinacuteischemicstrokepatientsbasedonmachinelearning |