A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm
Abstract Background The incidence of stroke is a challenge in China, as stroke imposes a heavy burden on families, national health services, social services, and the economy. The length of hospital stay (LOS) is an essential indicator of utilization of medical services and is usually used to assess...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-03-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-023-02140-4 |
| _version_ | 1797859869025370112 |
|---|---|
| author | Rui Chen Shengfa Zhang Jie Li Dongwei Guo Weijun Zhang Xiaoying Wang Donghua Tian Zhiyong Qu Xiaohua Wang |
| author_facet | Rui Chen Shengfa Zhang Jie Li Dongwei Guo Weijun Zhang Xiaoying Wang Donghua Tian Zhiyong Qu Xiaohua Wang |
| author_sort | Rui Chen |
| collection | DOAJ |
| description | Abstract Background The incidence of stroke is a challenge in China, as stroke imposes a heavy burden on families, national health services, social services, and the economy. The length of hospital stay (LOS) is an essential indicator of utilization of medical services and is usually used to assess the efficiency of hospital management and patient quality of care. This study established a prediction model based on a machine learning algorithm to predict ischemic stroke patients’ LOS. Methods A total of 18,195 ischemic stroke patients’ electronic medical records and 28 attributes were extracted from electronic medical records in a large comprehensive hospital in China. The prediction of LOS was regarded as a multi classification problem, and LOS was divided into three categories: 1–7 days, 8–14 days and more than 14 days. After preprocessing the data and feature selection, the XGBoost algorithm was used to build a machine learning model. Ten fold cross-validation was used for model validation. The accuracy (ACC), recall rate (RE) and F1 measure were used to evaluate the performance of the prediction model of LOS of ischemic stroke patients. Finally, the XGBoost algorithm was used to identify and remove irrelevant features by ranking all attributes based on feature importance. Results Compared with the naive Bayesian algorithm, logistic region algorithm, decision tree classifier algorithm and ADaBoost classifier algorithm, the XGBoot algorithm has higher ACC, RE and F1 measure. The average ACC, RE and F1 measure were 0.89, 0.89 and 0.89 under the 10-fold cross-validation. According to the analysis of the importance of features, the LOS of ischemic stroke patients was affected by demographic characteristics, past medical history, admission examination features, and operation characteristics. Finally, the features in terms of hemiplegia aphasia, MRS, NIHSS, TIA, Operation or not, coma index etc. were found to be the top features in importance in predicting the LOS of ischemic stroke patients. Conclusions The XGBoost algorithm was an appropriate machine learning method for predicting the LOS of patients with ischemic stroke. Based on the prediction model, an intelligent medical management prediction system could be developed to predict the LOS based on ischemic stroke patients’ electronic medical records. |
| first_indexed | 2024-04-09T21:37:38Z |
| format | Article |
| id | doaj.art-2626f61a05b14d82ad702f33b3ffabba |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-04-09T21:37:38Z |
| publishDate | 2023-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-2626f61a05b14d82ad702f33b3ffabba2023-03-26T11:12:33ZengBMCBMC Medical Informatics and Decision Making1472-69472023-03-0123111010.1186/s12911-023-02140-4A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithmRui Chen0Shengfa Zhang1Jie Li2Dongwei Guo3Weijun Zhang4Xiaoying Wang5Donghua Tian6Zhiyong Qu7Xiaohua Wang8Refined Management Office, Cangzhou Central HospitalNational Population Heath Data Center, Chinese Academy of Medical Sciences and Peking Union Medical CollegeSchool of Economics and Management, Hebei University of TechnologySchool of Economics and Management, Hebei University of TechnologySchool of Social Development and Public Policy, Beijing Normal UniversitySchool of Social Development and Public Policy, Beijing Normal UniversitySchool of Social Development and Public Policy, Beijing Normal UniversitySchool of Social Development and Public Policy, Beijing Normal UniversitySchool of Social Development and Public Policy, Beijing Normal UniversityAbstract Background The incidence of stroke is a challenge in China, as stroke imposes a heavy burden on families, national health services, social services, and the economy. The length of hospital stay (LOS) is an essential indicator of utilization of medical services and is usually used to assess the efficiency of hospital management and patient quality of care. This study established a prediction model based on a machine learning algorithm to predict ischemic stroke patients’ LOS. Methods A total of 18,195 ischemic stroke patients’ electronic medical records and 28 attributes were extracted from electronic medical records in a large comprehensive hospital in China. The prediction of LOS was regarded as a multi classification problem, and LOS was divided into three categories: 1–7 days, 8–14 days and more than 14 days. After preprocessing the data and feature selection, the XGBoost algorithm was used to build a machine learning model. Ten fold cross-validation was used for model validation. The accuracy (ACC), recall rate (RE) and F1 measure were used to evaluate the performance of the prediction model of LOS of ischemic stroke patients. Finally, the XGBoost algorithm was used to identify and remove irrelevant features by ranking all attributes based on feature importance. Results Compared with the naive Bayesian algorithm, logistic region algorithm, decision tree classifier algorithm and ADaBoost classifier algorithm, the XGBoot algorithm has higher ACC, RE and F1 measure. The average ACC, RE and F1 measure were 0.89, 0.89 and 0.89 under the 10-fold cross-validation. According to the analysis of the importance of features, the LOS of ischemic stroke patients was affected by demographic characteristics, past medical history, admission examination features, and operation characteristics. Finally, the features in terms of hemiplegia aphasia, MRS, NIHSS, TIA, Operation or not, coma index etc. were found to be the top features in importance in predicting the LOS of ischemic stroke patients. Conclusions The XGBoost algorithm was an appropriate machine learning method for predicting the LOS of patients with ischemic stroke. Based on the prediction model, an intelligent medical management prediction system could be developed to predict the LOS based on ischemic stroke patients’ electronic medical records.https://doi.org/10.1186/s12911-023-02140-4Ischemic strokeXGBoost algorithmLength of hospital stay (LOS)Machine learning (ML) model |
| spellingShingle | Rui Chen Shengfa Zhang Jie Li Dongwei Guo Weijun Zhang Xiaoying Wang Donghua Tian Zhiyong Qu Xiaohua Wang A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm BMC Medical Informatics and Decision Making Ischemic stroke XGBoost algorithm Length of hospital stay (LOS) Machine learning (ML) model |
| title | A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm |
| title_full | A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm |
| title_fullStr | A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm |
| title_full_unstemmed | A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm |
| title_short | A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm |
| title_sort | study on predicting the length of hospital stay for chinese patients with ischemic stroke based on the xgboost algorithm |
| topic | Ischemic stroke XGBoost algorithm Length of hospital stay (LOS) Machine learning (ML) model |
| url | https://doi.org/10.1186/s12911-023-02140-4 |
| work_keys_str_mv | AT ruichen astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT shengfazhang astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT jieli astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT dongweiguo astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT weijunzhang astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT xiaoyingwang astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT donghuatian astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT zhiyongqu astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT xiaohuawang astudyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT ruichen studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT shengfazhang studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT jieli studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT dongweiguo studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT weijunzhang studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT xiaoyingwang studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT donghuatian studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT zhiyongqu studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm AT xiaohuawang studyonpredictingthelengthofhospitalstayforchinesepatientswithischemicstrokebasedonthexgboostalgorithm |