Machine learning algorithms to predict stroke in China based on causal inference of time series analysis
Abstract Importance Identifying and managing high-risk populations for stroke in a targeted manner is a key area of preventive healthcare. Objective To assess machine learning (ML) models and causal inference of time series analysis for predicting stroke clinically meaningful model. Design This is a...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | BMC Neurology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12883-025-04261-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849704719366225920 |
|---|---|
| author | Qizhi Zheng Ayang Zhao Xinzhu Wang Yanhong Bai Zikun Wang Xiuying Wang Xianzhang Zeng Guanghui Dong |
| author_facet | Qizhi Zheng Ayang Zhao Xinzhu Wang Yanhong Bai Zikun Wang Xiuying Wang Xianzhang Zeng Guanghui Dong |
| author_sort | Qizhi Zheng |
| collection | DOAJ |
| description | Abstract Importance Identifying and managing high-risk populations for stroke in a targeted manner is a key area of preventive healthcare. Objective To assess machine learning (ML) models and causal inference of time series analysis for predicting stroke clinically meaningful model. Design This is a retrospective cohort study and data is from China Health and Retirement Longitudinal Study (CHARLS) assessed 11,789 adults in China from 2011 to 2018. Data analysis was performed from June 1 to December 1, 2024. Setting CHARLS adopts a multi-stage probability sampling method, covering samples from 28 provinces, and collects data every two years through computer-aided personal interviews (CAPI). Participants This study employed a combination of Vector Autoregression (VAR) model and Graph Neural Networks (GNN) to systematically construct dynamic causal inference. Multiple classic classification algorithms were compared, including Random Forest, Logistic Regression, XGBoost, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Gradient Boosting, and Multi-Layer Perceptron (MLP). The Synthetic Minority Oversampling Technique (SMOTE) algorithm was used to undersample a small number of samples and employed Stratified K-fold Cross Validation. Main Outcome(s) and Measure(s) AUC (Area Under the Curve), Accuracy, Precision, Recall, F1 Score, and Matthews Correlation Coefficient (MCC). Results This study included a total of 11,789 participants, including 6,334 females (53.73%) and 5,455 males (46.27%), with an average age of 65 years. Introduction of dynamic causal inference features has significantly improved the performance of almost all models. The area under the ROC curve of each model ranged from 0.78 to 0.83, indicating significant difference (P < 0.01). Among all the models, the Gradient Boosting model demonstrated the highest performance and stability. Model explanation and feature importance analysis generated model interpretation that illustrated significant contributors associated with risks of stroke. Conclusions and Relevance This study proposes a stroke risk prediction method that combines dynamic causal inference with machine learning models, significantly improving prediction accuracy and revealing key health factors that affect stroke. The research results indicate that dynamic causal inference features have important value in predicting stroke risk, especially in capturing the impact of changes in health status over time on stroke risk. By further optimizing the model and introducing more variables, this study provides theoretical basis and practical guidance for future stroke prevention and intervention strategies. Trial registration IRB00001052-11015.1.2. |
| format | Article |
| id | doaj-art-fa6cf6059af14d1a89daab6b0e7fcdf2 |
| institution | DOAJ |
| issn | 1471-2377 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Neurology |
| spelling | doaj-art-fa6cf6059af14d1a89daab6b0e7fcdf22025-08-20T03:16:40ZengBMCBMC Neurology1471-23772025-05-0125111210.1186/s12883-025-04261-xMachine learning algorithms to predict stroke in China based on causal inference of time series analysisQizhi Zheng0Ayang Zhao1Xinzhu Wang2Yanhong Bai3Zikun Wang4Xiuying Wang5Xianzhang Zeng6Guanghui Dong7College of Computer and Control Engineering, Northeast Forestry UniversitySchool of Medicine and Health, Key Laboratory of Micro-systems and Micro-structures Manufacturing (Ministry of Education), Harbin Institute of TechnologyCollege of Computer and Control Engineering, Northeast Forestry UniversityCollege of Computer and Control Engineering, Northeast Forestry UniversityCollege of Computer and Control Engineering, Northeast Forestry UniversityCollege of Computer and Control Engineering, Northeast Forestry UniversityDepartment of Anesthesiology, Chongqing University Cancer HospitalCollege of Computer and Control Engineering, Northeast Forestry UniversityAbstract Importance Identifying and managing high-risk populations for stroke in a targeted manner is a key area of preventive healthcare. Objective To assess machine learning (ML) models and causal inference of time series analysis for predicting stroke clinically meaningful model. Design This is a retrospective cohort study and data is from China Health and Retirement Longitudinal Study (CHARLS) assessed 11,789 adults in China from 2011 to 2018. Data analysis was performed from June 1 to December 1, 2024. Setting CHARLS adopts a multi-stage probability sampling method, covering samples from 28 provinces, and collects data every two years through computer-aided personal interviews (CAPI). Participants This study employed a combination of Vector Autoregression (VAR) model and Graph Neural Networks (GNN) to systematically construct dynamic causal inference. Multiple classic classification algorithms were compared, including Random Forest, Logistic Regression, XGBoost, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Gradient Boosting, and Multi-Layer Perceptron (MLP). The Synthetic Minority Oversampling Technique (SMOTE) algorithm was used to undersample a small number of samples and employed Stratified K-fold Cross Validation. Main Outcome(s) and Measure(s) AUC (Area Under the Curve), Accuracy, Precision, Recall, F1 Score, and Matthews Correlation Coefficient (MCC). Results This study included a total of 11,789 participants, including 6,334 females (53.73%) and 5,455 males (46.27%), with an average age of 65 years. Introduction of dynamic causal inference features has significantly improved the performance of almost all models. The area under the ROC curve of each model ranged from 0.78 to 0.83, indicating significant difference (P < 0.01). Among all the models, the Gradient Boosting model demonstrated the highest performance and stability. Model explanation and feature importance analysis generated model interpretation that illustrated significant contributors associated with risks of stroke. Conclusions and Relevance This study proposes a stroke risk prediction method that combines dynamic causal inference with machine learning models, significantly improving prediction accuracy and revealing key health factors that affect stroke. The research results indicate that dynamic causal inference features have important value in predicting stroke risk, especially in capturing the impact of changes in health status over time on stroke risk. By further optimizing the model and introducing more variables, this study provides theoretical basis and practical guidance for future stroke prevention and intervention strategies. Trial registration IRB00001052-11015.1.2.https://doi.org/10.1186/s12883-025-04261-xMachine learningDynamic causal inferenceStroke risk predictionGradient boosting |
| spellingShingle | Qizhi Zheng Ayang Zhao Xinzhu Wang Yanhong Bai Zikun Wang Xiuying Wang Xianzhang Zeng Guanghui Dong Machine learning algorithms to predict stroke in China based on causal inference of time series analysis BMC Neurology Machine learning Dynamic causal inference Stroke risk prediction Gradient boosting |
| title | Machine learning algorithms to predict stroke in China based on causal inference of time series analysis |
| title_full | Machine learning algorithms to predict stroke in China based on causal inference of time series analysis |
| title_fullStr | Machine learning algorithms to predict stroke in China based on causal inference of time series analysis |
| title_full_unstemmed | Machine learning algorithms to predict stroke in China based on causal inference of time series analysis |
| title_short | Machine learning algorithms to predict stroke in China based on causal inference of time series analysis |
| title_sort | machine learning algorithms to predict stroke in china based on causal inference of time series analysis |
| topic | Machine learning Dynamic causal inference Stroke risk prediction Gradient boosting |
| url | https://doi.org/10.1186/s12883-025-04261-x |
| work_keys_str_mv | AT qizhizheng machinelearningalgorithmstopredictstrokeinchinabasedoncausalinferenceoftimeseriesanalysis AT ayangzhao machinelearningalgorithmstopredictstrokeinchinabasedoncausalinferenceoftimeseriesanalysis AT xinzhuwang machinelearningalgorithmstopredictstrokeinchinabasedoncausalinferenceoftimeseriesanalysis AT yanhongbai machinelearningalgorithmstopredictstrokeinchinabasedoncausalinferenceoftimeseriesanalysis AT zikunwang machinelearningalgorithmstopredictstrokeinchinabasedoncausalinferenceoftimeseriesanalysis AT xiuyingwang machinelearningalgorithmstopredictstrokeinchinabasedoncausalinferenceoftimeseriesanalysis AT xianzhangzeng machinelearningalgorithmstopredictstrokeinchinabasedoncausalinferenceoftimeseriesanalysis AT guanghuidong machinelearningalgorithmstopredictstrokeinchinabasedoncausalinferenceoftimeseriesanalysis |