Predicting new-onset stroke with machine learning: development of a model integrating traditional Chinese and western medicine

IntroductionThe integration of traditional Chinese medicine (TCM) and Western medicine has demonstrated effectiveness in the primary prevention of stroke. Therefore, our study aims to utilize TCM syndromes alongside conventional risk factors as predictive variables to construct a machine learning mo...

Full description

Saved in:
Bibliographic Details
Main Authors: Liuding Wang, Jingzi Shi, Lina Miao, Yifan Chen, Jingjing Wei, Min Jia, Zhiyi Gong, Ze Yang, Jian Lyu, Yunling Zhang, Xiao Liang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-02-01
Series:Frontiers in Pharmacology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphar.2025.1546878/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850024028205481984
author Liuding Wang
Jingzi Shi
Lina Miao
Yifan Chen
Jingjing Wei
Min Jia
Zhiyi Gong
Ze Yang
Jian Lyu
Jian Lyu
Jian Lyu
Yunling Zhang
Xiao Liang
author_facet Liuding Wang
Jingzi Shi
Lina Miao
Yifan Chen
Jingjing Wei
Min Jia
Zhiyi Gong
Ze Yang
Jian Lyu
Jian Lyu
Jian Lyu
Yunling Zhang
Xiao Liang
author_sort Liuding Wang
collection DOAJ
description IntroductionThe integration of traditional Chinese medicine (TCM) and Western medicine has demonstrated effectiveness in the primary prevention of stroke. Therefore, our study aims to utilize TCM syndromes alongside conventional risk factors as predictive variables to construct a machine learning model for assessing the risk of new-onset stroke.MethodsWe conducted a ten-year follow-up study encompassing 4,511 participants from multiple Chinese community hospitals. The dependent variable was the occurrence of the new-onset stroke, while independent variables included age, gender, systolic blood pressure (SBP), diabetes, blood lipids, carotid atherosclerosis, smoking status, and TCM syndromes. We developed the models using XGBoost in conjunction with SHapley Additive exPlanations (SHAP) for interpretability, and logistic regression with a nomogram for clinical application.ResultsA total of 1,783 individuals were included (1,248 in the training set and 535 in the validation set), with 110 patients diagnosed with new-onset stroke. The logistic model demonstrated an AUC of 0.746 (95% CI: 0.719–0.774) in the training set and 0.658 (95% CI: 0.572–0.745) in the validation set. The XGBoost model achieved a training set AUC of 0.811 (95% CI: 0.788–0.834) and a validation set AUC of 0.628 (95% CI: 0.537–0.719). SHAP analysis showed that elevated SBP, Fire syndrome in TCM, and carotid atherosclerosis were the three most important features for predicting the new-onset stroke.ConclusionUnder identical traditional risk factors, Chinese residents with Fire syndrome may have a higher risk of new-onset stroke. In high-risk populations for stroke, it is recommended to prioritize the screening and management of hypertension, Fire syndrome, and carotid atherosclerosis. However, future high-performance TCM predictive models require more objective and larger datasets for optimization.
format Article
id doaj-art-115fa93b0ac44798a906a9be8c3ece5c
institution DOAJ
issn 1663-9812
language English
publishDate 2025-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Pharmacology
spelling doaj-art-115fa93b0ac44798a906a9be8c3ece5c2025-08-20T03:01:14ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122025-02-011610.3389/fphar.2025.15468781546878Predicting new-onset stroke with machine learning: development of a model integrating traditional Chinese and western medicineLiuding Wang0Jingzi Shi1Lina Miao2Yifan Chen3Jingjing Wei4Min Jia5Zhiyi Gong6Ze Yang7Jian Lyu8Jian Lyu9Jian Lyu10Yunling Zhang11Xiao Liang12Departmalet of Neurology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaGraduate School, Beijing University of Chinese Medicine, Beijing, ChinaDepartmalet of Neurology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaDepartmalet of Cardiology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaDepartmalet of Neurology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaMedical Ethics Committee, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaShandong University of Traditional Chinese Medicine, Jinan, ChinaDepartmalet of Neurology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaDepartmalet of Neurology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaNMPA Key Laboratory for Clinical Research and Evaluation of Traditional Chinese Medicine, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaNational Clinical Research Center for Chinese Medicine Cardiology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaDepartmalet of Neurology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaDepartmalet of Neurology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, ChinaIntroductionThe integration of traditional Chinese medicine (TCM) and Western medicine has demonstrated effectiveness in the primary prevention of stroke. Therefore, our study aims to utilize TCM syndromes alongside conventional risk factors as predictive variables to construct a machine learning model for assessing the risk of new-onset stroke.MethodsWe conducted a ten-year follow-up study encompassing 4,511 participants from multiple Chinese community hospitals. The dependent variable was the occurrence of the new-onset stroke, while independent variables included age, gender, systolic blood pressure (SBP), diabetes, blood lipids, carotid atherosclerosis, smoking status, and TCM syndromes. We developed the models using XGBoost in conjunction with SHapley Additive exPlanations (SHAP) for interpretability, and logistic regression with a nomogram for clinical application.ResultsA total of 1,783 individuals were included (1,248 in the training set and 535 in the validation set), with 110 patients diagnosed with new-onset stroke. The logistic model demonstrated an AUC of 0.746 (95% CI: 0.719–0.774) in the training set and 0.658 (95% CI: 0.572–0.745) in the validation set. The XGBoost model achieved a training set AUC of 0.811 (95% CI: 0.788–0.834) and a validation set AUC of 0.628 (95% CI: 0.537–0.719). SHAP analysis showed that elevated SBP, Fire syndrome in TCM, and carotid atherosclerosis were the three most important features for predicting the new-onset stroke.ConclusionUnder identical traditional risk factors, Chinese residents with Fire syndrome may have a higher risk of new-onset stroke. In high-risk populations for stroke, it is recommended to prioritize the screening and management of hypertension, Fire syndrome, and carotid atherosclerosis. However, future high-performance TCM predictive models require more objective and larger datasets for optimization.https://www.frontiersin.org/articles/10.3389/fphar.2025.1546878/fullartificial intelligencecombination of disease and syndromeprevention strategypopulations at high risk of stroketraditional medicine
spellingShingle Liuding Wang
Jingzi Shi
Lina Miao
Yifan Chen
Jingjing Wei
Min Jia
Zhiyi Gong
Ze Yang
Jian Lyu
Jian Lyu
Jian Lyu
Yunling Zhang
Xiao Liang
Predicting new-onset stroke with machine learning: development of a model integrating traditional Chinese and western medicine
Frontiers in Pharmacology
artificial intelligence
combination of disease and syndrome
prevention strategy
populations at high risk of stroke
traditional medicine
title Predicting new-onset stroke with machine learning: development of a model integrating traditional Chinese and western medicine
title_full Predicting new-onset stroke with machine learning: development of a model integrating traditional Chinese and western medicine
title_fullStr Predicting new-onset stroke with machine learning: development of a model integrating traditional Chinese and western medicine
title_full_unstemmed Predicting new-onset stroke with machine learning: development of a model integrating traditional Chinese and western medicine
title_short Predicting new-onset stroke with machine learning: development of a model integrating traditional Chinese and western medicine
title_sort predicting new onset stroke with machine learning development of a model integrating traditional chinese and western medicine
topic artificial intelligence
combination of disease and syndrome
prevention strategy
populations at high risk of stroke
traditional medicine
url https://www.frontiersin.org/articles/10.3389/fphar.2025.1546878/full
work_keys_str_mv AT liudingwang predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT jingzishi predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT linamiao predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT yifanchen predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT jingjingwei predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT minjia predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT zhiyigong predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT zeyang predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT jianlyu predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT jianlyu predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT jianlyu predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT yunlingzhang predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine
AT xiaoliang predictingnewonsetstrokewithmachinelearningdevelopmentofamodelintegratingtraditionalchineseandwesternmedicine