Machine learning-based prediction model for post-stroke cerebral-cardiac syndrome: a risk stratification study

Abstract Background Cerebral-cardiac syndrome (CCS) is a severe cardiac complication following acute ischemic stroke, often associated with adverse outcomes. This study developed and validated a machine learning (ML) model to predict CCS using clinical, laboratory, and pre-extracted imaging features...

Full description

Saved in:
Bibliographic Details
Main Authors: Tingyu Zhang, Zelin Hao, Qunlian Jiang, Linhui Zhu, Lifang Ye
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10104-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226360347688960
author Tingyu Zhang
Zelin Hao
Qunlian Jiang
Linhui Zhu
Lifang Ye
author_facet Tingyu Zhang
Zelin Hao
Qunlian Jiang
Linhui Zhu
Lifang Ye
author_sort Tingyu Zhang
collection DOAJ
description Abstract Background Cerebral-cardiac syndrome (CCS) is a severe cardiac complication following acute ischemic stroke, often associated with adverse outcomes. This study developed and validated a machine learning (ML) model to predict CCS using clinical, laboratory, and pre-extracted imaging features. A retrospective cohort of 511 post-stroke patients was analyzed. Data on demographics, laboratory results, imaging findings, and medications were collected. CCS diagnosis was based on cardiac dysfunction occurring after stroke, excluding pre-existing cardiac diseases. Five machine learning models, including Logistic Regression, Random Forest, Support Vector Machine (SVM), XGBoost, and Deep Neural Network, were trained on 80% of the data and tested on the remaining 20%. Discrimination was assessed by AUC (95% CI), calibration by Hosmer–Lemeshow test and Brier score, and thresholds by Youden’s index. Model interpretability was evaluated using SHAP. On the test set, XGBoost achieved the highest discrimination (AUC 0.879; 95% CI 0.807–0.942), accuracy 0.825, precision 0.844, recall 0.675, and F1 score 0.750. Random forest followed closely (AUC 0.866; accuracy 0.845; precision 0.962; recall 0.625; F1 0.758). SVM and logistic regression yielded AUCs of 0.853 and 0.818, respectively. Calibration was optimal for SVM (HL p > 0.05; Brier 0.126) and random forest (HL p > 0.05; Brier 0.131). SHAP analysis identified D-dimer, ACEI/ARB use, HbA1c, C-reactive protein, and prothrombin time as top predictors. ML-based models accurately predict early CCS in ischemic stroke patients. XGBoost offers superior discrimination, while SVM and random forest demonstrate better calibration. Incorporation of these models into clinical workflows may enhance risk stratification and guide targeted preventive strategies.
format Article
id doaj-art-7bcaa051229d4d6f8765abfdcd91aac2
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7bcaa051229d4d6f8765abfdcd91aac22025-08-24T11:24:06ZengNature PortfolioScientific Reports2045-23222025-08-0115111010.1038/s41598-025-10104-zMachine learning-based prediction model for post-stroke cerebral-cardiac syndrome: a risk stratification studyTingyu Zhang0Zelin Hao1Qunlian Jiang2Linhui Zhu3Lifang Ye4Department of Neurosurgery, The Affiliated Hospital of Hangzhou Normal UniversityDepartment of Neurosurgery, The Affiliated Hospital of Hangzhou Normal UniversityDepartment of Neurosurgery, The Affiliated Hospital of Hangzhou Normal UniversityDepartment of Neurosurgery, The Affiliated Hospital of Hangzhou Normal UniversityHeart Center, Department of Cardiovascular Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College)Abstract Background Cerebral-cardiac syndrome (CCS) is a severe cardiac complication following acute ischemic stroke, often associated with adverse outcomes. This study developed and validated a machine learning (ML) model to predict CCS using clinical, laboratory, and pre-extracted imaging features. A retrospective cohort of 511 post-stroke patients was analyzed. Data on demographics, laboratory results, imaging findings, and medications were collected. CCS diagnosis was based on cardiac dysfunction occurring after stroke, excluding pre-existing cardiac diseases. Five machine learning models, including Logistic Regression, Random Forest, Support Vector Machine (SVM), XGBoost, and Deep Neural Network, were trained on 80% of the data and tested on the remaining 20%. Discrimination was assessed by AUC (95% CI), calibration by Hosmer–Lemeshow test and Brier score, and thresholds by Youden’s index. Model interpretability was evaluated using SHAP. On the test set, XGBoost achieved the highest discrimination (AUC 0.879; 95% CI 0.807–0.942), accuracy 0.825, precision 0.844, recall 0.675, and F1 score 0.750. Random forest followed closely (AUC 0.866; accuracy 0.845; precision 0.962; recall 0.625; F1 0.758). SVM and logistic regression yielded AUCs of 0.853 and 0.818, respectively. Calibration was optimal for SVM (HL p > 0.05; Brier 0.126) and random forest (HL p > 0.05; Brier 0.131). SHAP analysis identified D-dimer, ACEI/ARB use, HbA1c, C-reactive protein, and prothrombin time as top predictors. ML-based models accurately predict early CCS in ischemic stroke patients. XGBoost offers superior discrimination, while SVM and random forest demonstrate better calibration. Incorporation of these models into clinical workflows may enhance risk stratification and guide targeted preventive strategies.https://doi.org/10.1038/s41598-025-10104-zCerebral-cardiac syndromeMachine learningStrokeSHAP analysisRisk prediction
spellingShingle Tingyu Zhang
Zelin Hao
Qunlian Jiang
Linhui Zhu
Lifang Ye
Machine learning-based prediction model for post-stroke cerebral-cardiac syndrome: a risk stratification study
Scientific Reports
Cerebral-cardiac syndrome
Machine learning
Stroke
SHAP analysis
Risk prediction
title Machine learning-based prediction model for post-stroke cerebral-cardiac syndrome: a risk stratification study
title_full Machine learning-based prediction model for post-stroke cerebral-cardiac syndrome: a risk stratification study
title_fullStr Machine learning-based prediction model for post-stroke cerebral-cardiac syndrome: a risk stratification study
title_full_unstemmed Machine learning-based prediction model for post-stroke cerebral-cardiac syndrome: a risk stratification study
title_short Machine learning-based prediction model for post-stroke cerebral-cardiac syndrome: a risk stratification study
title_sort machine learning based prediction model for post stroke cerebral cardiac syndrome a risk stratification study
topic Cerebral-cardiac syndrome
Machine learning
Stroke
SHAP analysis
Risk prediction
url https://doi.org/10.1038/s41598-025-10104-z
work_keys_str_mv AT tingyuzhang machinelearningbasedpredictionmodelforpoststrokecerebralcardiacsyndromeariskstratificationstudy
AT zelinhao machinelearningbasedpredictionmodelforpoststrokecerebralcardiacsyndromeariskstratificationstudy
AT qunlianjiang machinelearningbasedpredictionmodelforpoststrokecerebralcardiacsyndromeariskstratificationstudy
AT linhuizhu machinelearningbasedpredictionmodelforpoststrokecerebralcardiacsyndromeariskstratificationstudy
AT lifangye machinelearningbasedpredictionmodelforpoststrokecerebralcardiacsyndromeariskstratificationstudy