Leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care.

<h4>Background</h4>Venous thromboembolism (VTE) is a life-threatening complication commonly occurring after acute ischemic stroke (AIS), with an increased risk of mortality. Traditional risk assessment tools lack precision in predicting VTE in AIS patients due to the omission of stroke-s...

Full description

Saved in:
Bibliographic Details
Main Authors: Youli Jiang, Ao Li, Zhihuan Li, Yanfeng Li, Rong Li, Qingshi Zhao, Guisu Li
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0302676
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261254876168192
author Youli Jiang
Ao Li
Zhihuan Li
Yanfeng Li
Rong Li
Qingshi Zhao
Guisu Li
author_facet Youli Jiang
Ao Li
Zhihuan Li
Yanfeng Li
Rong Li
Qingshi Zhao
Guisu Li
author_sort Youli Jiang
collection DOAJ
description <h4>Background</h4>Venous thromboembolism (VTE) is a life-threatening complication commonly occurring after acute ischemic stroke (AIS), with an increased risk of mortality. Traditional risk assessment tools lack precision in predicting VTE in AIS patients due to the omission of stroke-specific factors.<h4>Methods</h4>We developed a machine learning model using clinical data from patients with acute ischemic stroke (AIS) admitted between December 2021 and December 2023. Predictive models were developed using machine learning algorithms, including Gradient Boosting Machine (GBM), Random Forest (RF), and Logistic Regression (LR). Feature selection involved stepwise logistic regression and LASSO, with SHapley Additive exPlanations (SHAP) used to enhance model interpretability. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).<h4>Results</h4>Among the 1,632 AIS patients analyzed, 4.17% developed VTE. The GBM model achieved the highest predictive accuracy with an AUC of 0.923, outperforming other models such as Random Forest and Logistic Regression. The model demonstrated strong sensitivity (90.83%) and specificity (93.83%) in identifying high-risk patients. SHAP analysis revealed that key predictors of VTE risk included elevated D-dimer levels, premorbid mRS, and large vessel occlusion, offering clinicians valuable insights for personalized treatment decisions.<h4>Conclusion</h4>This study provides an accurate and interpretable method to predict VTE risk in patients with AIS using the GBM model, potentially improving early detection rates and reducing morbidity. Further validation is needed to assess its broader clinical applicability.
format Article
id doaj-art-e1861eee76dd46bcb6a9e247a737d793
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-e1861eee76dd46bcb6a9e247a737d7932025-08-20T01:55:27ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e030267610.1371/journal.pone.0302676Leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care.Youli JiangAo LiZhihuan LiYanfeng LiRong LiQingshi ZhaoGuisu Li<h4>Background</h4>Venous thromboembolism (VTE) is a life-threatening complication commonly occurring after acute ischemic stroke (AIS), with an increased risk of mortality. Traditional risk assessment tools lack precision in predicting VTE in AIS patients due to the omission of stroke-specific factors.<h4>Methods</h4>We developed a machine learning model using clinical data from patients with acute ischemic stroke (AIS) admitted between December 2021 and December 2023. Predictive models were developed using machine learning algorithms, including Gradient Boosting Machine (GBM), Random Forest (RF), and Logistic Regression (LR). Feature selection involved stepwise logistic regression and LASSO, with SHapley Additive exPlanations (SHAP) used to enhance model interpretability. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).<h4>Results</h4>Among the 1,632 AIS patients analyzed, 4.17% developed VTE. The GBM model achieved the highest predictive accuracy with an AUC of 0.923, outperforming other models such as Random Forest and Logistic Regression. The model demonstrated strong sensitivity (90.83%) and specificity (93.83%) in identifying high-risk patients. SHAP analysis revealed that key predictors of VTE risk included elevated D-dimer levels, premorbid mRS, and large vessel occlusion, offering clinicians valuable insights for personalized treatment decisions.<h4>Conclusion</h4>This study provides an accurate and interpretable method to predict VTE risk in patients with AIS using the GBM model, potentially improving early detection rates and reducing morbidity. Further validation is needed to assess its broader clinical applicability.https://doi.org/10.1371/journal.pone.0302676
spellingShingle Youli Jiang
Ao Li
Zhihuan Li
Yanfeng Li
Rong Li
Qingshi Zhao
Guisu Li
Leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care.
PLoS ONE
title Leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care.
title_full Leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care.
title_fullStr Leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care.
title_full_unstemmed Leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care.
title_short Leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care.
title_sort leveraging machine learning for enhanced and interpretable risk prediction of venous thromboembolism in acute ischemic stroke care
url https://doi.org/10.1371/journal.pone.0302676
work_keys_str_mv AT youlijiang leveragingmachinelearningforenhancedandinterpretableriskpredictionofvenousthromboembolisminacuteischemicstrokecare
AT aoli leveragingmachinelearningforenhancedandinterpretableriskpredictionofvenousthromboembolisminacuteischemicstrokecare
AT zhihuanli leveragingmachinelearningforenhancedandinterpretableriskpredictionofvenousthromboembolisminacuteischemicstrokecare
AT yanfengli leveragingmachinelearningforenhancedandinterpretableriskpredictionofvenousthromboembolisminacuteischemicstrokecare
AT rongli leveragingmachinelearningforenhancedandinterpretableriskpredictionofvenousthromboembolisminacuteischemicstrokecare
AT qingshizhao leveragingmachinelearningforenhancedandinterpretableriskpredictionofvenousthromboembolisminacuteischemicstrokecare
AT guisuli leveragingmachinelearningforenhancedandinterpretableriskpredictionofvenousthromboembolisminacuteischemicstrokecare