Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatment

BackgroundThis study aimed to develop a clinical-radiomics model using hyperattenuated imaging markers (HIM), characterized by hyperattenuation on head non-contrast computed tomography immediately after thrombectomy, to predict the risk of hemorrhagic transformation (HT) in patients undergoing endov...

Full description

Saved in:
Bibliographic Details
Main Authors: Sheng Hu, Junyu Liu, Jiayi Hong, Yuting Chen, Ziwen Wang, Jibo Hu, Shiying Gai, Xiaochao Yu, Jingjing Fu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-02-01
Series:Frontiers in Neurology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fneur.2025.1471274/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722163094880256
author Sheng Hu
Junyu Liu
Jiayi Hong
Yuting Chen
Ziwen Wang
Jibo Hu
Shiying Gai
Xiaochao Yu
Jingjing Fu
author_facet Sheng Hu
Junyu Liu
Jiayi Hong
Yuting Chen
Ziwen Wang
Jibo Hu
Shiying Gai
Xiaochao Yu
Jingjing Fu
author_sort Sheng Hu
collection DOAJ
description BackgroundThis study aimed to develop a clinical-radiomics model using hyperattenuated imaging markers (HIM), characterized by hyperattenuation on head non-contrast computed tomography immediately after thrombectomy, to predict the risk of hemorrhagic transformation (HT) in patients undergoing endovascular mechanical thrombectomy (MT).MethodsA total of 159 consecutive patients with HIM were screened immediately after MT for inclusion. The datasets were randomly divided into training and test cohorts at a ratio of 8:2. An optimal machine learning (ML) algorithm was used for model development. Subsequently, models for clinical, radiomics, and clinical-radiomics were developed. The performance of the models was measured using receiver operating characteristic (ROC) and decision curve analyses (DCA). The interpretability and predictor importance of the model were analyzed using Shapley additive explanations.ResultsOf the 159 patients, 100 (62.9%) exhibited HT. The support vector machine (SVM) was the optimal ML algorithm for constructing the models. In predicting HT, the areas under the curve (AUCs) of the clinical model were 0.918 (95% confidence interval [CI] = 0.869–0.966) in the training cohort and 0.854 (95% CI = 0.724–0.984) in the test cohort. The AUCs of the radiomics model were 0.869 (95% CI = 0.802–0.936) and 0.829 (95% CI = 0.668–0.990), while those of the clinical-radiomics model were 0.944 (95% CI = 0.905–0.984) and 0.925 (95% CI = 0.832–1.000).ConclusionThe suggested clinical-radiomics model based on HIM is a reliable method that can provide a risk evaluation of HT in individuals undergoing MT.
format Article
id doaj-art-46daf3df4ebe43b6a90bbf7c9cc61614
institution DOAJ
issn 1664-2295
language English
publishDate 2025-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neurology
spelling doaj-art-46daf3df4ebe43b6a90bbf7c9cc616142025-08-20T03:11:25ZengFrontiers Media S.A.Frontiers in Neurology1664-22952025-02-011610.3389/fneur.2025.14712741471274Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatmentSheng Hu0Junyu Liu1Jiayi Hong2Yuting Chen3Ziwen Wang4Jibo Hu5Shiying Gai6Xiaochao Yu7Jingjing Fu8Department of Radiology, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaDepartment of Neurology, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaDepartment of Neurology, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaDepartment of Neurology, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaDepartment of Radiology, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaDepartment of Radiology, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaDepartment of Neurosurgery, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaDepartment of Radiology, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaDepartment of Neurology, The Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu, Zhejiang, ChinaBackgroundThis study aimed to develop a clinical-radiomics model using hyperattenuated imaging markers (HIM), characterized by hyperattenuation on head non-contrast computed tomography immediately after thrombectomy, to predict the risk of hemorrhagic transformation (HT) in patients undergoing endovascular mechanical thrombectomy (MT).MethodsA total of 159 consecutive patients with HIM were screened immediately after MT for inclusion. The datasets were randomly divided into training and test cohorts at a ratio of 8:2. An optimal machine learning (ML) algorithm was used for model development. Subsequently, models for clinical, radiomics, and clinical-radiomics were developed. The performance of the models was measured using receiver operating characteristic (ROC) and decision curve analyses (DCA). The interpretability and predictor importance of the model were analyzed using Shapley additive explanations.ResultsOf the 159 patients, 100 (62.9%) exhibited HT. The support vector machine (SVM) was the optimal ML algorithm for constructing the models. In predicting HT, the areas under the curve (AUCs) of the clinical model were 0.918 (95% confidence interval [CI] = 0.869–0.966) in the training cohort and 0.854 (95% CI = 0.724–0.984) in the test cohort. The AUCs of the radiomics model were 0.869 (95% CI = 0.802–0.936) and 0.829 (95% CI = 0.668–0.990), while those of the clinical-radiomics model were 0.944 (95% CI = 0.905–0.984) and 0.925 (95% CI = 0.832–1.000).ConclusionThe suggested clinical-radiomics model based on HIM is a reliable method that can provide a risk evaluation of HT in individuals undergoing MT.https://www.frontiersin.org/articles/10.3389/fneur.2025.1471274/fullhemorrhagic transformationmachine learningthrombectomyacute ischemic strokemulti-detector CT
spellingShingle Sheng Hu
Junyu Liu
Jiayi Hong
Yuting Chen
Ziwen Wang
Jibo Hu
Shiying Gai
Xiaochao Yu
Jingjing Fu
Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatment
Frontiers in Neurology
hemorrhagic transformation
machine learning
thrombectomy
acute ischemic stroke
multi-detector CT
title Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatment
title_full Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatment
title_fullStr Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatment
title_full_unstemmed Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatment
title_short Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatment
title_sort machine learning clinical radiomics approach with him for hemorrhagic transformation prediction after thrombectomy and treatment
topic hemorrhagic transformation
machine learning
thrombectomy
acute ischemic stroke
multi-detector CT
url https://www.frontiersin.org/articles/10.3389/fneur.2025.1471274/full
work_keys_str_mv AT shenghu machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment
AT junyuliu machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment
AT jiayihong machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment
AT yutingchen machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment
AT ziwenwang machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment
AT jibohu machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment
AT shiyinggai machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment
AT xiaochaoyu machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment
AT jingjingfu machinelearningclinicalradiomicsapproachwithhimforhemorrhagictransformationpredictionafterthrombectomyandtreatment