Development and validation of a multi-omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomy

Abstract This study aimed to develop a predictive model integrating clinical, radiomics, and deep learning (DL) features of hyperattenuated imaging markers (HIM) from computed tomography scans immediately following mechanical thrombectomy (MT) to predict hemorrhagic transformation (HT). A total of 2...

Full description

Saved in:
Bibliographic Details
Main Authors: Lina Jiang, Guoping Zhu, Yue Wang, Jiayi Hong, Jingjing Fu, Jibo Hu, Shengxiang Xiao, Jiayi Chu, Sheng Hu, Wenbo Xiao
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02056-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850268820613103616
author Lina Jiang
Guoping Zhu
Yue Wang
Jiayi Hong
Jingjing Fu
Jibo Hu
Shengxiang Xiao
Jiayi Chu
Sheng Hu
Wenbo Xiao
author_facet Lina Jiang
Guoping Zhu
Yue Wang
Jiayi Hong
Jingjing Fu
Jibo Hu
Shengxiang Xiao
Jiayi Chu
Sheng Hu
Wenbo Xiao
author_sort Lina Jiang
collection DOAJ
description Abstract This study aimed to develop a predictive model integrating clinical, radiomics, and deep learning (DL) features of hyperattenuated imaging markers (HIM) from computed tomography scans immediately following mechanical thrombectomy (MT) to predict hemorrhagic transformation (HT). A total of 239 patients with HIM who underwent MT were enrolled, with 191 patients (80%) in the training cohort and 48 patients (20%) in the validation cohort. Additionally, the model was tested on an internal prospective cohort of 49 patients. A total of 1834 radiomics features and 2048 DL features were extracted from HIM images. Statistical methods, such as analysis of variance, Pearson’s correlation coefficient, principal component analysis, and least absolute shrinkage and selection operator, were used to select the most significant features. A K-Nearest Neighbor classifier was employed to develop a combined model integrating clinical, radiomics, and DL features for HT prediction. Model performance was evaluated using metrics such as accuracy, sensitivity, specificity, receiver operating characteristic curves, and area under curve (AUC). In the training, validation, and test cohorts, the combined model achieved AUCs of 0.926, 0.923, and 0.887, respectively, outperforming other models, including clinical, radiomics, and DL models, as well as hybrid models combining subsets of features (Clinical + Radiomics, DL + Radiomics, and Clinical + DL) in predicting HT. The combined model, which integrates clinical, radiomics, and DL features derived from HIM, demonstrated efficacy in noninvasively predicting HT. These findings suggest its potential utility in guiding clinical decision-making for patients with MT.
format Article
id doaj-art-2ebc5f769db440d9bb3a55cca973cd1c
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-2ebc5f769db440d9bb3a55cca973cd1c2025-08-20T01:53:22ZengNature PortfolioScientific Reports2045-23222025-05-0115111210.1038/s41598-025-02056-1Development and validation of a multi-omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomyLina Jiang0Guoping Zhu1Yue Wang2Jiayi Hong3Jingjing Fu4Jibo Hu5Shengxiang Xiao6Jiayi Chu7Sheng Hu8Wenbo Xiao9Department of Radiology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Radiology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Radiology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Neurology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Neurology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Radiology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Radiology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Radiology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Radiology, the Fourth Affiliated Hospital of School of Medicine, and International School of Medicine, International Institutes of Medicine, Zhejiang UniversityDepartment of Radiology, the First Affiliated Hospital, College of Medicine, Zhejiang UniversityAbstract This study aimed to develop a predictive model integrating clinical, radiomics, and deep learning (DL) features of hyperattenuated imaging markers (HIM) from computed tomography scans immediately following mechanical thrombectomy (MT) to predict hemorrhagic transformation (HT). A total of 239 patients with HIM who underwent MT were enrolled, with 191 patients (80%) in the training cohort and 48 patients (20%) in the validation cohort. Additionally, the model was tested on an internal prospective cohort of 49 patients. A total of 1834 radiomics features and 2048 DL features were extracted from HIM images. Statistical methods, such as analysis of variance, Pearson’s correlation coefficient, principal component analysis, and least absolute shrinkage and selection operator, were used to select the most significant features. A K-Nearest Neighbor classifier was employed to develop a combined model integrating clinical, radiomics, and DL features for HT prediction. Model performance was evaluated using metrics such as accuracy, sensitivity, specificity, receiver operating characteristic curves, and area under curve (AUC). In the training, validation, and test cohorts, the combined model achieved AUCs of 0.926, 0.923, and 0.887, respectively, outperforming other models, including clinical, radiomics, and DL models, as well as hybrid models combining subsets of features (Clinical + Radiomics, DL + Radiomics, and Clinical + DL) in predicting HT. The combined model, which integrates clinical, radiomics, and DL features derived from HIM, demonstrated efficacy in noninvasively predicting HT. These findings suggest its potential utility in guiding clinical decision-making for patients with MT.https://doi.org/10.1038/s41598-025-02056-1Intracranial hemorrhagesMachine learningThrombectomyAcute ischemic strokeMulti-detector CT
spellingShingle Lina Jiang
Guoping Zhu
Yue Wang
Jiayi Hong
Jingjing Fu
Jibo Hu
Shengxiang Xiao
Jiayi Chu
Sheng Hu
Wenbo Xiao
Development and validation of a multi-omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomy
Scientific Reports
Intracranial hemorrhages
Machine learning
Thrombectomy
Acute ischemic stroke
Multi-detector CT
title Development and validation of a multi-omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomy
title_full Development and validation of a multi-omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomy
title_fullStr Development and validation of a multi-omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomy
title_full_unstemmed Development and validation of a multi-omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomy
title_short Development and validation of a multi-omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomy
title_sort development and validation of a multi omics hemorrhagic transformation model based on hyperattenuated imaging markers following mechanical thrombectomy
topic Intracranial hemorrhages
Machine learning
Thrombectomy
Acute ischemic stroke
Multi-detector CT
url https://doi.org/10.1038/s41598-025-02056-1
work_keys_str_mv AT linajiang developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT guopingzhu developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT yuewang developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT jiayihong developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT jingjingfu developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT jibohu developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT shengxiangxiao developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT jiayichu developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT shenghu developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy
AT wenboxiao developmentandvalidationofamultiomicshemorrhagictransformationmodelbasedonhyperattenuatedimagingmarkersfollowingmechanicalthrombectomy