Skip to main content

ORIGINAL RESEARCH article

Front. Neuroinform.
Volume 18 - 2024 | doi: 10.3389/fninf.2024.1400702
This article is part of the Research Topic Innovative Applications of Machine Learning and Cutting-Edge Tools for Stroke Prediction and Treatment Strategies View all articles

Predicting the clinical prognosis of acute ischemic stroke using machine learning: an application of radiomic biomarkers on non-contrast CT after intravascular interventional

Provisionally accepted
Hongxian Gu Hongxian Gu 1Yuting Yan Yuting Yan 2Xiaodong He Xiaodong He 2Yuyun Xu Yuyun Xu 2Yuguo Wei Yuguo Wei 3Yuan Shao Yuan Shao 2*
  • 1 Department of Radiology, The People's Hospital of Jianyang City, Chengdu, Sichuan Province, China
  • 2 Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital, Hangzhou, Zhejiang Province, China
  • 3 GE Healthcare Life Sciences (China), Hangzhou, Jiangsu Province, China

The final, formatted version of the article will be published soon.

    To develop a radiomic model based on non-contrast CT (NCCT) after interventional treatment to predict the clinical prognosis of AIS (acute ischemic stroke) with large vessel occlusion. Methods: We retrospectively collected 141 cases of AIS from 2016 to 2020, and analyzed the patients' clinical data as well as NCCT data after interventional treatment. Then the total dataset was divided into training and testing set according to subject serial number. The cerebral hemispheres on the infarct side were segmented for radiomics signature extraction. After radiomics signatures were standardized and dimensionality reduction, the training set was used to construct a radiomics model by using machine learning. The testing set was then used to validate the prediction model, which was evaluated based on discrimination, calibration, and clinical utility. Finally, a joint model was constructed by incorporating the radiomics signatures and clinical data.The AUCs of the joint model, radiomics signature, the NIHSS score, and hypertension were 0.900, 0.863, 0.727, and 0.591 respectively in training set. In testing set, the AUCs of the joint model, radiomics signature, the NIHSS score, and hypertension were 0.885, 0.840, 0.721, and 0.590, respectively.Our results provided evidence that using post-interventional NCCT for radiomic model could be a valuable tool in predicting the clinical prognosis of AIS with large vessel occlusion.

    Keywords: Acute ischemic stroke, machine learning, radiomics signature, computed tomography, Stroke - Diagnosis

    Received: 14 Mar 2024; Accepted: 26 Jul 2024.

    Copyright: © 2024 Gu, Yan, He, Xu, Wei and Shao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Yuan Shao, Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People's Hospital, Hangzhou, 310014, Zhejiang Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.