Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning model
Background Identification of futile recanalisation following endovascular therapy (EVT) in patients with acute ischaemic stroke is both crucial and challenging. Here, we present a novel risk stratification system based on hybrid machine learning method for predicting futile recanalisation.Methods Hy...
Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMJ Publishing Group
|
Series: | Stroke and Vascular Neurology |
Online Access: | https://svn.bmj.com/content/early/2024/02/08/svn-2023-002500.full |
_version_ | 1797319355149582336 |
---|---|
author | Liping Liu Zhongrong Miao Zixiao Li Dongdong Liu Xia Meng Tao Liu Yong Jiang Yuesong Pan Jiaping Chen Weibin Gu Hongyi Yan Yufei Wei Zhonghua Yang Jian Cheng Ximing Nie Miao Wen Zhenzhou Wu Guoyang Gong Jinxu Yang Xinxin Li Tianming Zhan Xiran Liu |
author_facet | Liping Liu Zhongrong Miao Zixiao Li Dongdong Liu Xia Meng Tao Liu Yong Jiang Yuesong Pan Jiaping Chen Weibin Gu Hongyi Yan Yufei Wei Zhonghua Yang Jian Cheng Ximing Nie Miao Wen Zhenzhou Wu Guoyang Gong Jinxu Yang Xinxin Li Tianming Zhan Xiran Liu |
author_sort | Liping Liu |
collection | DOAJ |
description | Background Identification of futile recanalisation following endovascular therapy (EVT) in patients with acute ischaemic stroke is both crucial and challenging. Here, we present a novel risk stratification system based on hybrid machine learning method for predicting futile recanalisation.Methods Hybrid machine learning models were developed to address six clinical scenarios within the EVT and perioperative management workflow. These models were trained on a prospective database using hybrid feature selection technique to predict futile recanalisation following EVT. The optimal model was validated and compared with existing models and scoring systems in a multicentre prospective cohort to develop a hybrid machine learning-based risk stratification system for futile recanalisation prediction.Results Using a hybrid feature selection approach, we trained and tested multiple classifiers on two independent patient cohorts (n=1122) to develop a hybrid machine learning-based prediction model. The model demonstrated superior discriminative ability compared with other models and scoring systems (area under the curve=0.80, 95% CI 0.73 to 0.87) and was transformed into a web application (RESCUE-FR Index) that provides a risk stratification system for individual prediction (accessible online at fr-index.biomind.cn/RESCUE-FR/).Conclusions The proposed hybrid machine learning approach could be used as an individualised risk prediction model to facilitate adherence to clinical practice guidelines and shared decision-making for optimal candidate selection and prognosis assessment in patients undergoing EVT. |
first_indexed | 2024-03-08T04:05:43Z |
format | Article |
id | doaj.art-7b58549ee77b434bb6c1cd5b0235abd9 |
institution | Directory Open Access Journal |
issn | 2059-8696 |
language | English |
last_indexed | 2024-03-08T04:05:43Z |
publisher | BMJ Publishing Group |
record_format | Article |
series | Stroke and Vascular Neurology |
spelling | doaj.art-7b58549ee77b434bb6c1cd5b0235abd92024-02-09T05:05:08ZengBMJ Publishing GroupStroke and Vascular Neurology2059-869610.1136/svn-2023-002500Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning modelLiping Liu0Zhongrong Miao1Zixiao Li2Dongdong Liu3Xia Meng4Tao Liu5Yong Jiang6Yuesong Pan7Jiaping Chen8Weibin Gu9Hongyi Yan10Yufei Wei11Zhonghua Yang12Jian Cheng13Ximing Nie14Miao Wen15Zhenzhou Wu16Guoyang Gong17Jinxu Yang18Xinxin Li19Tianming Zhan20Xiran Liu21China National Clinical Research Center for Neurological Diseases, Beijing, ChinaDepartment of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China6 Pfizer Investment Co., Ltd, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaBeijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China1 Department of Epidemiology, Center for Global Health, School of Public Health, Nanjing Medical University, Nanjing, ChinaDepartment of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, China2 China National Clinical Research Center for Neurological Diseases, Beijing, China2 China National Clinical Research Center for Neurological Diseases, Beijing, ChinaDepartment of Epidemiology and Biostatistics, School of Public Health, Anhui Medical University, Hefei, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, ChinaDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China1 BioMind, SingaporeArtificial Intelligence Research Center, China National Clinical Research Center for Neurological Diseases, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology, Beijing, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, ChinaChina National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Beijing, ChinaDepartment of Neurology, Capital Medical University, Beijing, ChinaBackground Identification of futile recanalisation following endovascular therapy (EVT) in patients with acute ischaemic stroke is both crucial and challenging. Here, we present a novel risk stratification system based on hybrid machine learning method for predicting futile recanalisation.Methods Hybrid machine learning models were developed to address six clinical scenarios within the EVT and perioperative management workflow. These models were trained on a prospective database using hybrid feature selection technique to predict futile recanalisation following EVT. The optimal model was validated and compared with existing models and scoring systems in a multicentre prospective cohort to develop a hybrid machine learning-based risk stratification system for futile recanalisation prediction.Results Using a hybrid feature selection approach, we trained and tested multiple classifiers on two independent patient cohorts (n=1122) to develop a hybrid machine learning-based prediction model. The model demonstrated superior discriminative ability compared with other models and scoring systems (area under the curve=0.80, 95% CI 0.73 to 0.87) and was transformed into a web application (RESCUE-FR Index) that provides a risk stratification system for individual prediction (accessible online at fr-index.biomind.cn/RESCUE-FR/).Conclusions The proposed hybrid machine learning approach could be used as an individualised risk prediction model to facilitate adherence to clinical practice guidelines and shared decision-making for optimal candidate selection and prognosis assessment in patients undergoing EVT.https://svn.bmj.com/content/early/2024/02/08/svn-2023-002500.full |
spellingShingle | Liping Liu Zhongrong Miao Zixiao Li Dongdong Liu Xia Meng Tao Liu Yong Jiang Yuesong Pan Jiaping Chen Weibin Gu Hongyi Yan Yufei Wei Zhonghua Yang Jian Cheng Ximing Nie Miao Wen Zhenzhou Wu Guoyang Gong Jinxu Yang Xinxin Li Tianming Zhan Xiran Liu Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning model Stroke and Vascular Neurology |
title | Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning model |
title_full | Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning model |
title_fullStr | Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning model |
title_full_unstemmed | Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning model |
title_short | Prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke: development and validation of a hybrid machine learning model |
title_sort | prediction of futile recanalisation after endovascular treatment in acute ischaemic stroke development and validation of a hybrid machine learning model |
url | https://svn.bmj.com/content/early/2024/02/08/svn-2023-002500.full |
work_keys_str_mv | AT lipingliu predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT zhongrongmiao predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT zixiaoli predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT dongdongliu predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT xiameng predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT taoliu predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT yongjiang predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT yuesongpan predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT jiapingchen predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT weibingu predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT hongyiyan predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT yufeiwei predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT zhonghuayang predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT jiancheng predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT ximingnie predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT miaowen predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT zhenzhouwu predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT guoyanggong predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT jinxuyang predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT xinxinli predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT tianmingzhan predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel AT xiranliu predictionoffutilerecanalisationafterendovasculartreatmentinacuteischaemicstrokedevelopmentandvalidationofahybridmachinelearningmodel |