用于大血管前端闭塞血栓切除术结果预测的机器学习模型。

IF 4.4 2区 医学 Q1 CLINICAL NEUROLOGY Annals of Clinical and Translational Neurology Pub Date : 2024-08-23 DOI:10.1002/acn3.52185
Omid Shirvani, Stefanie Warnat-Herresthal, Ivan Savchuk, Felix J. Bode, Louisa Nitsch, Sebastian Stösser, Taraneh Ebrahimi, Niklas von Danwitz, Hannah Asperger, Julia Layer, Julius Meissner, Christian Thielscher, Franziska Dorn, Nils Lehnen, Joachim L. Schultze, Gabor C. Petzold, Johannes M. Weller, the GSR-ET Investigators
{"title":"用于大血管前端闭塞血栓切除术结果预测的机器学习模型。","authors":"Omid Shirvani,&nbsp;Stefanie Warnat-Herresthal,&nbsp;Ivan Savchuk,&nbsp;Felix J. Bode,&nbsp;Louisa Nitsch,&nbsp;Sebastian Stösser,&nbsp;Taraneh Ebrahimi,&nbsp;Niklas von Danwitz,&nbsp;Hannah Asperger,&nbsp;Julia Layer,&nbsp;Julius Meissner,&nbsp;Christian Thielscher,&nbsp;Franziska Dorn,&nbsp;Nils Lehnen,&nbsp;Joachim L. Schultze,&nbsp;Gabor C. Petzold,&nbsp;Johannes M. Weller,&nbsp;the GSR-ET Investigators","doi":"10.1002/acn3.52185","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Objective</h3>\n \n <p>Predicting long-term functional outcomes shortly after a stroke is challenging, even for experienced neurologists. Therefore, we aimed to evaluate multiple machine learning models and the importance of clinical/radiological parameters to develop a model that balances minimal input data with reliable predictions of long-term functional independency.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>Our study utilized data from the German Stroke Registry on patients with large anterior vessel occlusion who underwent endovascular treatment. We trained seven machine learning models using 30 parameters from the first day postadmission to predict a modified Ranking Scale of 0–2 at 90 days poststroke. Model performance was assessed using a 20-fold cross-validation and one-sided Wilcoxon rank-sum tests. Key features were identified through backward feature selection.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>We included 7485 individuals with a median age of 75 years and a median NIHSS score at admission of 14 in our analysis. Our Deep Neural Network model demonstrated the best performance among all models including data from 24 h postadmission. Backward feature selection identified the seven most important features to be NIHSS after 24 h, age, modified Ranking Scale after 24 h, premorbid modified Ranking Scale, intracranial hemorrhage within 24 h, intravenous thrombolysis, and NIHSS at admission. Narrowing the Deep Neural Network model's input data to these features preserved the high performance with an AUC of 0.9 (CI: 0.89–0.91).</p>\n </section>\n \n <section>\n \n <h3> Interpretation</h3>\n \n <p>Our Deep Neural Network model, trained on over 7000 patients, predicts 90-day functional independence using only seven clinical/radiological features from the first day postadmission, demonstrating both high accuracy and practicality for clinical implementation on stroke units.</p>\n </section>\n </div>","PeriodicalId":126,"journal":{"name":"Annals of Clinical and Translational Neurology","volume":null,"pages":null},"PeriodicalIF":4.4000,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/acn3.52185","citationCount":"0","resultStr":"{\"title\":\"Machine learning models for outcome prediction in thrombectomy for large anterior vessel occlusion\",\"authors\":\"Omid Shirvani,&nbsp;Stefanie Warnat-Herresthal,&nbsp;Ivan Savchuk,&nbsp;Felix J. Bode,&nbsp;Louisa Nitsch,&nbsp;Sebastian Stösser,&nbsp;Taraneh Ebrahimi,&nbsp;Niklas von Danwitz,&nbsp;Hannah Asperger,&nbsp;Julia Layer,&nbsp;Julius Meissner,&nbsp;Christian Thielscher,&nbsp;Franziska Dorn,&nbsp;Nils Lehnen,&nbsp;Joachim L. Schultze,&nbsp;Gabor C. Petzold,&nbsp;Johannes M. Weller,&nbsp;the GSR-ET Investigators\",\"doi\":\"10.1002/acn3.52185\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Objective</h3>\\n \\n <p>Predicting long-term functional outcomes shortly after a stroke is challenging, even for experienced neurologists. Therefore, we aimed to evaluate multiple machine learning models and the importance of clinical/radiological parameters to develop a model that balances minimal input data with reliable predictions of long-term functional independency.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Methods</h3>\\n \\n <p>Our study utilized data from the German Stroke Registry on patients with large anterior vessel occlusion who underwent endovascular treatment. We trained seven machine learning models using 30 parameters from the first day postadmission to predict a modified Ranking Scale of 0–2 at 90 days poststroke. Model performance was assessed using a 20-fold cross-validation and one-sided Wilcoxon rank-sum tests. Key features were identified through backward feature selection.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>We included 7485 individuals with a median age of 75 years and a median NIHSS score at admission of 14 in our analysis. Our Deep Neural Network model demonstrated the best performance among all models including data from 24 h postadmission. Backward feature selection identified the seven most important features to be NIHSS after 24 h, age, modified Ranking Scale after 24 h, premorbid modified Ranking Scale, intracranial hemorrhage within 24 h, intravenous thrombolysis, and NIHSS at admission. Narrowing the Deep Neural Network model's input data to these features preserved the high performance with an AUC of 0.9 (CI: 0.89–0.91).</p>\\n </section>\\n \\n <section>\\n \\n <h3> Interpretation</h3>\\n \\n <p>Our Deep Neural Network model, trained on over 7000 patients, predicts 90-day functional independence using only seven clinical/radiological features from the first day postadmission, demonstrating both high accuracy and practicality for clinical implementation on stroke units.</p>\\n </section>\\n </div>\",\"PeriodicalId\":126,\"journal\":{\"name\":\"Annals of Clinical and Translational Neurology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2024-08-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/acn3.52185\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals of Clinical and Translational Neurology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/acn3.52185\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Clinical and Translational Neurology","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/acn3.52185","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

摘要

目的:预测中风后不久的长期功能预后具有挑战性,即使是经验丰富的神经科医生也不例外。因此,我们旨在评估多种机器学习模型以及临床/放射学参数的重要性,以开发出一种模型,在最小输入数据与长期功能独立的可靠预测之间取得平衡:我们的研究利用了德国卒中登记处关于接受血管内治疗的前方大血管闭塞患者的数据。我们使用入院后第一天的 30 个参数训练了 7 个机器学习模型,以预测卒中后 90 天的修正排名量表 0-2。模型性能通过 20 倍交叉验证和单侧 Wilcoxon 秩和检验进行评估。通过反向特征选择确定了关键特征:我们在分析中纳入了 7485 名中位数年龄为 75 岁、入院时 NIHSS 评分中位数为 14 分的患者。在包括入院后 24 小时数据在内的所有模型中,我们的深度神经网络模型表现最佳。逆向特征选择确定了七个最重要的特征:24 小时后的 NIHSS、年龄、24 小时后的修正排名量表、入院前的修正排名量表、24 小时内的颅内出血、静脉溶栓和入院时的 NIHSS。将深度神经网络模型的输入数据缩小到这些特征后,其AUC为0.9(CI:0.89-0.91),保持了较高的性能:我们的深度神经网络模型是在 7000 多名患者身上训练出来的,只需使用入院后第一天的七个临床/放射学特征就能预测 90 天的功能独立性,证明了其高准确性和在卒中单元临床实施的实用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Machine learning models for outcome prediction in thrombectomy for large anterior vessel occlusion

Objective

Predicting long-term functional outcomes shortly after a stroke is challenging, even for experienced neurologists. Therefore, we aimed to evaluate multiple machine learning models and the importance of clinical/radiological parameters to develop a model that balances minimal input data with reliable predictions of long-term functional independency.

Methods

Our study utilized data from the German Stroke Registry on patients with large anterior vessel occlusion who underwent endovascular treatment. We trained seven machine learning models using 30 parameters from the first day postadmission to predict a modified Ranking Scale of 0–2 at 90 days poststroke. Model performance was assessed using a 20-fold cross-validation and one-sided Wilcoxon rank-sum tests. Key features were identified through backward feature selection.

Results

We included 7485 individuals with a median age of 75 years and a median NIHSS score at admission of 14 in our analysis. Our Deep Neural Network model demonstrated the best performance among all models including data from 24 h postadmission. Backward feature selection identified the seven most important features to be NIHSS after 24 h, age, modified Ranking Scale after 24 h, premorbid modified Ranking Scale, intracranial hemorrhage within 24 h, intravenous thrombolysis, and NIHSS at admission. Narrowing the Deep Neural Network model's input data to these features preserved the high performance with an AUC of 0.9 (CI: 0.89–0.91).

Interpretation

Our Deep Neural Network model, trained on over 7000 patients, predicts 90-day functional independence using only seven clinical/radiological features from the first day postadmission, demonstrating both high accuracy and practicality for clinical implementation on stroke units.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Annals of Clinical and Translational Neurology
Annals of Clinical and Translational Neurology Medicine-Neurology (clinical)
CiteScore
9.10
自引率
1.90%
发文量
218
审稿时长
8 weeks
期刊介绍: Annals of Clinical and Translational Neurology is a peer-reviewed journal for rapid dissemination of high-quality research related to all areas of neurology. The journal publishes original research and scholarly reviews focused on the mechanisms and treatments of diseases of the nervous system; high-impact topics in neurologic education; and other topics of interest to the clinical neuroscience community.
期刊最新文献
Subclinical imaging activity in multiple sclerosis patients during war-related psychological stress. Infantile Krabbe disease (0-12 months), progression, and recommended endpoints for clinical trials. Distinct neuroinflammatory patterns between cerebral microbleeds and microinfarcts in cerebral amyloid angiopathy. Medial intracranial carotid artery calcifications and hematoma expansion in deep intracerebral hemorrhage. Motor phenotypes associated with genetic neurodevelopmental disorders.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1