Data-Driven Prognostication in Distal Medium Vessel Occlusions Using Explainable Machine Learning.

Mert Karabacak, Burak Berksu Ozkara, Tobias D Faizy, Trevor Hardigan, Jeremy J Heit, Dhairya A Lakhani, Konstantinos Margetis, J Mocco, Kambiz Nael, Max Wintermark, Vivek S Yedavalli
{"title":"Data-Driven Prognostication in Distal Medium Vessel Occlusions Using Explainable Machine Learning.","authors":"Mert Karabacak, Burak Berksu Ozkara, Tobias D Faizy, Trevor Hardigan, Jeremy J Heit, Dhairya A Lakhani, Konstantinos Margetis, J Mocco, Kambiz Nael, Max Wintermark, Vivek S Yedavalli","doi":"10.3174/ajnr.A8547","DOIUrl":null,"url":null,"abstract":"<p><strong>Background and purpose: </strong>Distal medium vessel occlusions (DMVOs) are estimated to cause acute ischemic stroke (AIS) in 25-40% of cases. Prognostic models can inform patient counseling and research by enabling outcome predictions. However, models designed specifically for DMVOs are lacking.</p><p><strong>Materials and methods: </strong>This retrospective study developed a machine learning model to predict 90-day unfavorable outcome [defined as a modified Rankin Scale (mRS) score of 3-6] in 164 primary DMVO patients. A model developed with the TabPFN algorithm utilized selected clinical, laboratory, imaging, and treatment data with the Least Absolute Shrinkage and Selection Operator feature selection. Performance was evaluated via 5-repeat 5-fold cross-validation. Model discrimination and calibration were evaluated. SHapley Additive Explanations (SHAP) identified influential features. A web application deployed the model for individualized predictions.</p><p><strong>Results: </strong>The model achieved an area under the receiver operating characteristic curve of 0.815 (95% CI: 0.79-0.841) for predicting unfavorable outcome, demonstrating good discrimination, and a Brier score of 0.19 (95% CI: 0.177-0.202), demonstrating good calibration. SHAP analysis ranked admission National Institutes of Health Stroke Scale (NIHSS) score, premorbid mRS, type of thrombectomy, modified thrombolysis in cerebral infarction score, and history of malignancy as top predictors. The web application enables individualized prognostication.</p><p><strong>Conclusions: </strong>Our machine learning model demonstrated good discrimination and calibration for predicting 90-day unfavorable outcomes in primary DMVO strokes. This study demonstrates the potential for personalized prognostic counseling and research to support precision medicine in stroke care and recovery.</p><p><strong>Abbreviations: </strong>DMVO = Distal medium vessel occlusion; AIS = acute ischemic stroke; mRS = modified Rankin Scale; SHAP = SHapley Additive Explanations; NIHSS = National Institutes of Health Stroke Scale; ST = stroke thrombectomy; TRIPOD = Transparent Reporting of Multivariable Prediction Models for Individual Prognosis or Diagnosis; CT = computed tomography; CTP = CT perfusion; MRI = magnetic resonance imaging; CTA = CT angiography; DVT = deep vein thrombosis; PE = pulmonary emboli; TIA = transient ischemic attack; BMI = body mass index; ALP = alkaline phosphatase; ALT = alanine transaminase; AST = aspartate aminotransferase; NCCT-ASPECTS = Alberta Stroke Program Early CT Score; IVT = intravenous thrombolysis; mTICI = modified thrombolysis in cerebral infarction; ER = emergency room; kNN = k-nearest neighbor; LASSO = Least Absolute Shrinkage and Selection Operator; PDPs = partial dependence plots; ROC = receiver operating characteristic; PRC = precision-recall curve; AUROC = area under the ROC curve; AUPRC = area under the PRC; CI = confidence interval.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"AJNR. American journal of neuroradiology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3174/ajnr.A8547","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Background and purpose: Distal medium vessel occlusions (DMVOs) are estimated to cause acute ischemic stroke (AIS) in 25-40% of cases. Prognostic models can inform patient counseling and research by enabling outcome predictions. However, models designed specifically for DMVOs are lacking.

Materials and methods: This retrospective study developed a machine learning model to predict 90-day unfavorable outcome [defined as a modified Rankin Scale (mRS) score of 3-6] in 164 primary DMVO patients. A model developed with the TabPFN algorithm utilized selected clinical, laboratory, imaging, and treatment data with the Least Absolute Shrinkage and Selection Operator feature selection. Performance was evaluated via 5-repeat 5-fold cross-validation. Model discrimination and calibration were evaluated. SHapley Additive Explanations (SHAP) identified influential features. A web application deployed the model for individualized predictions.

Results: The model achieved an area under the receiver operating characteristic curve of 0.815 (95% CI: 0.79-0.841) for predicting unfavorable outcome, demonstrating good discrimination, and a Brier score of 0.19 (95% CI: 0.177-0.202), demonstrating good calibration. SHAP analysis ranked admission National Institutes of Health Stroke Scale (NIHSS) score, premorbid mRS, type of thrombectomy, modified thrombolysis in cerebral infarction score, and history of malignancy as top predictors. The web application enables individualized prognostication.

Conclusions: Our machine learning model demonstrated good discrimination and calibration for predicting 90-day unfavorable outcomes in primary DMVO strokes. This study demonstrates the potential for personalized prognostic counseling and research to support precision medicine in stroke care and recovery.

Abbreviations: DMVO = Distal medium vessel occlusion; AIS = acute ischemic stroke; mRS = modified Rankin Scale; SHAP = SHapley Additive Explanations; NIHSS = National Institutes of Health Stroke Scale; ST = stroke thrombectomy; TRIPOD = Transparent Reporting of Multivariable Prediction Models for Individual Prognosis or Diagnosis; CT = computed tomography; CTP = CT perfusion; MRI = magnetic resonance imaging; CTA = CT angiography; DVT = deep vein thrombosis; PE = pulmonary emboli; TIA = transient ischemic attack; BMI = body mass index; ALP = alkaline phosphatase; ALT = alanine transaminase; AST = aspartate aminotransferase; NCCT-ASPECTS = Alberta Stroke Program Early CT Score; IVT = intravenous thrombolysis; mTICI = modified thrombolysis in cerebral infarction; ER = emergency room; kNN = k-nearest neighbor; LASSO = Least Absolute Shrinkage and Selection Operator; PDPs = partial dependence plots; ROC = receiver operating characteristic; PRC = precision-recall curve; AUROC = area under the ROC curve; AUPRC = area under the PRC; CI = confidence interval.

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
利用可解释的机器学习对远端中脉闭塞进行数据驱动预诊
背景和目的:据估计,25%-40% 的病例由远端中血管闭塞(DMVO)引起急性缺血性卒中(AIS)。预后模型可通过预测结果为患者咨询和研究提供信息。然而,目前还缺乏专门针对 DMVO 设计的模型:这项回顾性研究开发了一种机器学习模型,用于预测 164 例原发性 DMVO 患者的 90 天不良预后(定义为改良 Rankin 量表(mRS)评分 3-6 分)。使用 TabPFN 算法开发的模型利用了选定的临床、实验室、成像和治疗数据,并使用最小绝对收缩和选择操作器进行特征选择。通过 5 次重复 5 倍交叉验证对其性能进行了评估。对模型辨别和校准进行了评估。SHapley Additive Explanations (SHAP) 确定了有影响力的特征。网络应用程序部署了个性化预测模型:结果:该模型预测不利结果的接收者操作特征曲线下面积为 0.815(95% CI:0.79-0.841),显示出良好的辨别能力;Brier 评分为 0.19(95% CI:0.177-0.202),显示出良好的校准能力。SHAP分析将入院时美国国立卫生研究院卒中量表(NIHSS)评分、病前mRS、血栓切除类型、改良脑梗塞溶栓评分和恶性肿瘤病史列为最主要的预测因素。网络应用可实现个性化预后:我们的机器学习模型在预测原发性DMVO脑卒中90天不良预后方面表现出了良好的辨别能力和校准能力。这项研究展示了个性化预后咨询和研究的潜力,以支持中风护理和康复中的精准医疗:缩写:ABC = 定义;XYZ = 定义。DMVO = 远端中血管闭塞;AIS = 急性缺血性卒中;mRS = 改良 Rankin 量表;SHAP = SHapley Additive Explanations;NIHSS = 美国国立卫生研究院卒中量表;ST = 卒中血栓切除术;TRIPOD = Transparent Reporting of Multivariable Prediction Models for Individual Prognosis or Diagnosis;CT = 计算机断层扫描;CTP = CT 灌注;MRI = 磁共振成像;CTA = CT 血管造影;DVT = 深静脉血栓;PE = 肺栓塞;TIA = 短暂性脑缺血发作;BMI = 体重指数;ALP=碱性磷酸酶;ALT=丙氨酸转氨酶;AST=天冬氨酸氨基转移酶;NCCT-ASPECTS=阿尔伯塔省卒中项目早期 CT 评分;IVT=静脉溶栓;mTICI=改良脑梗塞溶栓;ER=急诊室;kNN=k-近邻;LASSO=最小绝对缩减和选择操作器;PDPs=部分依赖图;ROC=接收者操作特征;PRC=精确度-召回曲线;AUROC=ROC曲线下面积;AUPRC=PRC下面积;CI=置信区间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Meningioma: Molecular Updates from the 2021 World Health Organization Classification of CNS Tumors and Imaging Correlates. Light-Chain Deposition Diseases of the CNS: Review of Pathogenesis, Imaging Features, and Radiographic Mimics. Incorporation of Edited MRS into Clinical Practice May Improve Care of Patients with IDH-Mutant Glioma. Visualization of Intracranial Aneurysms Treated with Woven EndoBridge Devices using Ultrashort TE MR Imaging. Comprehensive Review of the Utility of Dynamic Contrast-Enhanced MRI for the Diagnosis and Treatment Assessment of Spinal Benign and Malignant Osseous Disease.
×
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