José Pedro Lavrador, Ana Mirallave-Pescador, Christos Soumpasis, Alba Díaz Baamonde, Jahard Aliaga-Arias, Asfand Baig Mirza, Sabina Patel, José David Siado Mosquera, Richard Gullan, Keyoumars Ashkan, Ranjeev Bhangoo, Francesco Vergani
{"title":"基于经颅磁刺激的运动神经胶质瘤肿瘤分级机器学习预测。","authors":"José Pedro Lavrador, Ana Mirallave-Pescador, Christos Soumpasis, Alba Díaz Baamonde, Jahard Aliaga-Arias, Asfand Baig Mirza, Sabina Patel, José David Siado Mosquera, Richard Gullan, Keyoumars Ashkan, Ranjeev Bhangoo, Francesco Vergani","doi":"10.1227/neu.0000000000002902","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Navigated transcranial magnetic stimulation (nTMS) is a well-established preoperative mapping tool for motor-eloquent glioma surgery. Machine learning (ML) and nTMS may improve clinical outcome prediction and histological correlation.</p><p><strong>Methods: </strong>This was a retrospective cohort study of patients who underwent surgery for motor-eloquent gliomas between 2018 and 2022. Ten healthy subjects were included. Preoperative nTMS-derived variables were collected: resting motor threshold (RMT), interhemispheric RMT ratio (iRMTr)-abnormal if above 10%-and cortical excitability score-number of abnormal iRMTrs. World Health Organization (WHO) grade and molecular profile were collected to characterize each tumor. ML models were fitted to the data after statistical feature selection to predict tumor grade.</p><p><strong>Results: </strong>A total of 177 patients were recruited: WHO grade 2-32 patients, WHO grade 3-65 patients, and WHO grade 4-80 patients. For the upper limb, abnormal iRMTr were identified in 22.7% of WHO grade 2, 62.5% of WHO grade 3, and 75.4% of WHO grade 4 patients. For the lower limb, iRMTr was abnormal in 23.1% of WHO grade 2, 67.6% of WHO grade 3%, and 63.6% of WHO grade 4 patients. Cortical excitability score ( P = .04) was statistically significantly related with WHO grading. Using these variables as predictors, the ML model had an accuracy of 0.57 to predict WHO grade 4 lesions. In subgroup analysis of high-grade gliomas vs low-grade gliomas, the accuracy for high-grade gliomas prediction increased to 0.83. The inclusion of molecular data into the model-IDH mutation and 1p19q codeletion status-increases the accuracy of the model in predicting tumor grading (0.95 and 0.74, respectively).</p><p><strong>Conclusion: </strong>ML algorithms based on nTMS-derived interhemispheric excitability assessment provide accurate predictions of HGGs affecting the motor pathway. Their accuracy is further increased when molecular data are fitted onto the model paving the way for a joint preoperative approach with radiogenomics.</p>","PeriodicalId":19276,"journal":{"name":"Neurosurgery","volume":null,"pages":null},"PeriodicalIF":3.9000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Transcranial Magnetic Stimulation-Based Machine Learning Prediction of Tumor Grading in Motor-Eloquent Gliomas.\",\"authors\":\"José Pedro Lavrador, Ana Mirallave-Pescador, Christos Soumpasis, Alba Díaz Baamonde, Jahard Aliaga-Arias, Asfand Baig Mirza, Sabina Patel, José David Siado Mosquera, Richard Gullan, Keyoumars Ashkan, Ranjeev Bhangoo, Francesco Vergani\",\"doi\":\"10.1227/neu.0000000000002902\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Navigated transcranial magnetic stimulation (nTMS) is a well-established preoperative mapping tool for motor-eloquent glioma surgery. Machine learning (ML) and nTMS may improve clinical outcome prediction and histological correlation.</p><p><strong>Methods: </strong>This was a retrospective cohort study of patients who underwent surgery for motor-eloquent gliomas between 2018 and 2022. Ten healthy subjects were included. Preoperative nTMS-derived variables were collected: resting motor threshold (RMT), interhemispheric RMT ratio (iRMTr)-abnormal if above 10%-and cortical excitability score-number of abnormal iRMTrs. World Health Organization (WHO) grade and molecular profile were collected to characterize each tumor. ML models were fitted to the data after statistical feature selection to predict tumor grade.</p><p><strong>Results: </strong>A total of 177 patients were recruited: WHO grade 2-32 patients, WHO grade 3-65 patients, and WHO grade 4-80 patients. For the upper limb, abnormal iRMTr were identified in 22.7% of WHO grade 2, 62.5% of WHO grade 3, and 75.4% of WHO grade 4 patients. For the lower limb, iRMTr was abnormal in 23.1% of WHO grade 2, 67.6% of WHO grade 3%, and 63.6% of WHO grade 4 patients. Cortical excitability score ( P = .04) was statistically significantly related with WHO grading. Using these variables as predictors, the ML model had an accuracy of 0.57 to predict WHO grade 4 lesions. In subgroup analysis of high-grade gliomas vs low-grade gliomas, the accuracy for high-grade gliomas prediction increased to 0.83. The inclusion of molecular data into the model-IDH mutation and 1p19q codeletion status-increases the accuracy of the model in predicting tumor grading (0.95 and 0.74, respectively).</p><p><strong>Conclusion: </strong>ML algorithms based on nTMS-derived interhemispheric excitability assessment provide accurate predictions of HGGs affecting the motor pathway. Their accuracy is further increased when molecular data are fitted onto the model paving the way for a joint preoperative approach with radiogenomics.</p>\",\"PeriodicalId\":19276,\"journal\":{\"name\":\"Neurosurgery\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2024-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neurosurgery\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1227/neu.0000000000002902\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/3/21 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurosurgery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1227/neu.0000000000002902","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/3/21 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0
摘要
背景：导航经颅磁刺激（nTMS）是一种行之有效的术前映射工具，可用于运动性胶质瘤手术。机器学习（ML）和 nTMS 可改善临床结果预测和组织学相关性：这是一项回顾性队列研究，研究对象为2018年至2022年间接受运动灶胶质瘤手术的患者。研究还纳入了 10 名健康受试者。收集了术前 nTMS 衍生变量：静息运动阈值（RMT）、半球间 RMT 比值（iRMTr）--如果高于 10%，则为异常；皮质兴奋性评分--异常 iRMTrs 的数量。还收集了世界卫生组织（WHO）的分级和分子特征，以确定每个肿瘤的特征。在统计特征选择后，对数据拟合 ML 模型，以预测肿瘤分级：结果：共招募了 177 名患者：结果：共招募了 177 名患者：WHO 分级为 2-32 级的患者、WHO 分级为 3-65 级的患者和 WHO 分级为 4-80 级的患者。在上肢，22.7% 的 WHO 2 级患者、62.5% 的 WHO 3 级患者和 75.4% 的 WHO 4 级患者发现 iRMTr 异常。在下肢，23.1% 的 WHO 2 级患者、67.6% 的 WHO 3 级患者和 63.6% 的 WHO 4 级患者的 iRMTr 异常。皮层兴奋性评分（P = .04）与 WHO 分级有显著统计学关系。使用这些变量作为预测因子，ML 模型预测 WHO 4 级病变的准确率为 0.57。在高级别胶质瘤与低级别胶质瘤的亚组分析中，高级别胶质瘤的预测准确率提高到了0.83。在模型中加入分子数据--IDH突变和1p19q编码缺失状态--提高了模型预测肿瘤分级的准确性（分别为0.95和0.74）：结论：基于 nTMS 衍生的大脑半球间兴奋性评估的多重L算法能准确预测影响运动通路的 HGGs。当将分子数据拟合到模型中时，其准确性会进一步提高，这为与放射基因组学联合开展术前研究铺平了道路。
Transcranial Magnetic Stimulation-Based Machine Learning Prediction of Tumor Grading in Motor-Eloquent Gliomas.
Background: Navigated transcranial magnetic stimulation (nTMS) is a well-established preoperative mapping tool for motor-eloquent glioma surgery. Machine learning (ML) and nTMS may improve clinical outcome prediction and histological correlation.
Methods: This was a retrospective cohort study of patients who underwent surgery for motor-eloquent gliomas between 2018 and 2022. Ten healthy subjects were included. Preoperative nTMS-derived variables were collected: resting motor threshold (RMT), interhemispheric RMT ratio (iRMTr)-abnormal if above 10%-and cortical excitability score-number of abnormal iRMTrs. World Health Organization (WHO) grade and molecular profile were collected to characterize each tumor. ML models were fitted to the data after statistical feature selection to predict tumor grade.
Results: A total of 177 patients were recruited: WHO grade 2-32 patients, WHO grade 3-65 patients, and WHO grade 4-80 patients. For the upper limb, abnormal iRMTr were identified in 22.7% of WHO grade 2, 62.5% of WHO grade 3, and 75.4% of WHO grade 4 patients. For the lower limb, iRMTr was abnormal in 23.1% of WHO grade 2, 67.6% of WHO grade 3%, and 63.6% of WHO grade 4 patients. Cortical excitability score ( P = .04) was statistically significantly related with WHO grading. Using these variables as predictors, the ML model had an accuracy of 0.57 to predict WHO grade 4 lesions. In subgroup analysis of high-grade gliomas vs low-grade gliomas, the accuracy for high-grade gliomas prediction increased to 0.83. The inclusion of molecular data into the model-IDH mutation and 1p19q codeletion status-increases the accuracy of the model in predicting tumor grading (0.95 and 0.74, respectively).
Conclusion: ML algorithms based on nTMS-derived interhemispheric excitability assessment provide accurate predictions of HGGs affecting the motor pathway. Their accuracy is further increased when molecular data are fitted onto the model paving the way for a joint preoperative approach with radiogenomics.
期刊介绍：
Neurosurgery, the official journal of the Congress of Neurological Surgeons, publishes research on clinical and experimental neurosurgery covering the very latest developments in science, technology, and medicine. For professionals aware of the rapid pace of developments in the field, this journal is nothing short of indispensable as the most complete window on the contemporary field of neurosurgery.
Neurosurgery is the fastest-growing journal in the field, with a worldwide reputation for reliable coverage delivered with a fresh and dynamic outlook.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
