文献速递神经MR

基于影像组学机器学习模型预测多发性硬化10年临床结局

Predicting 10-Year Clinical Outcomes in MS with Radiomics-Based Machine Learning Models.
PubMed 文献 · AJNR Am J Neuroradiol · 2026-01-05

本研究回顾性分析177例多发性硬化患者的3T脑MRI,基于体积、影像组学和宏观结构失连接特征,用三种机器学习算法构建预测10年确认残疾进展和认知障碍的模型;测试集准确率分别为0.71、0.69、0.67(残疾进展)和0.69、0.64、0.62(认知障碍),模型间无显著差异。

要点

  • 基于常规脑MRI的体积、影像组学和失连接特征可构建多发性硬化10年临床结局预测模型。
  • Extra Trees、逻辑回归和SVM模型预测残疾进展的测试集准确率分别为0.71、0.69和0.67。
  • 三种模型预测认知障碍的测试集准确率分别为0.69、0.64和0.62,模型间无显著差异。

核心结论

  • 基于常规MRI扫描衍生的定量特征,获得了多发性硬化长期预后模型,可能有助于患者分层和临床决策。

研究设计与样本

  • 纵向单中心研究,回顾性分析177例多发性硬化患者的3T结构MRI,基于平均9.4±1.1年的10年临床随访,按确认残疾进展和认知障碍分类,采用留出法随机将患者分为训练集(75%)和测试集(25%)。

诊断标准与关键数值

  • 确认残疾进展通过扩展残疾状态量表评估,认知障碍通过简明国际多发性硬化认知评估 battery 评估;三维T1加权和FLAIR图像自动分割获得116个灰质脑区的体积、失连接评分和影像组学特征。

临床应用与阅片要点

  • Extra Trees模型预测残疾进展的测试集准确率为0.71,逻辑回归为0.69,支持向量机为0.67;预测认知障碍时分别选择16、17和19个特征,测试集准确率分别为0.69、0.64和0.62。

局限性

  • 本研究为单中心研究。
  • 本研究为回顾性分析。
  • 模型验证采用留出法随机分割,测试集样本量有限。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

BACKGROUND AND PURPOSE: Identifying patients with MS at higher risk of clinical progression is essential to inform clinical management. We aimed to build prognostic models by using machine learning (ML) algorithms predicting long-term clinical outcomes based on a systematic mapping of volumetric, radiomic, and macrostructural disconnection features from routine brain MRI scans of patients with MS.

MATERIALS AND METHODS: In this longitudinal monocentric study, 3T structural MRI scans of patients with MS were retrospectively analyzed. Based on a 10-year clinical follow-up (average duration = 9.4 ± 1.1 years), patients were classified according to confirmed disability progression (CDP) and cognitive impairment (CI) as assessed through the Expanded Disability Status Scale and the Brief International Cognitive Assessment of Multiple Sclerosis battery, respectively. Three-dimensional T1-weighted and FLAIR images were automatically segmented to obtain volumes, disconnection scores (estimated based on lesion masks and normative tractography data), and radiomic features from 116 GM regions defined according to the automated anatomic labeling atlas. Three ML algorithms (Extra Trees, Logistic Regression, and Support Vector Machine) were used to build models predicting long-term CDP and CI based on MRI-derived features. Feature selection was performed on the training set with a multistep process, and models were validated with a holdout approach, randomly splitting the patients into training (75%) and test (25%) sets.

RESULTS: We studied 177 patients with MS (men/women = 51/126; mean ± standard deviation age: 35.2 ± 8.7 years). Long-term CDP and CI were observed in 71 and 55 patients, respectively. Regarding the CDP class prediction analysis, the feature selection identified 13-, 12-, and 10-feature subsets obtaining an accuracy on the test set of 0.71, 0.69, and 0.67 for the Extra Trees, Logistic Regression, and Support Vector Machine classifiers, respectively. Similarly, for the CI prediction, subsets of 16, 17, and 19 features were selected, with 0.69, 0.64, and 0.62 accuracy values on the test set, respectively. There were no significant differences in accuracy between ML models for CDP (P = .65) or CI (P = .31).

CONCLUSIONS: Building on quantitative features derived from conventional MRI scans, we obtained long-term prognostic models, potentially informing patients' stratification and clinical decision-making.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Tranfa M, Petracca M, Cuocolo R, et al. Predicting 10-Year Clinical Outcomes in MS with Radiomics-Based Machine Learning Models. AJNR Am J Neuroradiol. 2026. PMID: 40610234. doi:10.3174/ajnr.A8912

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。