小狗阅读会员会员
有解析的医学SCI阅读工具

扫码登录小狗阅读

阅读SCI医学文献

Machine learning analysis of motor evoked potential time series to predict disability progression in multiple sclerosis.

机器学习分析运动诱发电位时间序列预测多发性硬化残疾进展。

  • 影响因子:2.44
  • DOI:10.1186/s12883-020-01672-w
  • 作者列表:"Yperman J","Becker T","Valkenborg D","Popescu V","Hellings N","Wijmeersch BV","Peeters LM
  • 发表时间:2020-03-21
Abstract

BACKGROUND:Evoked potentials (EPs) are a measure of the conductivity of the central nervous system. They are used to monitor disease progression of multiple sclerosis patients. Previous studies only extracted a few variables from the EPs, which are often further condensed into a single variable: the EP score. We perform a machine learning analysis of motor EP that uses the whole time series, instead of a few variables, to predict disability progression after two years. Obtaining realistic performance estimates of this task has been difficult because of small data set sizes. We recently extracted a dataset of EPs from the Rehabiliation & MS Center in Overpelt, Belgium. Our data set is large enough to obtain, for the first time, a performance estimate on an independent test set containing different patients. METHODS:We extracted a large number of time series features from the motor EPs with the highly comparative time series analysis software package. Mutual information with the target and the Boruta method are used to find features which contain information not included in the features studied in the literature. We use random forests (RF) and logistic regression (LR) classifiers to predict disability progression after two years. Statistical significance of the performance increase when adding extra features is checked. RESULTS:Including extra time series features in motor EPs leads to a statistically significant improvement compared to using only the known features, although the effect is limited in magnitude (ΔAUC = 0.02 for RF and ΔAUC = 0.05 for LR). RF with extra time series features obtains the best performance (AUC = 0.75±0.07 (mean and standard deviation)), which is good considering the limited number of biomarkers in the model. RF (a nonlinear classifier) outperforms LR (a linear classifier). CONCLUSIONS:Using machine learning methods on EPs shows promising predictive performance. Using additional EP time series features beyond those already in use leads to a modest increase in performance. Larger datasets, preferably multi-center, are needed for further research. Given a large enough dataset, these models may be used to support clinicians in their decision making process regarding future treatment.

摘要

背景: 诱发电位 (EPs) 是中枢神经系统电导率的量度。它们用于监测多发性硬化症患者的疾病进展。以前的研究仅从EPs中提取了几个变量,这些变量通常进一步浓缩为单个变量: EP评分。我们对运动EP进行机器学习分析,使用整个时间序列而不是几个变量来预测两年后的残疾进展。由于小的数据集大小,获得该任务的实际性能估计一直是困难的。我们最近从比利时Overpelt的康复和MS中心提取了一个EPs数据集。我们的数据集足够大,可以首次获得包含不同患者的独立测试集的性能评估。 方法: 利用高度比较性的时间序列分析软件包,从运动EPs中提取大量的时间序列特征。与目标的互信息和Boruta方法用于发现包含未包括在文献中研究的特征中的信息的特征。我们使用随机森林 (RF) 和逻辑回归 (LR) 分类器来预测两年后的残疾进展。检查添加额外功能时性能提升的统计显著性。 结果: 与仅使用已知特征相比,在运动EPs中包括额外的时间序列特征导致统计学上显著的改善,尽管效果在幅度上是有限的 (对于RF,Δ auc = 0.02,对于LR,Δ auc = 0.05)。具有额外时间序列特征的RF获得最佳性能 (AUC = 0.75 ± 0.07 (平均值和标准差)),考虑到模型中生物标志物的数量有限,这是良好的。RF (非线性分类器) 优于LR (线性分类器)。 结论: 在EPs上使用机器学习方法显示出有希望的预测性能。使用已经使用的EP时间序列特征之外的附加EP时间序列特征导致性能的适度提高。需要更大的数据集,优选多中心,用于进一步研究。给定足够大的数据集,这些模型可以用于支持临床医生在关于未来治疗的决策过程中。

下载该文献
小狗阅读

帮助医生、学生、科研工作者解决SCI文献找不到、看不懂、阅读效率低的问题。提供领域精准的SCI文献,通过多角度解析提高文献阅读效率,从而使用户获得有价值研究思路。

相关文献
影响因子:1.52
发表时间:2020-04-02
DOI:10.1080/09273948.2019.1597896
作者列表:["Apivatthakakul A","Kunavisarut P","Rothova A","Pathanapitoon K"]

METHODS::Purpose: To report on ocular Vogt-Koyanagi-Harada (VKH)-like syndrome under vemurafenib treatment for metastatic melanoma.Design: A case report.Method: Description of clinical and imaging manifestations including fundus photography, fluorescein, and indocyanine green angiography.Results: A 46-year-old Thai female was diagnosed with metastatic melanoma of the skin and had been treated with multiple surgical excisions, radiotherapy, and vemurafenib (initial dose 480 mg orally twice daily, subsequently increased to maximum dose of 960 mg twice daily). After 6 months of vemurafenib use, she complained of bilateral redness and photophobia and was diagnosed with bilateral anterior uveitis, which was topically treated. Two weeks later, her visual acuity (VA) sharply deteriorated to 20/80 and counting fingers. Ocular examination at that stage stronly resembled acute VKH disease. She exhibited intraocular inflammation, and her fundus examination revealed bilateral optic disc swelling and serous retinal detachment. Fluorescein angiogram showed disc leakage and multiple pinpoint hyperfluorescence leakage spots and indocyanine green demonstrated multiple hypofluorescent spots. Oral prednisolone 30 mg/day was commenced while vemurafenib medication was ceased. Three weeks later, her vision improved, and serous retinal detachment subsided. However, her cutaneous melanoma recurred.Conclusions: Vemurafenib, a potential adjunct treatment for metastatic melanoma, was complicated by the development of panuveitis, papillitis, and multiple serous detachments. These ocular symptoms were similar to the presentation of acute VKH syndrome.

翻译标题与摘要 下载文献
影响因子:2.19
发表时间:2020-01-01
DOI:10.1111/dmcn.14268
作者列表:["Crow YJ","Shetty J","Livingston JH"]

METHODS::Comprehensive reviews of the clinical characteristics and pathogenesis of Aicardi-Goutières syndrome (AGS), particularly its contextualization within a putative type I interferonopathy framework, already exist. However, recent reports of attempts at treatment suggest that an assessment of the field from a therapeutic perspective is warranted at this time. Here, we briefly summarize the neurological phenotypes associated with mutations in the seven genes so far associated with AGS, rehearse current knowledge of the pathology as it relates to possible treatment approaches, critically appraise the potential utility of therapies, and discuss the challenges in assessing clinical efficacy. WHAT THIS PAPER ADDS: Progress in understanding AGS disease pathogenesis has led to the first attempts at targeted treatment. Further rational therapies are expected to become available in the short- to medium-term.

关键词: 暂无
翻译标题与摘要 下载文献
影响因子:1.52
发表时间:2020-04-02
DOI:10.1080/09273948.2019.1603312
作者列表:["Takayama K","Obata H","Takeuchi M"]

METHODS::Purpose: To report the efficacy of adalimumab in a case of chronic Vogt-Koyanagi-Harada (VKH) disease refractory to conventional corticosteroids and immunosuppressive therapy and complicated by central serous chorioretinopathy (CSC).Case report: A 66-year-old woman diagnosed with VKH was treated with intravenous corticosteroids followed by oral corticosteroids and cyclosporine. However, systemic corticosteroids could not be tapered because of recurrent ocular inflammation and systemic complications (diabetes mellitus, moon face, bone weakness), while CSC appeared in both eyes. A diagnosis of chronic VKH resistant to medications complicated by corticosteroid-induced CSC was made. Systemic corticosteroids and cyclosporine were tapered and adalimumab initiated. Bilateral ocular inflammation and CSC were gradually reduced and visual acuity improved without any adverse effect. Twelve months after starting adalimumab monotherapy, no signs of active VKH and CSC were present.Conclusions: Adalimumab is one of the effective therapeutic options for refractory VKH disease complicated with corticosteroid-induced adverse effects.

神经系统自身免疫性疾病方向

神经系统自身免疫性疾病是以自身免疫细胞、免疫分子等攻击神经系统为主要致病机制的自身免疫性疾病。在免疫反应中,作用于神经系统自身抗原的致病抗体统称为神经系统自身抗体。

复制标题
发送后即可在该邮箱或我的下载查看该文献
发送
该文献默认存储到我的下载

科研福利

报名咨询

建议反馈
问题标题:
联系方式:
电子邮件:
您的需求: