Prediction of antiepileptic drug treatment outcomes using machine learning
Prediction of antiepileptic drug treatment outcomes using machine learning
复制标题
DOI：
10.1088/1741-2560/14/1/016002
复制
发表时间：
2017-02-01
影响因子：
4
通讯作者：
Bardakjian, Berj L.
中科院分区：
文献类型：
--
作者：
Colic, Sinisa;Wither, Robert G.;Bardakjian, Berj L.
目标。抗癫痫药物（AED）治疗产生不一致的结果，通常需要患者进行多次药物试验，直到找到成功的治疗方法。本研究提出使用机器学习技术来预测常用aed的癫痫治疗结果。的方法。机器学习算法的训练和评估使用了在Rett综合征mecp2缺陷小鼠模型中观察到的癫痫样放电的颅内脑电图（iEEG）记录的特征。先前的工作已经将癫痫样放电中δ (2-5 Hz)节律与快速纹波（400-600 Hz）节律的交叉频率耦合（I-CFC）联系起来。使用ICFC标记治疗后结果，我们比较了支持向量机（svm）和随机森林（RF）机器学习分类器，以提供成功治疗结果的可能性得分。主要的结果。(a) AED治疗结果存在异质性，(b)机器学习技术可用于通过估计成功治疗结果的可能性得分来对AED的疗效进行排名，(c) I-CFC特征产生了最有效的AED治疗的先验识别，(d)两种分类器的表现相当。的意义。机器学习方法可以预测成功的药物治疗结果，从而减少药物试验的负担，并大大改善患者的生活质量。
Objective. Antiepileptic drug (AED) treatments produce inconsistent outcomes, often necessitating patients to go through several drug trials until a successful treatment can be found. This study proposes the use of machine learning techniques to predict epilepsy treatment outcomes of commonly used AEDs. Approach. Machine learning algorithms were trained and evaluated using features obtained from intracranial electroencephalogram (iEEG) recordings of the epileptiform discharges observed in Mecp2-deficient mouse model of the Rett Syndrome. Previous work have linked the presence of cross-frequency coupling (I-CFC) of the delta (2-5 Hz) rhythm with the fast ripple (400-600 Hz) rhythm in epileptiform discharges. Using the ICFC to label post-treatment outcomes we compared support vector machines (SVMs) and random forest (RF) machine learning classifiers for providing likelihood scores of successful treatment outcomes. Main results. (a) There was heterogeneity in AED treatment outcomes, (b) machine learning techniques could be used to rank the efficacy of AEDs by estimating likelihood scores for successful treatment outcome, (c) I-CFC features yielded the most effective a priori identification of appropriate AED treatment, and (d) both classifiers performed comparably. Significance. Machine learning approaches yielded predictions of successful drug treatment outcomes which in turn could reduce the burdens of drug trials and lead to substantial improvements in patient quality of life.