Support vector machine based classification of smokers and nonsmokers using diffusion tensor imaging.
Support vector machine based classification of smokers and nonsmokers using diffusion tensor imaging.
复制标题
使用扩散张量成像基于支持向量机对吸烟者和非吸烟者进行分类。
DOI：
10.1007/s11682-019-00176-7
复制
发表时间：
2020
影响因子：
3.2
通讯作者：
Yuan Kai
中科院分区：
文献类型：
--
作者：
Zhao Meng;Liu Jingjing;Cai Wanye;Li Jun;Zhu Xueling;Yu Dahua;Yuan Kai
尽管戒烟治疗取得了重大进展，但吸烟仍然是一个重大的公共卫生问题，特别是在年轻的成年人中。因此，开发一种预测模型，可以对基于大脑的生物标志物进行分类和表征，以预测吸烟状态，这对于改善治疗开发至关重要。在这项研究中，我们采用了基于支持向量机的分类方法来区分70名年轻男性吸烟者和70名匹配的非吸烟者使用他们的扩散张量成像（DTI）数据。分类程序实现了88.6%的平均准确度和0.95的平均曲线下面积。最具鉴别力的特征主要位于矢状层（SS）、外囊（EC）、上级纵束（SLF）、前放射冠（ACR）和下前枕束（IFOF）。以下回归分析显示左侧ACR的平均RD值（r =-0.247，p = 0.039）与FTND之间存在显著负相关。右EC的平均MD值（r =-0.254，p = 0.034）和右IFOF的平均RD值（r =-0.240，p = 0.046）与包年呈负相关。我们的研究结果表明，作为大脑生物标志物的区分性白色物质（WM）特征为吸烟状态提供了很大的预测能力，并表明机器学习技术可以揭示潜在的吸烟相关神经生物学。
Despite significant progress in treatments for smoking cessation, smoking continues to be a significant public health concern, especially in young adulthood. Thus, developing a predictive model that can classify and characterize the brain-based biomarkers predicting smoking status would be imperative to improving treatment development. In this study, we applied a support vector machine-based classification method to discriminate 70 young male smokers and 70 matched nonsmokers using their diffusion tensor imaging (DTI) data. The classification procedure achieved an average accuracy of 88.6% and an average area under the curve of 0.95. The most discriminative features that contributed to the classification were primarily located in the sagittal stratum (SS), external capsule (EC), superior longitudinal fasciculus (SLF), anterior corona radiata (ACR) and inferior front-occipital fasciculus (IFOF). The following regression analysis showed a significant negatively correlation between the average RD values of the left ACR (r = −0.247,p= 0.039) and FTND. The average MD values in the right EC (r = −0.254,p= 0.034) and RD values in the right IFOF (r = −0.240,p= 0.046) were inversely associated with pack-years. Our findings indicate that the discriminative white matter (WM) features as brain biomarkers provide great predictive power for smoking status and suggest that machine learning techniques can reveal underlying smoking-related neurobiology.