Automatic classification and prediction models for early Parkinson's disease diagnosis from SPECT imaging
Automatic classification and prediction models for early Parkinson's disease diagnosis from SPECT imaging
复制标题
DOI：
10.1016/j.eswa.2013.11.031
复制
发表时间：
2014-06-01
影响因子：
8.5
通讯作者：
Ghosh, Shantanu
中科院分区：
文献类型：
--
作者：
Prashanth, R.;Roy, Sumantra Dutta;Ghosh, Shantanu
帕金森病（PD）的早期和准确诊断对于早期管理，适当的治疗和一旦可用就开始神经保护治疗非常重要。最近的神经成像技术，如多巴胺能成像，使用单光子发射计算机断层扫描（SPECT）与I-123-Ioflupane（DaTSCAN）已显示检测甚至早期阶段的疾病。在本文中，我们使用的纹状体结合率（SBR）的值，计算从I-123-loflupane SPECT扫描（从帕金森病进展标志物倡议（PPMI）数据库）开发自动分类和预测/预后模型早期PD。在建模过程中，我们使用了支持向量机（SVM）和逻辑回归。我们观察到，与RBF核的SVM分类器产生了96%以上的高准确性，在早期PD和健康正常的分类对象;和逻辑模型估计PD的风险也产生了高度的拟合与统计学意义，表明其有用的PD风险估计。因此，我们推断这种模型有可能帮助临床医生在PD诊断过程中。(C)2013爱思唯尔有限公司保留所有权利。
Early and accurate diagnosis of Parkinson's disease (PD) is important for early management, proper prognostication and for initiating neuroprotective therapies once they become available. Recent neuroimaging techniques such as dopaminergic imaging using single photon emission computed tomography (SPECT) with I-123-Ioflupane (DaTSCAN) have shown to detect even early stages of the disease. In this paper, we use the striatal binding ratio (SBR) values that are calculated from the I-123-loflupane SPECT scans (as obtained from the Parkinson's progression markers initiative (PPMI) database) for developing automatic classification and prediction/prognostic models for early PD. We used support vector machine (SVM) and logistic regression in the model building process. We observe that the SVM classifier with RBF kernel produced a high accuracy of more than 96% in classifying subjects into early PD and healthy normal; and the logistic model for estimating the risk of PD also produced high degree of fitting with statistical significance indicating its usefulness in PD risk estimation. Hence, we infer that such models have the potential to aid the clinicians in the PD diagnostic process. (C) 2013 Elsevier Ltd. All rights reserved.