Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes.
Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes.
复制标题
DOI：
10.1186/1472-6947-10-16
复制
发表时间：
2010-03-22
影响因子：
3.5
通讯作者：
Khoury MJ
中科院分区：
文献类型：
--
作者：
Yu W;Liu T;Valdez R;Gwinn M;Khoury MJ
我们提出了一种基于支持向量机(SVM)技术的潜在有用的替代方法来对有和没有常见疾病的人进行分类。我们在美国人口的代表性横断面样本中说明了检测糖尿病患者和糖尿病前期患者的方法。我们使用1999-2004年全国健康和营养检查调查(NHANES)的数据来开发和验证两个分类方案的支持向量机模型：分类方案I(诊断或未诊断的糖尿病与糖尿病前期或非糖尿病)和分类方案II(未诊断的糖尿病或糖尿病前期与非糖尿病)。支持向量机模型被用来选择变量集，这些变量集将产生对这些糖尿病类别的个体的最佳分类。在分类方案I中，表现最佳的糖尿病相关变量包括家族史、年龄、种族和民族、体重、身高、腰围、身体质量指数(BMI)和高血压。对于分类方案II，还包括两个额外的变量--性和体力活动。根据ROC曲线下面积，支持向量机模型对分类方案I和II的识别率分别为83.5%和73.2%。开发基于网络的工具-糖尿病分类器是为了演示一个用户友好的应用程序，该应用程序允许使用可配置的、用户定义的阈值进行个人或小组评估。支持向量机建模是一种很有前景的分类方法，用于检测人群中患有糖尿病和糖尿病前期等常见疾病的人。这一方法应该在使用共同变量的其他复杂疾病中进一步探索。
We present a potentially useful alternative approach based on support vector machine (SVM) techniques to classify persons with and without common diseases. We illustrate the method to detect persons with diabetes and pre-diabetes in a cross-sectional representative sample of the U.S. population. We used data from the 1999-2004 National Health and Nutrition Examination Survey (NHANES) to develop and validate SVM models for two classification schemes: Classification Scheme I (diagnosed or undiagnosed diabetes vs. pre-diabetes or no diabetes) and Classification Scheme II (undiagnosed diabetes or pre-diabetes vs. no diabetes). The SVM models were used to select sets of variables that would yield the best classification of individuals into these diabetes categories. For Classification Scheme I, the set of diabetes-related variables with the best classification performance included family history, age, race and ethnicity, weight, height, waist circumference, body mass index (BMI), and hypertension. For Classification Scheme II, two additional variables--sex and physical activity--were included. The discriminative abilities of the SVM models for Classification Schemes I and II, according to the area under the receiver operating characteristic (ROC) curve, were 83.5% and 73.2%, respectively. The web-based tool-Diabetes Classifier was developed to demonstrate a user-friendly application that allows for individual or group assessment with a configurable, user-defined threshold. Support vector machine modeling is a promising classification approach for detecting persons with common diseases such as diabetes and pre-diabetes in the population. This approach should be further explored in other complex diseases using common variables.
登录
查看更多内容
影响因子：
158.5
作者：
Knowler, WC;Barrett-Connor, E;Nathan, DM
通讯作者：
Nathan, DM
影响因子：
16.2
作者：
Franciosi, M;De Berardis, G;Nicolucci, A
通讯作者：
Nicolucci, A
影响因子：
5.8
作者：
Ng, Kwang Loong Stanley;Mishra, Santosh K.
通讯作者：
Mishra, Santosh K.
DOI：
10.1109/pgec.1965.264137
发表时间：
1965-01-01
期刊：
IEEE TRANSACTIONS ON ELECTRONIC COMPUTERS
影响因子：
--
作者：
COVER, TM
通讯作者：
COVER, TM
通过支持向量机，提高生理热闪光测量的性能。
影响因子：
3.7
作者：
Thurston RC;Matthews KA;Hernandez J;De La Torre F
通讯作者：
De La Torre F