...
首页> 外文期刊>International Journal of Scientific & Technology Research >A Multivariate Binary Logistic Regression Modeling For Assessing Various Risk Factors That Affect Diabetes
【24h】

A Multivariate Binary Logistic Regression Modeling For Assessing Various Risk Factors That Affect Diabetes

机译:用于评估影响糖尿病的各种风险因素的多元二元Logistic回归模型

获取原文
           

摘要

This study is based on the development of multivariate logistic regression model to assess the effect of various risk factors like age, BMI, meal-regularity and fast-food consumption on the prevalence of diabetes spatially in urban and rural areas of India. The existence of non-multicollinearity, non-normality and non-linearity between the variables was studied. The test-of-association showed that age, BMI and fast-food were significantly associated with diabetes in rural(p1)showed that age and BMI were significant predictors of diabetes. The intake of fast-food has 4.08 times more effect on diabetes than those who do not take. Similarly, the persons with regular nutritional diet were at low risk of getting diabetic. The area under the ROC curve showed the better performance of the model. Hence, the developed logistic regression model can be a powerful statistical technique for identifying the association of most prominent risk factor to diabetes and thus timely notify to take needful actions to reduce the risk of getting diabetes.
机译:这项研究基于多元logistic回归模型的开发,以评估年龄,体重指数,饮食规律和快餐消费等各种风险因素对印度城乡糖尿病患病率的空间影响。研究了变量之间存在非多重共线性,非正态性和非线性的情况。联想测试显示,年龄,BMI和快餐与农村地区的糖尿病显着相关(p1),表明年龄和BMI是糖尿病的重要预测指标。快餐的摄入量对糖尿病的影响是不服用快餐的人的4.08倍。同样,定期营养饮食的人患糖尿病的风险较低。 ROC曲线下的面积显示了该模型的较好性能。因此,开发的逻辑回归模型可以成为一种强大的统计技术,用于识别最突出的危险因素与糖尿病的关联,从而及时通知采取必要的行动以降低患上糖尿病的风险。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号