基于数据挖掘的2型糖尿病风险预测模型的建立和应用
|
摘要
目的采用数据挖掘方法,考察2型糖尿病的危险因素,确定最优风险预测模型,为建立手机APP软件提供算法,为糖尿病I级预防提供风险预测支持。方法收集某医院2016年1月—2017年7月的糖尿病患者全数据集,共5 571例,通过与同期体检健康对照组5 571例进行对比研究,分别建立Logistic回归模型和多层感知器神经网络模型,比较优劣,确定最终预测模型。结果结果显示Logistic回归和多层感知器神经网络模型对训练样本的预测准确率分别为89.7%、80.4%,对测试样本的预测准确率分别为89.8%、79.8%。结论 Logistic回归模型对2型糖尿病风险预测效能较高,预测结果也更容易结合临床实际,用于风险控制手机APP软件后台编程。
Objective To investigate the risk factors of type 2 diabetes by using data mining methods, to determine the optimal risk prediction model, to provide algorithms for establishing mobile APP software, and to provide risk prediction support for diabetes level I prevention. Methods A total of 5 571 patients with diabetes mellitus from January 2016 to July 2017 in the hospital were enrolled. A logistic regression model and a multi-layer perceptron neural network model were established by comparing with 5 571 healthy people in the same period, comparing the pros and cons, determine the final prediction model. Results The results showed that the prediction accuracy of the logistic regression and multi-layer perceptron neural network model for training samples were 89.7% and 80.4%, respectively, and the prediction accuracy for the test samples was 89.8% and 79.8%, respectively. Conclusion Logistic regression model has higher predictive effect on risk of type 2 diabetes, and the prediction results are more easily combined with clinical practice. It is used for background programming of risk control mobile APP software.
Objective To investigate the risk factors of type 2 diabetes by using data mining methods, to determine the optimal risk prediction model, to provide algorithms for establishing mobile APP software, and to provide risk prediction support for diabetes level I prevention. Methods A total of 5 571 patients with diabetes mellitus from January 2016 to July 2017 in the hospital were enrolled. A logistic regression model and a multi-layer perceptron neural network model were established by comparing with 5 571 healthy people in the same period, comparing the pros and cons, determine the final prediction model. Results The results showed that the prediction accuracy of the logistic regression and multi-layer perceptron neural network model for training samples were 89.7% and 80.4%, respectively, and the prediction accuracy for the test samples was 89.8% and 79.8%, respectively. Conclusion Logistic regression model has higher predictive effect on risk of type 2 diabetes, and the prediction results are more easily combined with clinical practice. It is used for background programming of risk control mobile APP software.
引文
[1]Nathan DM.Diabetes:advances in diagnosis and treatment[J].JAMA,2015,314(10):1052-1062.
[2]中华医学会糖尿病学分会.新诊断2型糖尿病患者短期胰岛素强化治疗专家共识[J].中华医学杂志,2013,93(20):1524-1526.
[3]Bhushan R,Elkind-hirsch KE,Bhushan M,et al.Improved glycemic control and reduction of cardiometabolic risk factors in subjects with type 2 diabetes and metabolic syndrome treated with exenatide in a clinical practice setting[J].Diabetes Technol Ther,2009,11(6):353-359.
[4]吴伟,郭军巧,安淑一,等.使用思维进化算法优化的神经网络建立肾综合征出血热预测模型[J].中国卫生统计,2016,33(1):27-30.
[5]叶华容,杨怡,林萱,等.BP神经网络在高频彩超特征诊断乳腺癌中的应用[J].中国卫生统计,2016,33(1):71-72.
[6]Tseng WT,Chiang WF,Liu SY,et al.The application of data mining techniques to oral cancer prognosis[J].J Med Syst,2015,39(5):59-66.
[7]Gonzalez GH,Tahsin T,Goodale BC,et al.Recent advances and emerging applications in text and data mining for biomedical discovery[J].Brief Bioinform,2015,17(1):33-42.
[8]黄雅铃,杨晓波,龙禹,等.广西地区妊娠期糖尿病的危险因素分析及其风险预测模型的建立[J].广西医科大学学报,2017,34(6):835-838.
[9]吕喆,陈亦棋,沈丽君,等.2型糖尿病患者糖尿病视网膜病变风险预测模型的建立和初步验证[J].中华眼底病杂志,2017,33(3).
[10]中华医学会糖尿病学分会.中国2型糖尿病防治指南(2010年版)[J].中国实用乡村医生杂志,2011,20(6):4-5.
[11]中华医学会心血管病学分会,中华心血管病杂志编辑委员会.非ST段抬高急性冠状动脉综合征诊断和治疗指南[J].中华心血管病杂志,2012,40(5):353-367.
[12]党乐,胡雅婷,张永莉.多种抗体检测在甲状腺疾病诊断中的应用价值[J].中国医药导报,2016,13(18):65-68.
[13]杨小军,张雪超,李安琪.利用Excel和Tableau实现业务工作数据化管理[J].电脑编程技巧与维护,2017(12):66-68.
[14]陈春明,孔灵芝.中华人民共和国卫生部疾病控制司.中国成人超重和肥胖症预防控制指南[M].北京:人民卫生出版社,2006.
[15]宋健,吴学森,张杰,等.三种统计学模型在糖尿病个体患病风险预测中的应用[J].中国卫生统计,2017(2):312-314.
[16]赵晓华.基于大数据下2型糖尿病及并发症患者就诊信息的挖掘研究[D].广州:广州中医药大学,2016.
[17]Leon BM,Maddox TM.Diabetes and cardiovascular disease:Epidemiology,biological mechanisms,treatment recommendations and future research[J].World J Diabetes,2015,6(13):1246-1258.
[18]王东营,张琨,许天敏.宫颈癌患病危险因素及一级预防[J].现代肿瘤医学,2017,25(11):1827-1830.
[2]中华医学会糖尿病学分会.新诊断2型糖尿病患者短期胰岛素强化治疗专家共识[J].中华医学杂志,2013,93(20):1524-1526.
[3]Bhushan R,Elkind-hirsch KE,Bhushan M,et al.Improved glycemic control and reduction of cardiometabolic risk factors in subjects with type 2 diabetes and metabolic syndrome treated with exenatide in a clinical practice setting[J].Diabetes Technol Ther,2009,11(6):353-359.
[4]吴伟,郭军巧,安淑一,等.使用思维进化算法优化的神经网络建立肾综合征出血热预测模型[J].中国卫生统计,2016,33(1):27-30.
[5]叶华容,杨怡,林萱,等.BP神经网络在高频彩超特征诊断乳腺癌中的应用[J].中国卫生统计,2016,33(1):71-72.
[6]Tseng WT,Chiang WF,Liu SY,et al.The application of data mining techniques to oral cancer prognosis[J].J Med Syst,2015,39(5):59-66.
[7]Gonzalez GH,Tahsin T,Goodale BC,et al.Recent advances and emerging applications in text and data mining for biomedical discovery[J].Brief Bioinform,2015,17(1):33-42.
[8]黄雅铃,杨晓波,龙禹,等.广西地区妊娠期糖尿病的危险因素分析及其风险预测模型的建立[J].广西医科大学学报,2017,34(6):835-838.
[9]吕喆,陈亦棋,沈丽君,等.2型糖尿病患者糖尿病视网膜病变风险预测模型的建立和初步验证[J].中华眼底病杂志,2017,33(3).
[10]中华医学会糖尿病学分会.中国2型糖尿病防治指南(2010年版)[J].中国实用乡村医生杂志,2011,20(6):4-5.
[11]中华医学会心血管病学分会,中华心血管病杂志编辑委员会.非ST段抬高急性冠状动脉综合征诊断和治疗指南[J].中华心血管病杂志,2012,40(5):353-367.
[12]党乐,胡雅婷,张永莉.多种抗体检测在甲状腺疾病诊断中的应用价值[J].中国医药导报,2016,13(18):65-68.
[13]杨小军,张雪超,李安琪.利用Excel和Tableau实现业务工作数据化管理[J].电脑编程技巧与维护,2017(12):66-68.
[14]陈春明,孔灵芝.中华人民共和国卫生部疾病控制司.中国成人超重和肥胖症预防控制指南[M].北京:人民卫生出版社,2006.
[15]宋健,吴学森,张杰,等.三种统计学模型在糖尿病个体患病风险预测中的应用[J].中国卫生统计,2017(2):312-314.
[16]赵晓华.基于大数据下2型糖尿病及并发症患者就诊信息的挖掘研究[D].广州:广州中医药大学,2016.
[17]Leon BM,Maddox TM.Diabetes and cardiovascular disease:Epidemiology,biological mechanisms,treatment recommendations and future research[J].World J Diabetes,2015,6(13):1246-1258.
[18]王东营,张琨,许天敏.宫颈癌患病危险因素及一级预防[J].现代肿瘤医学,2017,25(11):1827-1830.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |