收稿日期: 2014-09-25
修回日期: 2015-03-16
网络出版日期: 2015-11-15
基金资助
国家973重点基础研究发展计划项目(2011CB504601)资助
Juvenile myopia study using modern variable selection methods
Received date: 2014-09-25
Revised date: 2015-03-16
Online published: 2015-11-15
通过分析一组医学数据挖掘出影响青少年近视的关键因素,建立青少年近视患病概率预测模型.数据集主要由两部分组成:一是青少年眼睛的医学测量数据,二是由生活学习习惯调查问卷得到的数据.采用几种现代统计学方法,并利用ROC曲线得到较优的患病概率模型.结果表明,性别、眼轴长度、角膜曲率、工作日睡眠时间、不戴眼镜远视力、远距离调节反应等因素对青少年近视有重要的影响作用,并由此建立预测模型.
关键词： 变量选择; logistic回归; Lasso; MCP; ROC曲线
海豹 , 李仕明 , 刘洛如 , 申立勇 , 张三国 , 李偲圆 , 李翯 , 康梦田 , 孙芸芸 , 孟博 , 张庆昭 . 现代变量选择方法在青少年近视研究中的应用[J]. 中国科学院大学学报, 2015 , 32(6) : 728 -734 . DOI: 10.7523/j.issn.2095-6134.2015.06.002
In this work we used some variable-selection techniques to find out the relevant factors that cause adolescent myopia, and established probabilistic models for myopia prediction. The research is based on a medical dataset consisting of two parts: medical measurement data of the youths and data on daily living habits obtained by questionnaire survey. We used some modern variable selection methods and the ROC curve to evaluate different modes. The results show that gender, axial length, corneal curvature, weekday sleeping time, distance vision without glasses, and remote adjustment reaction have important influences on adolescent myopia.
Key words： variable selection; classical logistic regression; Lasso; MCP; ROC curve
[1] Morgan I G, Ohno-Matsui K, Saw S M. Myopia[J]. The Lancet, 2012, 379(9827):1 739-1 748.
[2] Saw S M, Goh P P, Cheng A, et al. Ethnicity-specific prevalences of refractive errors vary in Asian children in neighbouring Malaysia and Singapore[J]. British journal of ophthalmology, 2006, 90(10):1 230-1 235.
[3] Rose K A, Morgan I G, Ip J, et al. Outdoor activity reduces the prevalence of myopia in children[J]. Ophthalmology, 2008, 115(8):1 279-1 285.
[4] Jones-Jordan L A, Mitchell G L, Cotter S A, et al. CLEERE Study Group. Visual activity before and after the onset of juvenile myopia[J]. Invest Ophthalmol Vis Sci, 2011, 52:1 841-1 850.
[5] French A N, Morgan I G, Mitchell P, et al. Risk factors for incident myopia in Australian schoolchildren:the Sydney adolescent vascular and eye study[J]. Ophthalmology, 2013, 120(10):2 100-2 108.
[6] Rose K A, Morgan I G, Smith W, et al. Myopia, lifestyle, and schooling in students of Chinese ethnicity in Singapore and Sydney[J]. Archives of ophthalmology, 2008, 126(4):527-530.
[7] Mutti D O, Mitchell G L, Moeschberger M L, et al. Parental myopia, near work, school achievement, and children's refractive error[J]. Investigative ophthalmology & visual science, 2002, 43(12):3 633-3 640.
[8] Ip J M, Huynh S C, Robaei D, et al. Ethnic differences in refraction and ocular biometry in a population-based sample of 11-15-year-old Australian children[J]. Eye, 2008, 22(5):649-656.
[9] Borchert M S, Varma R, Cotter S A, et al. Risk factors for hyperopia and myopia in preschool children:the multi-ethnic pediatric eye disease and Baltimore pediatric eye disease studies[J]. Ophthalmology, 2011, 118(10):1 966-1 973.
[10] Li S M, Liu L R, Li S Y, et al. Design, methodology and baseline data of a school-based cohort study in central China:the Anyang childhood eye study[J]. Ophthalmic Epidemiology, 2013, 20:348-359.
[11] 李翯,李仕明,刘洛如,等.河南安阳初中学生眼屈光度及生物学参数分布[J].中华医学杂志,2014,94(17):1 284-1 288.
[12] Tibshirani R. Regression shrinkage and selection via the lasso[J]. Journal of the Royal Statistical Society. Series B (Methodological), 1996:267-288.
[13] Yuan M, Lin Y. Model selection and estimation in regression with grouped variables[J]. Journal of the Royal Statistical Society:Series B (Statistical Methodology), 2006, 68(1):49-67.
[14] Meier L, Van De Geer S, Bühlmann P. The group lasso for logistic regression[J]. Journal of the Royal Statistical Society:Series B (Statistical Methodology), 2008, 70(1):53-71.
[15] Zhang C H. Penalized linear unbiased selection[J]. Department of Statistics, Rutgers University, 2007:2 007-2 003.
[16] Breheny P, Huang J. Penalized methods for bi-level variable selection[J]. Statistics and its Interface, 2009, 2(3):369-380.
[17] Huang J, Breheny P, Ma S. A selective review of group selection in high dimensional models[J]. Statistical Science, 2012, 27:481-499.
[18] Zhou X H, McClish D K, Obuchowski N A.诊断医学统计学[M].北京:人民卫生出版社,2005:13.
/
| 〈 |
|
〉 |
