使用帮助

当前位置:

首页> 电子期刊 >正文

基于Apriori关联规则的脑卒中危险因素分析

发布日期:2017-12-25
作者:
罗一夫① 何健① 赵会晶① 王晓波*
Author:
LUO YI-fu, HE Jian, ZHAO Hui-jing, et al
单位:
解放军第二一〇医院,116021,辽宁省大连市西岗区胜利路80号
关键词:
脑卒中 危险因素 关联规则挖掘 Apriori算法
Keywords:
stroke, risk factors, association rule mining, Apriori algorithm
分类号:R743.3
出版年,卷(期):页码:2017,12(11):85-88
摘要:

使用大规模脑卒中初筛数据分析,研究脑卒中发病的危险因素规则模式。方法:采集了国家脑卒中筛查与防控数据中心的脑卒中危险因素初筛数据(数据采集于11个省份,共862 244份危险因素初筛表)。筛查了9个与脑卒中发病关联紧密的危险因素。采用关联规则挖掘方法研究了大范围人群中脑卒中发病相关的危险因素,关联规则挖掘采用Apriori算法,选择最小支持度为0.1%,最小置信度为10%,挖掘了脑卒中发病的模式规则。结果:关联规则挖掘结果显示,TIA、房颤或瓣膜性心脏病、脑卒中家族史、高血压、糖尿病是影响脑卒中发病的最主要的危险因素。同时,研究中发现,当年龄超过60岁时,年龄也成为一个影响脑卒中发病的重要危险因素。结论:研究发现了21个大概率导致脑卒中发病的规则模式,其中一些危险因素组合此前并没有得到足够的重视,为临床医学提供了新的有价值的知识。

Abstract:

To study the association between the incidence of stroke and the risk factors using a large-scale stroke screening data. Methods: In this study, the data of stroke risk factors in the National Center for Stroke Screening and Prevention and Control were collected. The data covered 11 provinces and 862 244 respondents. The Risk Factor Screening Table covered nine risk factors closely related to the incidence of stroke. In this study, we used the association rule mining method to study the risk factors of stroke in the large population, and association rules mining uses Apriori algorithm, the minimum support is 0.1%, the minimum confidence is 10%, mining stroke pattern rules. Results: Association rules mining result shows that TIA, atrial fibrillation or valvular heart disease,family history of stroke, hypertension, diabetes is the most important risk factors for the incidence of stroke. At the same time, the study found that when older than 60 years of age, age has also become an important risk factor for the incidence of stroke. Conclusion: We also found 21 presumptive patterns of stroke onset, some of which had not previously received sufficient attention, providing a new valuable knowledge for clinical medicine.

基金项目:
参考文献:

[1] Mosley WJ,Greenland P,Garside DB,et al.Predictive utility of pulse pressur eandother bloodpressure measuresfor cardiovascula routcome [J].Hypertension,2007,49(6):1256-1264.

[2] Zhang XF.Prevalence and Magnitude of Classical Risk Factors for Stroke in a Cohort of 5092 Chinese Steelworkers Over 13.5 Years of Follow-up[J].Stroke,2004,35(5):1052-1056.
[3] Z h a o D , L i u J , W A N G W , e t al.Epidemiological Transition of Stroke in China:twenty-one-year observational study from the Sino-MONICA-Beijing Project[J].Stroke,2008,39(6):1668-1674.
[4] G o A S ,Mo z a f f a r i a n D ,Ro g e r V L , e t al.Heart Disease and Stroke Statistics—2014 Update A Report From the American Heart Association[J].Circulation,2014,129(3):e28-e292.
[5] Wo l f P A ,D' A g o s t i n o RB , B e l a n g e r A J , e t a l . P r o b a b i l i t y o f s t r o k e : a r i s k p r o f i l e f r om t h e F r ami n g h am S t u d y [ J ] .Stroke,1991,22(3):312-318.
[6] Agrawal R,Imielinski T,Swami A,et al.Mining association rules between sets of items in large databases[J].Int Conf Manag Data,1993,22(2):207-216,.
[7] Lewington S,Clarke R,Qizilbash N,et al.Age-specific relevance of usual blood pressure to vascular mortality:a meta-analysis of individual data for one million adults in 61 prospective studies[J].The Lancet,2002,360(9349):1903-1913.
[8] 王维治,矫毓娟.血液病与缺血性卒中[J].中国神经免疫学和神经病学杂志,2001,8(1):40-43.
[9] 孟昭远.脑卒中危险因素研究进展[J].中国慢性病预防与控制,2008,16(5):549-551.
[10] Wiberg B,Sundström J,Arnlö v J,et al.Metabolic Risk Factors for Stroke and Transient Ischemic Attacks in Middle-Aged Men A Community-Based Study With Long-Term Follow-Up[J].Stroke,2006,37(12):2898-2903.
[11] Jenkins AJ,Rowley KG,Lyons TJ,etal.Lipoproteins and diabetic microvascularcomplications[J].Curr Pharm Des,2004,10(27):3395-3418.
 
服务与反馈:
【文章下载】【加入收藏】