老年保健人群缺血性心脑血管病预警模型研究
|
摘要
老年保健人群为党和国家建设做出了巨大的贡献。利用现代社会先进医疗技术、信息技术和管理手段,延长老年保健人群寿命,提高老年保健人群生活质量,为该人群提供一个系统、无缝、主动的保健模式是各医疗保健机构任务之一。
自改革开放以来,随着社会经济的快速发展,人民生活水平的不断提高,心脑血管疾病已成为危害我国老年人群身心健康的第一“杀手”。目前,心脑血管疾病防治多基于临床经验,包含太多主观成分,且缺乏量化,尤其对发病率高低不能进行准确预测。为了弥补人工决策的不足,各种疾病预测预警模型研究应运而生。但目前国内外大多数预测模型多为没有心脑血管疾病背景的中年人若干年(一般是10年)的风险概率预警,而没有老年人的预测模型,特别是缺血性心脑血管病(ischemic cardiovascular disease,ICVD)的预测模型国内外尚未见报道。
老年保健人群对医疗保健期望高,但因年龄大,基础疾病多,危险因素暴露时间长,各危险因素之间相互作用关系复杂,疾病预测更加困难。建立此类人群疾病风险预警模型必须考虑所患疾病的整体性、复杂性、动态性以及各危险因素之间的非线性协同作用,传统预警模型很难满足这些要求,而人工神经网络方法以其独特的整体性、系统性、非线性、自学习性、自组织性和极强的容错性等特点,以及并行性信息处理的方法,在危险因素识别、信号处理、辅助决策等众多研究领域取得了显著成效,是目前处理复杂非线性问题的主要方法之一。本研究利用人工神经网络强大的分类与预测功能,研究开发出针对老年保健人群ICVD发病风险的预警模型,用以解决老年保健人群ICVD早期预警关键问题,期望为老年保健人群保健工作和老年人健康管理工作提供科学合理的解决方案。
目的和意义:
1.进一步明确老年保健人群罹患ICVD的危险因素,并进行描述性分析。
2.利用误差逆向传递学习(Back Propagation)人工神经网络(以下简称BP人工神经网络)拟合仿真老年保健人群ICVD的预测模型。
3.建立老年保健人群ICVD的Cox比例风险回归模型。
4.建立基于BP人工神经网络的老年保健人群的ICVD的预测模型。并把预测值与实际患病情况相比较,检验两模型的判别能力、预测准确性以及两模型在个体、群体水平的预测能力。
国内外关于老年人ICVD的预警模型研究尚未见报道,本研究旨在进一步明确老年保健人群罹患该病的危险因素,开发出以这些危险因素为自变量的基于BP人工神经网络模型的预测模型。在充分利用、开发和整理我国特有的干部保健人群的医疗记录的基础上,构建科学实用的资料数据库,重点进行老年保健人群常见重大疾病的早期预警模型研究,并在此基础上开展符合本人群特点的健康促进模式的研究,探索和制定一系列相配套的规范化诊疗程序、综合防治措施和科学管理办法,为临床医疗的循证保健和规范防治提供理论依据和具有可操作性的工作指南,为决策机关制定医疗保健的宏观策略提供信息技术支撑。
方法:
基线人群为2003年5月,在某保健医院数据库记录在案的、出生于1938年1月1日前(即基线年龄大于65岁)的所有保健对象。数据来源有四个渠道:2003年5月的体检资料、历年住院资料、问卷调查资料和电话回访资料。数据随访的截止日期为2009年10月,随访期为6年零4个月(以下简称6年)。数据收集采取了查询电子病历和纸质病例相结合、客观指标测量与问卷调查相结合、现场调查与电话回访相结合的方式,充分挖掘了研究对象的诊疗信息,着重对体检数据、问卷调查数据进行质量控制。
结合国内外研究综述、专家咨询结果、数据库实际情况,本研究纳入预测模型的危险因素有:基线时年龄、体重指数(BMI)、收缩压(SBP)、血总胆固醇浓度(TC)、血甘油三酯浓度(TG)、血高密度脂蛋白浓度(HDL-C)、血肌酐浓度(Scr)、血载脂蛋白A1浓度(ApoAⅠ)、糖尿病和吸烟。
为减少偏性,建模时剔除女性(ICVD阳性事件例数少)和基线时已患有ICVD的男性,按照4:1的比例随机分组基线人群,生成训练组和测试组。分别用BP人工神经网络模型和COX比例风险回归模型拟合各自最优模型。最优模型确定后,将测试人群基线资料分别回代生成预测值。用受试者工作特征曲线(Receiver Operating characteristic Curve,以下简称ROC曲线)下面积大小检验预测模型的判别能力优劣;用Hosmer-Lemeshow检验比较每十分位分组的预测发病率和实际发病率来判断模型预测的准确性;将预测6年老年保健人群ICVD发病风险人群均值与实际观察到的6年累计发病率进行比较,计算误差率,来验证和比较预测模型在群体水平的预测能力。
使用Epidata 3.1软件设计数据录入系统,使用Stata 9/SE软件进行数据清洗、数据分析、绘制图表、建立COX比例风险回归模型,使用Matlab7.0软件构建BP人工神经网络模型。
结果:
1.本研究最终基线人群为2271名65岁以上的老年人,全部为男性,累计观察12852.8人年。在观察期内,因ICVD住院523人(23.03%),因其它原因住院1499人(66.01%),未住院249人(10.96%);在观察期内,因ICVD死亡81人(3.57%),因其它原因死亡370人(16.29%)。ICVD人年发病率为41.63/千人年,累计发病率为23.56%,ICVD累计死亡率为3.57%,ICVD死亡人年率为6.30/千人年。观察期内,按发病系统统计排名前四位的疾病分别是:消化系统疾病、缺血性心血管病、缺血性脑血管病、循环系统疾病(不含ICVD)。心血管疾病发病人数占总人数的比重达到了34.91%,缺血性心脑血管发病人数占心血管发病人数的比重达到了69.86%。从发病排名前十名的病种来看,脑梗死、心肌梗死排名分别是第一、第二。从死亡的疾病病种来看,排名前四名的病种及其占死亡者的百分比分别是:脑梗死35例(7.76%)、心肌梗死32例(7.10%)、上呼吸道感染17例(3.77%)、慢性支气管炎集中发作17例(3.77%),脑梗死及心肌梗死是主要的致死病种。
2.使用寿命表法进行生存分析:ICVD的发病率逐年增高,生存概率逐年下降,第5-6年的失效概率最高,是ICVD的高发期。
3.危险因素与ICVD事件的单因素分析表明:与ICVD事件正相关的变量是:SBP、BMI、TG、TC、ApoAⅠ、糖尿病、吸烟;与ICVD事件负相关的变量是:HDL-C、Scr。
4.构建BP人工神经网络预测模型:将训练数据随机分为训练数据、校验数据,其中训练数据1400人,校验数据417人。使用Matlab7.0编程实现变量值的归一化处理、网络初始化、网络训练、网络仿真。输入层输入神经元的个数与输入变量的个数相同,为10个。隐含层设计为1层,本研究尝试建立了隐单元数从5到15的11个预测模型,通过试验法并结合ROC曲线下面积为筛选最优模型的指标。经过反复训练,当隐单元数为8时,网络训练速度最快,网络震荡小,很快达到预期训练误差,ROC曲线下面积达到最大值,网络此后逐步减小,提示网络判别能力的下降,到隐单元数为12时又缓慢上升,但网络训练速度变慢。训练数据与校验数据ROC曲线下面积的差值也在当隐单元数为8时最小。本研究最终确立隐单元数为8的BP人工神经网络模型为最优模型。输出层设计为1层,输出变量有3个:分别是6年内是否发病,发病则为1,不发病则为0;从基线时到ICVD事件发生的潜隐期;6年ICVD的累计发病率。该网络测试数据的网络仿真结果较好,当训练到7401步时,下降梯度为0,达到要求,训练误差为:0.0923879;隐单元数为8的网络结果最佳,其R值达到了0.914。
5.构建COX比例风险回归模型:把年龄分为两层(大于等于75岁称高龄组;小于75岁称老龄组)时,将除年龄之外的其余不符合正态分布的连续变量仿照弗明汉研究取自然对数值后进行PH(Proportional Hazards)检验,每层的自变量都满足了PH假定,按年龄段作为分层因素引入全部危险因素建立分层COX比例风险回归模型。结果表明:对于老龄组来说,统计学意义显著的危险因素自变量是:年龄、ln(SBP)、ln(Scr)、ln(空腹血糖),保护因素是:ln(HDL-C);对于高龄组来说,统计学意义显著的危险因素自变量是:ln(BMI)、ln(SBP)、ln(TC)、ln(Scr)、ln(空腹血糖),保护因素自变量是:ln(HDL-C)。根据单因素分析和多因素分析的结果,剔除多因素和单因素分析回归系数不显著的自变量,建立分层COX比例风险回归模型。老龄组COX比例风险回归模型最终引入的危险因素自变量是:年龄、ln(SBP)、ln(HDL-C)、ln(Scr)、ln(空腹血糖);高龄组COX比例风险回归模型最终引入的危险因素自变量是:ln(BMI)、ln(SBP)、ln(TC)、ln(HDL-C)、ln(Scr)、ln(空腹血糖)。老龄组6年基线风险概率h(6)=0.254,高龄组h(6)=0.328。
6.模型的验证与比较:将测试组基线资料分别代入最优BP人工神经网络模型和分层COX比例风险回归模型来预测该人群6年间ICVD的发病风险,并与实际的6年发病率比较,绘制ROC曲线。BP人工神经网络模型ROC曲线下面积(AUC)及95% CI为0.892(0.870~0.914),COX比例风险回归模型ROC曲线下面积(AUC)及95% CI为0.723(0.687~0.759),BP人工神经网络模型的判别能力要优于COX比例风险回归模型。将个体按预测ICVD累积发病率从小到大排序,并按十分位数分组,比较每一组预测概率的平均值和实际的累积发病率,BP人工神经网络模型的Hosmer-Lemshow检验:χ2=0.82 , P=0.896 , COX比例风险回归模型的Hosmer-Lemshow检验:χ2=1.43,P=0.786。除第10组预测率高于实际率外,其它组都是预测率略低于实际率。整体上看,两个模型预测都比较准确。预测人群实际累积发病率为26.43%,COX比例风险回归模型预测发病率的平均值为25.84%,误差率为-2.23%;BP人工神经网络模型预测发病率的平均值为26.42%,误差率仅为-0.04%,BP人工神经网络模型群体水平的预测能力优于COX比例风险回归模型。
结论:
1.通过对老年保健人群观察期内ICVD发病和死亡分析,可以看出:ICVD成为老年保健人群慢性病最主要的病种。老年保健人群ICVD发病率高,潜隐期较短,病程较长,疾病负担较重。因此,防治ICVD是老年保健人群健康管理工作的重心之一。
2.通过单因素和多因素分析,SBP、空腹血糖、TC水平是ICVD事件最主要的危险因素,血高密度脂蛋白浓度是最主要的保护因素,因此,控制血压血糖、控制TC水平、提高HDL-C是预防未来ICVD事件的必要措施。
3.本研究将BP人工神经网络应用于老年保健人群ICVD 6年发病率预测,与经典COX比例风险回归模型相比较,BP人工神经网络方法在疾病预测时充分考虑疾病的整体性、动态性和复杂性,凸显其在复杂数据处理时的整体性、系统性、非线性、并行性、自学习性、自组织性和极强容错性等优点。研究进一步发现BP人工神经网络模型的判别能力、预测的准确性、个体、群体水平的预测能力都要优于COX比例风险回归模型,而且对原始数据要求不严、对使用者统计学背景知识要求不高、对缺失数据容错性好、对变量筛选比较宽泛、使用过程方便,易于理解,因此具有一定的应用推广价值。
Aged health care population has made remarkable contributions to the Chinese Communist Party and national reconstruction. Prolonging the life span and improving the quality of the aged health care population and providing a systematic, solid and active health care model for them is responsibility of the health maintenance organizations using advanced medical technology, information technology and management strategy in modern society.
With the rapid development of social economy and increasing improvement in the people’s life quality, ischemic cardiovascular disease (ICVD) has become the first killer. At present,the diagnosis and treatment of ICVD most depend on clinical experience, including too much subjective judgment and lack of precise forecasting for the incidence rate of disease and necessary quantization . In order to make up for the deficiency of human decision-making, kinds of prediction models appear Recently, most models are used to predict the risk rate of the middle aged people usually about 10 years without the background of cardiovascular diseases. However, the expected models of the aged without disease background are limited, especially for the ischemic cerebrovascular disease.
The aged health care population holds high expectations to the medical health care. However, due to their old age, various elementary illness factors and longtime exposure to the dangerous factors, every factor is in complicated relationship with each other. So the establishment of the illness-risk-calculating model for the aged should take the integrity, complexity, dynamic characteristics of the illness and the cooperative relations among these factors into account. The man-made nerve approach is characterized with its comprehensive, systematic, cooperative, self-taught, self-organized properties and the extreme capacity to the mistakes. Moreover, it has made extraordinary achievement in such fields as recognizing dangerous factors, processing information and aiding decision duing to its peculiar structures and information-processing methods. It is one of the main methods to process the complicated non-linear problems. Using the classification and calculation functions of the research of the man-made nerve net, the research develops the illness-risk-calculating model for the aged health care population, thus to solve the key problems of the prior-warning of ischemic cerebrocardiac disease for the aged health care population By doing so, we hold the expectation that we will give a reasonable safeguard scheme for the aged health care population and the corresponding aged health management.
Objective and significance:
1. To study the risk factors and descriptive characteristics of ICVD for the aged health care population .
2. Using Back Propagation(BP) artificial neural network to establish the prediction models of ICVD for the aged health care population.
3. To establish Cox’s proportional hazard (PH) regression model of ICVD for the aged health care population .
4. To establish the prediction models of ICVD for high-ranking military based on BP artificial neural network. comparing the predictive value with the actual situation, testing model’s discrimination ability, prediction accuracy, the predictive power of group level.
The early prediction model of ICVD for the aged are rare at home and abroad, the aim of this study was to found the prediction models based on BP artificial neural network with these risk factors as independent variable, utilizing and sorting the characteristic medical record about cadre health care population in our country, construction a scientific and utility information databases, focused on the study of the early warning model in the common serious disease with health care population, and found the model which is better to healthy accord with the characteristic of this population, exploration and development of a series of supplementary procedures standardization of treatment, comprehensive prevention and control measures and scientific management methods, which can provide theoretical basis and operational work guide for clinical evidence-based care and standard medical care, meanwhile, to develop the macro-strategy for health care information technology support and protection for decision-making bodies.
Methods:
Baseline population is all the total aged health care population that was born before 01.01.1938 (>65 years) that was recorded in the database of the hospital.. All the data were from physical examination data at 05, 2003, hospitalization data of past years, questionnaire and telephone return visit .The deadline of follow-up is 10.2009, and the follow-up period is 6years and 4 months. Data collection through combination of electronic medical record and traditional paper medical record, objective index measurement and questionnaire, field survey and telephone return visit, with emphasis on quality control of physical examination and questionnaire data.
According to the latest development of researches in home and overseas, risk factors involved in the model of this study: Baseline age,body mass index (BMI),systolic blood pressure (SBP),serum total cholesterol (TC),serum triglyceride levels (TG),serum high density lipoprotein levels (HDL-C),serum creatinine levels (Scr), plasma apolipoproteinα1(ApoAⅠ), diabetic mellitus, smoking.
In order to reduce bias, female and male patients underwent ICVD at the baseline time were removed at the establishment of the model. Randomly selected baseline population with a proportion of 4:1, generates module group and verification group. Using BP neural network model and COX PH regression model respectively to fit the optimal model. To verify distinguished ability with area under ROC curve; to verify the predictive veracity through comparing the predictive incidence rate and actual incidence rate of every deciles group by Hosmer-Lemeshow test. To verify the predictive veracity of the prediction model at population level through comparing predictive 6 years incidence rate of ICVD with actual 6 years accumulative incidence rate of ICVD and calculating error rate.
Epidata 3.1 was used to input the data, Stata 9/SE was used to clean data,analyze data, draw chart and establish COX PH regression model, Matlab 7.0 was used to establish BP neural network model.
Result:
1. The baseline population of this study is 2271 cases of old male, and The accumulated personnel year is 12852.8 in the observation. Of that, 523 cases were hospitalized for ICVD (23.03%), 1499 hospitalized for other reasons (66.01%) and 249 without hospitalization experiences (10.96%). 81 died for ICVD (3.57%), and 370 died for other reasons (16.29%). The disease incidence of personnel year of ICVD was 41.63/1000 personnel years and the cumulative life-incidence was 23.56%. The cumulative death rate was 3.57% and death rate of personnel year was 6.30/1000 personnel years. According to the system invaded, the highest rate was diseases of digestive system followed by ICVD, ischemic cerebrovascular diseases and circulatory diseases (ICVD is excluded) one by one. Of all the cases, 34.91% was the incidence of cardiovascular diseases. Of the cases with cardiovascular diseases, 69.86% was ICVD with a relatively long observation. Cerebral infarction incidence was first, followed by myocardial infarction closely. However, the main death reason was disease of respiratory system and disease of digestive system with the shortest observation. In the whole, the reasons and its proportion of death cases were separately cerebral infarction (35 cases, 7.76%), and myocardial infarction (32 cases 7.10%), upper respiratory infection (17 cases 3.77%), and chronic bronchitis (17 cases 3.77%).
2. By life table method, we conclude the incidence of ICVD rises year by year, with the survival rate decreasing meanwhile. The invalid rate reaches the top in the 5th year and 6th year with high incidence of ICVD.
3. By mono-factor analysis of risk factors and ICVD, we conclude variables which are positively correlated with ICVD are SBP, BMI, TG, TC, ApoAⅠ, diabetes, smoking, and variables which are negatively correlated with ICVD are HDL-C、Scr.
4. Construction of BP neural network model Training data was at random divided into training data (1400 persons) and efficacy data (417 persons). By Matlab7.0, we realized random separation, variable normalization, network initialization, network training, network simulation, output function design in training data. Neuronic count of input layer was 10 as the same as input variable. The count of hidden layer was 1. We tried to construct predictive model with hidden units from 5 to 15, taking ROC area under curve as the index which was used to screen the optimal model. After training repeatedly, we conclude that when the hidden unit is 8, network speed is fastest, with the smallest vibration amplitude and the largest index of ROC area under curve. Therefore, the network can reach the expected training error very fast. However, after that, the network decreases gradually, indicating the decrease of net discriminating power. When the hidden unit is 12, the network begins to increase slowly again. The difference of ROC area under curve between training data and efficacy will reach the smallest index when the hidden node is 8. Therefore, when the hidden count is 8, we can obtain the optimal model of BP neural network model 1 output layer and 3 output variables was designed: the number 1 meant that disease occurred within 6 years, and the number 2 meant no incidence within 6 years; from baseline to eclipse period of ICVD; cumulative life-incidence of ICVD within 6 years. This network can obtain good simulation effect. When the training reached 7401 steps, descending gradient became 0, which could meet the requirement. The training error was 0.0923879. When hidden unit was 8, the effect of the network was best, with the index of R reaching 0.914.
5. Construction of COX PH regression models. The factor of age was divided into advanced age group (≥75) and old age group (<75). Except the factor of age, Proportional Hazards(PH)analysis was done for natural logarithm of other continuous variables that did not obey to Gaussian distribution. Independent variables in every layer must obey to presumption. As a result, by the introduction of all the risk factors according to age intervals as layer standard, COX PH regression models was constructed finally. The result of old age group revealed the risk factors of statistical significance were age, ln (SBP)、ln (Scr)、ln (Blood-fasting sugar) and the conservative factor was ln (HDL-C); the result of advanced age group revealed the risk factors of statistical significance were ln (BMI)、ln (SBP)、ln (TC)、ln (Scr)、ln (Blood-fasting sugar) and the conservative factor was ln (HDL-C). According to the results of mono-factor analysis and multiple factors analysis, we rejected the independent variables without statistical significance and then constructed COX PH regression models. Finally, the risk factors induced into the COX PH regression model in the old age group were ln (BMI)、ln (SBP)、ln (TC)、ln (HDL-C)、ln (Scr)、ln (Blood-fasting sugar); the risk factors in the advanced age group were ln (BMI)、ln (SBP)、ln (TC)、ln (HDL-C)、ln (Scr)、ln (Blood-fasting sugar). Baseline risk possibility for 6 years was 0.254 in the old age group and was 0.328 in the advanced age group.
6. Verification and comparison of the model. Baseline data of verification group was put into the optimal BP neural network model and COX PH regression model respectively to anticipate the disease incidence of ICVD for 6 years. According to the contrast of the anticipated index and actual index, ROC curve was constructed. ROC area under curve (AUC) of BP neural network model was 0.892 (0.870~0.914) (95% CI), and ROC AUC of COX PH regression model was 0.723 (0.687~0.759) (95% CI). Thus, the discrimination ability of BP neural network model is considered to better than that of COX PH regression model. Individual cumulative incidence rate of ICVD anticipated was sequenced from the lowest point to the top and then was divided into groups in decile. Mean value of anticipated incidence rate in every group was compared with actual cumulative incidence rate. Hosmer-Lemshow test was used respectively in BP neural network model (χ2=0.82,P =0.896) and COX PH regression model (χ2=1.43,P =0.786). Except the anticipated incidence rate of 10th group, other groups had slightly lower anticipated incidence rate than the actual index. However, generally speaking, both models were relatively accurate. The actual cumulative incidence rate was 26.43%. In contrast, the anticipated mean incidence rate of COX PH regression model was 25.84% with an error rate of﹣2.23%, and that of BP neural network model was 26.42% with a tiny error rate of﹣0.04%. Therefore, the anticipation ability of BP neural network model at population level is better than that of COX PH regression model.
Conclusions:
1. ICVD become the most important chronic diseases in the aged, and in the aged health care population the incidence of ICVD is higher, shorter latency, longer duration and heavier burden. Therefore, prevention of ICVD is one of the most important works of the aged health care population.
2. SBP, fasting blood glucose, TC are major risk factors of ICVD events, HDL-C is the most important protective factor, therefore, the necessary measures to prevent future ICVD are control of blood pressure and blood sugar, total cholesterol levels, increase high density cholesterol level .
3. This study applyed BP neural network to forecast the 6-year incidence of ICVD in the aged health care population. Compared with Cox’s PH regression model, artificial neural network has the advantages of highlights the holistic, systematic, nonlinear, parallel, self-learning, self-organization and strong fault tolerance, and the discriminate ability, prediction accuracy, the predictive power of groups to be superior to the level of Cox’s proportional hazard regression model, but also less demanding on the raw data, and the process is simple, so it have better ability to spread and apply.
自改革开放以来,随着社会经济的快速发展,人民生活水平的不断提高,心脑血管疾病已成为危害我国老年人群身心健康的第一“杀手”。目前,心脑血管疾病防治多基于临床经验,包含太多主观成分,且缺乏量化,尤其对发病率高低不能进行准确预测。为了弥补人工决策的不足,各种疾病预测预警模型研究应运而生。但目前国内外大多数预测模型多为没有心脑血管疾病背景的中年人若干年(一般是10年)的风险概率预警,而没有老年人的预测模型,特别是缺血性心脑血管病(ischemic cardiovascular disease,ICVD)的预测模型国内外尚未见报道。
老年保健人群对医疗保健期望高,但因年龄大,基础疾病多,危险因素暴露时间长,各危险因素之间相互作用关系复杂,疾病预测更加困难。建立此类人群疾病风险预警模型必须考虑所患疾病的整体性、复杂性、动态性以及各危险因素之间的非线性协同作用,传统预警模型很难满足这些要求,而人工神经网络方法以其独特的整体性、系统性、非线性、自学习性、自组织性和极强的容错性等特点,以及并行性信息处理的方法,在危险因素识别、信号处理、辅助决策等众多研究领域取得了显著成效,是目前处理复杂非线性问题的主要方法之一。本研究利用人工神经网络强大的分类与预测功能,研究开发出针对老年保健人群ICVD发病风险的预警模型,用以解决老年保健人群ICVD早期预警关键问题,期望为老年保健人群保健工作和老年人健康管理工作提供科学合理的解决方案。
目的和意义:
1.进一步明确老年保健人群罹患ICVD的危险因素,并进行描述性分析。
2.利用误差逆向传递学习(Back Propagation)人工神经网络(以下简称BP人工神经网络)拟合仿真老年保健人群ICVD的预测模型。
3.建立老年保健人群ICVD的Cox比例风险回归模型。
4.建立基于BP人工神经网络的老年保健人群的ICVD的预测模型。并把预测值与实际患病情况相比较,检验两模型的判别能力、预测准确性以及两模型在个体、群体水平的预测能力。
国内外关于老年人ICVD的预警模型研究尚未见报道,本研究旨在进一步明确老年保健人群罹患该病的危险因素,开发出以这些危险因素为自变量的基于BP人工神经网络模型的预测模型。在充分利用、开发和整理我国特有的干部保健人群的医疗记录的基础上,构建科学实用的资料数据库,重点进行老年保健人群常见重大疾病的早期预警模型研究,并在此基础上开展符合本人群特点的健康促进模式的研究,探索和制定一系列相配套的规范化诊疗程序、综合防治措施和科学管理办法,为临床医疗的循证保健和规范防治提供理论依据和具有可操作性的工作指南,为决策机关制定医疗保健的宏观策略提供信息技术支撑。
方法:
基线人群为2003年5月,在某保健医院数据库记录在案的、出生于1938年1月1日前(即基线年龄大于65岁)的所有保健对象。数据来源有四个渠道:2003年5月的体检资料、历年住院资料、问卷调查资料和电话回访资料。数据随访的截止日期为2009年10月,随访期为6年零4个月(以下简称6年)。数据收集采取了查询电子病历和纸质病例相结合、客观指标测量与问卷调查相结合、现场调查与电话回访相结合的方式,充分挖掘了研究对象的诊疗信息,着重对体检数据、问卷调查数据进行质量控制。
结合国内外研究综述、专家咨询结果、数据库实际情况,本研究纳入预测模型的危险因素有:基线时年龄、体重指数(BMI)、收缩压(SBP)、血总胆固醇浓度(TC)、血甘油三酯浓度(TG)、血高密度脂蛋白浓度(HDL-C)、血肌酐浓度(Scr)、血载脂蛋白A1浓度(ApoAⅠ)、糖尿病和吸烟。
为减少偏性,建模时剔除女性(ICVD阳性事件例数少)和基线时已患有ICVD的男性,按照4:1的比例随机分组基线人群,生成训练组和测试组。分别用BP人工神经网络模型和COX比例风险回归模型拟合各自最优模型。最优模型确定后,将测试人群基线资料分别回代生成预测值。用受试者工作特征曲线(Receiver Operating characteristic Curve,以下简称ROC曲线)下面积大小检验预测模型的判别能力优劣;用Hosmer-Lemeshow检验比较每十分位分组的预测发病率和实际发病率来判断模型预测的准确性;将预测6年老年保健人群ICVD发病风险人群均值与实际观察到的6年累计发病率进行比较,计算误差率,来验证和比较预测模型在群体水平的预测能力。
使用Epidata 3.1软件设计数据录入系统,使用Stata 9/SE软件进行数据清洗、数据分析、绘制图表、建立COX比例风险回归模型,使用Matlab7.0软件构建BP人工神经网络模型。
结果:
1.本研究最终基线人群为2271名65岁以上的老年人,全部为男性,累计观察12852.8人年。在观察期内,因ICVD住院523人(23.03%),因其它原因住院1499人(66.01%),未住院249人(10.96%);在观察期内,因ICVD死亡81人(3.57%),因其它原因死亡370人(16.29%)。ICVD人年发病率为41.63/千人年,累计发病率为23.56%,ICVD累计死亡率为3.57%,ICVD死亡人年率为6.30/千人年。观察期内,按发病系统统计排名前四位的疾病分别是:消化系统疾病、缺血性心血管病、缺血性脑血管病、循环系统疾病(不含ICVD)。心血管疾病发病人数占总人数的比重达到了34.91%,缺血性心脑血管发病人数占心血管发病人数的比重达到了69.86%。从发病排名前十名的病种来看,脑梗死、心肌梗死排名分别是第一、第二。从死亡的疾病病种来看,排名前四名的病种及其占死亡者的百分比分别是:脑梗死35例(7.76%)、心肌梗死32例(7.10%)、上呼吸道感染17例(3.77%)、慢性支气管炎集中发作17例(3.77%),脑梗死及心肌梗死是主要的致死病种。
2.使用寿命表法进行生存分析:ICVD的发病率逐年增高,生存概率逐年下降,第5-6年的失效概率最高,是ICVD的高发期。
3.危险因素与ICVD事件的单因素分析表明:与ICVD事件正相关的变量是:SBP、BMI、TG、TC、ApoAⅠ、糖尿病、吸烟;与ICVD事件负相关的变量是:HDL-C、Scr。
4.构建BP人工神经网络预测模型:将训练数据随机分为训练数据、校验数据,其中训练数据1400人,校验数据417人。使用Matlab7.0编程实现变量值的归一化处理、网络初始化、网络训练、网络仿真。输入层输入神经元的个数与输入变量的个数相同,为10个。隐含层设计为1层,本研究尝试建立了隐单元数从5到15的11个预测模型,通过试验法并结合ROC曲线下面积为筛选最优模型的指标。经过反复训练,当隐单元数为8时,网络训练速度最快,网络震荡小,很快达到预期训练误差,ROC曲线下面积达到最大值,网络此后逐步减小,提示网络判别能力的下降,到隐单元数为12时又缓慢上升,但网络训练速度变慢。训练数据与校验数据ROC曲线下面积的差值也在当隐单元数为8时最小。本研究最终确立隐单元数为8的BP人工神经网络模型为最优模型。输出层设计为1层,输出变量有3个:分别是6年内是否发病,发病则为1,不发病则为0;从基线时到ICVD事件发生的潜隐期;6年ICVD的累计发病率。该网络测试数据的网络仿真结果较好,当训练到7401步时,下降梯度为0,达到要求,训练误差为:0.0923879;隐单元数为8的网络结果最佳,其R值达到了0.914。
5.构建COX比例风险回归模型:把年龄分为两层(大于等于75岁称高龄组;小于75岁称老龄组)时,将除年龄之外的其余不符合正态分布的连续变量仿照弗明汉研究取自然对数值后进行PH(Proportional Hazards)检验,每层的自变量都满足了PH假定,按年龄段作为分层因素引入全部危险因素建立分层COX比例风险回归模型。结果表明:对于老龄组来说,统计学意义显著的危险因素自变量是:年龄、ln(SBP)、ln(Scr)、ln(空腹血糖),保护因素是:ln(HDL-C);对于高龄组来说,统计学意义显著的危险因素自变量是:ln(BMI)、ln(SBP)、ln(TC)、ln(Scr)、ln(空腹血糖),保护因素自变量是:ln(HDL-C)。根据单因素分析和多因素分析的结果,剔除多因素和单因素分析回归系数不显著的自变量,建立分层COX比例风险回归模型。老龄组COX比例风险回归模型最终引入的危险因素自变量是:年龄、ln(SBP)、ln(HDL-C)、ln(Scr)、ln(空腹血糖);高龄组COX比例风险回归模型最终引入的危险因素自变量是:ln(BMI)、ln(SBP)、ln(TC)、ln(HDL-C)、ln(Scr)、ln(空腹血糖)。老龄组6年基线风险概率h(6)=0.254,高龄组h(6)=0.328。
6.模型的验证与比较:将测试组基线资料分别代入最优BP人工神经网络模型和分层COX比例风险回归模型来预测该人群6年间ICVD的发病风险,并与实际的6年发病率比较,绘制ROC曲线。BP人工神经网络模型ROC曲线下面积(AUC)及95% CI为0.892(0.870~0.914),COX比例风险回归模型ROC曲线下面积(AUC)及95% CI为0.723(0.687~0.759),BP人工神经网络模型的判别能力要优于COX比例风险回归模型。将个体按预测ICVD累积发病率从小到大排序,并按十分位数分组,比较每一组预测概率的平均值和实际的累积发病率,BP人工神经网络模型的Hosmer-Lemshow检验:χ2=0.82 , P=0.896 , COX比例风险回归模型的Hosmer-Lemshow检验:χ2=1.43,P=0.786。除第10组预测率高于实际率外,其它组都是预测率略低于实际率。整体上看,两个模型预测都比较准确。预测人群实际累积发病率为26.43%,COX比例风险回归模型预测发病率的平均值为25.84%,误差率为-2.23%;BP人工神经网络模型预测发病率的平均值为26.42%,误差率仅为-0.04%,BP人工神经网络模型群体水平的预测能力优于COX比例风险回归模型。
结论:
1.通过对老年保健人群观察期内ICVD发病和死亡分析,可以看出:ICVD成为老年保健人群慢性病最主要的病种。老年保健人群ICVD发病率高,潜隐期较短,病程较长,疾病负担较重。因此,防治ICVD是老年保健人群健康管理工作的重心之一。
2.通过单因素和多因素分析,SBP、空腹血糖、TC水平是ICVD事件最主要的危险因素,血高密度脂蛋白浓度是最主要的保护因素,因此,控制血压血糖、控制TC水平、提高HDL-C是预防未来ICVD事件的必要措施。
3.本研究将BP人工神经网络应用于老年保健人群ICVD 6年发病率预测,与经典COX比例风险回归模型相比较,BP人工神经网络方法在疾病预测时充分考虑疾病的整体性、动态性和复杂性,凸显其在复杂数据处理时的整体性、系统性、非线性、并行性、自学习性、自组织性和极强容错性等优点。研究进一步发现BP人工神经网络模型的判别能力、预测的准确性、个体、群体水平的预测能力都要优于COX比例风险回归模型,而且对原始数据要求不严、对使用者统计学背景知识要求不高、对缺失数据容错性好、对变量筛选比较宽泛、使用过程方便,易于理解,因此具有一定的应用推广价值。
Aged health care population has made remarkable contributions to the Chinese Communist Party and national reconstruction. Prolonging the life span and improving the quality of the aged health care population and providing a systematic, solid and active health care model for them is responsibility of the health maintenance organizations using advanced medical technology, information technology and management strategy in modern society.
With the rapid development of social economy and increasing improvement in the people’s life quality, ischemic cardiovascular disease (ICVD) has become the first killer. At present,the diagnosis and treatment of ICVD most depend on clinical experience, including too much subjective judgment and lack of precise forecasting for the incidence rate of disease and necessary quantization . In order to make up for the deficiency of human decision-making, kinds of prediction models appear Recently, most models are used to predict the risk rate of the middle aged people usually about 10 years without the background of cardiovascular diseases. However, the expected models of the aged without disease background are limited, especially for the ischemic cerebrovascular disease.
The aged health care population holds high expectations to the medical health care. However, due to their old age, various elementary illness factors and longtime exposure to the dangerous factors, every factor is in complicated relationship with each other. So the establishment of the illness-risk-calculating model for the aged should take the integrity, complexity, dynamic characteristics of the illness and the cooperative relations among these factors into account. The man-made nerve approach is characterized with its comprehensive, systematic, cooperative, self-taught, self-organized properties and the extreme capacity to the mistakes. Moreover, it has made extraordinary achievement in such fields as recognizing dangerous factors, processing information and aiding decision duing to its peculiar structures and information-processing methods. It is one of the main methods to process the complicated non-linear problems. Using the classification and calculation functions of the research of the man-made nerve net, the research develops the illness-risk-calculating model for the aged health care population, thus to solve the key problems of the prior-warning of ischemic cerebrocardiac disease for the aged health care population By doing so, we hold the expectation that we will give a reasonable safeguard scheme for the aged health care population and the corresponding aged health management.
Objective and significance:
1. To study the risk factors and descriptive characteristics of ICVD for the aged health care population .
2. Using Back Propagation(BP) artificial neural network to establish the prediction models of ICVD for the aged health care population.
3. To establish Cox’s proportional hazard (PH) regression model of ICVD for the aged health care population .
4. To establish the prediction models of ICVD for high-ranking military based on BP artificial neural network. comparing the predictive value with the actual situation, testing model’s discrimination ability, prediction accuracy, the predictive power of group level.
The early prediction model of ICVD for the aged are rare at home and abroad, the aim of this study was to found the prediction models based on BP artificial neural network with these risk factors as independent variable, utilizing and sorting the characteristic medical record about cadre health care population in our country, construction a scientific and utility information databases, focused on the study of the early warning model in the common serious disease with health care population, and found the model which is better to healthy accord with the characteristic of this population, exploration and development of a series of supplementary procedures standardization of treatment, comprehensive prevention and control measures and scientific management methods, which can provide theoretical basis and operational work guide for clinical evidence-based care and standard medical care, meanwhile, to develop the macro-strategy for health care information technology support and protection for decision-making bodies.
Methods:
Baseline population is all the total aged health care population that was born before 01.01.1938 (>65 years) that was recorded in the database of the hospital.. All the data were from physical examination data at 05, 2003, hospitalization data of past years, questionnaire and telephone return visit .The deadline of follow-up is 10.2009, and the follow-up period is 6years and 4 months. Data collection through combination of electronic medical record and traditional paper medical record, objective index measurement and questionnaire, field survey and telephone return visit, with emphasis on quality control of physical examination and questionnaire data.
According to the latest development of researches in home and overseas, risk factors involved in the model of this study: Baseline age,body mass index (BMI),systolic blood pressure (SBP),serum total cholesterol (TC),serum triglyceride levels (TG),serum high density lipoprotein levels (HDL-C),serum creatinine levels (Scr), plasma apolipoproteinα1(ApoAⅠ), diabetic mellitus, smoking.
In order to reduce bias, female and male patients underwent ICVD at the baseline time were removed at the establishment of the model. Randomly selected baseline population with a proportion of 4:1, generates module group and verification group. Using BP neural network model and COX PH regression model respectively to fit the optimal model. To verify distinguished ability with area under ROC curve; to verify the predictive veracity through comparing the predictive incidence rate and actual incidence rate of every deciles group by Hosmer-Lemeshow test. To verify the predictive veracity of the prediction model at population level through comparing predictive 6 years incidence rate of ICVD with actual 6 years accumulative incidence rate of ICVD and calculating error rate.
Epidata 3.1 was used to input the data, Stata 9/SE was used to clean data,analyze data, draw chart and establish COX PH regression model, Matlab 7.0 was used to establish BP neural network model.
Result:
1. The baseline population of this study is 2271 cases of old male, and The accumulated personnel year is 12852.8 in the observation. Of that, 523 cases were hospitalized for ICVD (23.03%), 1499 hospitalized for other reasons (66.01%) and 249 without hospitalization experiences (10.96%). 81 died for ICVD (3.57%), and 370 died for other reasons (16.29%). The disease incidence of personnel year of ICVD was 41.63/1000 personnel years and the cumulative life-incidence was 23.56%. The cumulative death rate was 3.57% and death rate of personnel year was 6.30/1000 personnel years. According to the system invaded, the highest rate was diseases of digestive system followed by ICVD, ischemic cerebrovascular diseases and circulatory diseases (ICVD is excluded) one by one. Of all the cases, 34.91% was the incidence of cardiovascular diseases. Of the cases with cardiovascular diseases, 69.86% was ICVD with a relatively long observation. Cerebral infarction incidence was first, followed by myocardial infarction closely. However, the main death reason was disease of respiratory system and disease of digestive system with the shortest observation. In the whole, the reasons and its proportion of death cases were separately cerebral infarction (35 cases, 7.76%), and myocardial infarction (32 cases 7.10%), upper respiratory infection (17 cases 3.77%), and chronic bronchitis (17 cases 3.77%).
2. By life table method, we conclude the incidence of ICVD rises year by year, with the survival rate decreasing meanwhile. The invalid rate reaches the top in the 5th year and 6th year with high incidence of ICVD.
3. By mono-factor analysis of risk factors and ICVD, we conclude variables which are positively correlated with ICVD are SBP, BMI, TG, TC, ApoAⅠ, diabetes, smoking, and variables which are negatively correlated with ICVD are HDL-C、Scr.
4. Construction of BP neural network model Training data was at random divided into training data (1400 persons) and efficacy data (417 persons). By Matlab7.0, we realized random separation, variable normalization, network initialization, network training, network simulation, output function design in training data. Neuronic count of input layer was 10 as the same as input variable. The count of hidden layer was 1. We tried to construct predictive model with hidden units from 5 to 15, taking ROC area under curve as the index which was used to screen the optimal model. After training repeatedly, we conclude that when the hidden unit is 8, network speed is fastest, with the smallest vibration amplitude and the largest index of ROC area under curve. Therefore, the network can reach the expected training error very fast. However, after that, the network decreases gradually, indicating the decrease of net discriminating power. When the hidden unit is 12, the network begins to increase slowly again. The difference of ROC area under curve between training data and efficacy will reach the smallest index when the hidden node is 8. Therefore, when the hidden count is 8, we can obtain the optimal model of BP neural network model 1 output layer and 3 output variables was designed: the number 1 meant that disease occurred within 6 years, and the number 2 meant no incidence within 6 years; from baseline to eclipse period of ICVD; cumulative life-incidence of ICVD within 6 years. This network can obtain good simulation effect. When the training reached 7401 steps, descending gradient became 0, which could meet the requirement. The training error was 0.0923879. When hidden unit was 8, the effect of the network was best, with the index of R reaching 0.914.
5. Construction of COX PH regression models. The factor of age was divided into advanced age group (≥75) and old age group (<75). Except the factor of age, Proportional Hazards(PH)analysis was done for natural logarithm of other continuous variables that did not obey to Gaussian distribution. Independent variables in every layer must obey to presumption. As a result, by the introduction of all the risk factors according to age intervals as layer standard, COX PH regression models was constructed finally. The result of old age group revealed the risk factors of statistical significance were age, ln (SBP)、ln (Scr)、ln (Blood-fasting sugar) and the conservative factor was ln (HDL-C); the result of advanced age group revealed the risk factors of statistical significance were ln (BMI)、ln (SBP)、ln (TC)、ln (Scr)、ln (Blood-fasting sugar) and the conservative factor was ln (HDL-C). According to the results of mono-factor analysis and multiple factors analysis, we rejected the independent variables without statistical significance and then constructed COX PH regression models. Finally, the risk factors induced into the COX PH regression model in the old age group were ln (BMI)、ln (SBP)、ln (TC)、ln (HDL-C)、ln (Scr)、ln (Blood-fasting sugar); the risk factors in the advanced age group were ln (BMI)、ln (SBP)、ln (TC)、ln (HDL-C)、ln (Scr)、ln (Blood-fasting sugar). Baseline risk possibility for 6 years was 0.254 in the old age group and was 0.328 in the advanced age group.
6. Verification and comparison of the model. Baseline data of verification group was put into the optimal BP neural network model and COX PH regression model respectively to anticipate the disease incidence of ICVD for 6 years. According to the contrast of the anticipated index and actual index, ROC curve was constructed. ROC area under curve (AUC) of BP neural network model was 0.892 (0.870~0.914) (95% CI), and ROC AUC of COX PH regression model was 0.723 (0.687~0.759) (95% CI). Thus, the discrimination ability of BP neural network model is considered to better than that of COX PH regression model. Individual cumulative incidence rate of ICVD anticipated was sequenced from the lowest point to the top and then was divided into groups in decile. Mean value of anticipated incidence rate in every group was compared with actual cumulative incidence rate. Hosmer-Lemshow test was used respectively in BP neural network model (χ2=0.82,P =0.896) and COX PH regression model (χ2=1.43,P =0.786). Except the anticipated incidence rate of 10th group, other groups had slightly lower anticipated incidence rate than the actual index. However, generally speaking, both models were relatively accurate. The actual cumulative incidence rate was 26.43%. In contrast, the anticipated mean incidence rate of COX PH regression model was 25.84% with an error rate of﹣2.23%, and that of BP neural network model was 26.42% with a tiny error rate of﹣0.04%. Therefore, the anticipation ability of BP neural network model at population level is better than that of COX PH regression model.
Conclusions:
1. ICVD become the most important chronic diseases in the aged, and in the aged health care population the incidence of ICVD is higher, shorter latency, longer duration and heavier burden. Therefore, prevention of ICVD is one of the most important works of the aged health care population.
2. SBP, fasting blood glucose, TC are major risk factors of ICVD events, HDL-C is the most important protective factor, therefore, the necessary measures to prevent future ICVD are control of blood pressure and blood sugar, total cholesterol levels, increase high density cholesterol level .
3. This study applyed BP neural network to forecast the 6-year incidence of ICVD in the aged health care population. Compared with Cox’s PH regression model, artificial neural network has the advantages of highlights the holistic, systematic, nonlinear, parallel, self-learning, self-organization and strong fault tolerance, and the discriminate ability, prediction accuracy, the predictive power of groups to be superior to the level of Cox’s proportional hazard regression model, but also less demanding on the raw data, and the process is simple, so it have better ability to spread and apply.
引文
[1] Marmot MG. Interpretation of trends in coronary heart disease mortality[J] Acta Med Scand, 1985, 701(suppl): 58-65
[2] Zhou B, zhang H, Wu Y, et al. Ecological analysis of the association between incidence and risk factors of coronary heart disease and stroke in Chinese populations[J]. CVD Prevent, 1998,1: 207-216
[3] Yangfeng Wu, Xiaoqing Liu, Xian Li. et al. Estimation of 10-Year Risk of Fatal and Nonfatal Ischemic Cardiovascular Diseases in Chinese Adults[J]. Circulation, 2006, 114:2217-225
[4]李慧凤,王萍,王鸿雁等.“国人缺血性心血管病发病危险简易评估工具”在青岛地区的临床应用及分析[J].中华心血管病杂志,2005,33(2):178-180
[5]程宇宁,焦宝明,杨向阳.“国人缺血性心血管病发病危险简易评估工具”在我部男性体检人群中的应用分析[J].实用医学杂志,2007,23(19):3093-3095
[6]王征,向新生,徐华泉等.“国人缺血性心血管病发病危险简易评估工具”在疗养院的应用[J].中国疗养医学,2007,16(10):598-600
[7] Andrew Moran, Dong Zhao, Dongfeng Gu, etc. The future impact of population growth and aging on coronary heart disease in China: projections from the coronary heart disease policy model-China[J]. BMC Public Health, 2008, 8: 394
[8] Anderson KM, Odell PM, Wilson PWF, et al. Cardiovascular disease risk profiles[J]. Am Heart J, 1991 ;121:293-298
[9]国家“十五”攻关“冠心病、脑卒中综合危险度评估及干预方案的研究”课题组.国人缺血性心血管病发病危险的评估方法及简易评估工具的开发研究[J].中华心血管病杂志,2003,31(12):893-901
[10] Hansson L, Zanchetti A, Carruthers SG., et al. Effects of intensive blood-pressure lowering and low-dose aspirin in patients with hypertension: principle results of the Hypertension: principle results of the Hypertension Optimal Treatment (HOT) randomized trial. Lancer,1998,351:1755-1762
[11] WHO. Multination monitoring of treads and determinants in cardiovascular disease (MONICA project) and manual of operation. Geneva: WHO Cardiovascular Disease Unit,1993
[12]吕卓人.心血管病危险控制与循证医学[J].华夏医药,2002,(3):3-7
[13] Epstein FH, Ostrander LD Jr, Johnson BC, et al. Epidemiological studies of cardiovascular disease in a total community-Tecumeh, Michigan[J]. Ann Intern Med,1965;72:1170
[14] Truett J, Cornfield J, Kannel W. A Multivariate analysis of the risk of coronary heart disease in Framingham[J]. J Chron Dis, 1967,20: 511-524
[15] Kannel WB, McGee D, Gordon T. A general Cardiovascular risk profile: the Framingham Study. Am J Cardiol, 1976; 38: 46-51
[16] Anderson KM, Wilson PWF, Odell PM, et al. An updated coronary risk profile: a statement for health professionals. Circulation,1991,83: 356-362
[17] Wilson PWF, D’Agostino RB, Levy D,et al. Prediction of coronary heart disease using risk factor categories. Circulation,1998, 97: 1837-1847
[18] McGee D, Gordon T. The results of the Framingham study applied to four other US based studies of cardiovascular disease in: Kannel WB, Gordon T (eds).The Framingham study, an Epidemiology investigations of cardiovascular Disease. DHEW Publication No.(NIH) 76-1083, 1976. Washington DC, US Government Printing Office.
[19] Truelsen T, Lindenstorn E, Boysen G. Comparison of probability of stroke between the Copenhagen City Heart Study and the Framingham Study. Storke, 1994,25: 802-807
[20] Wood D, De Backer G, Faergeman D, et al. Prevention of coronary heart disease in clinical practice: recommendations of the second joint Task Force of European and other societies on Coronary Prevention. Atherosclerosis, 1998, 140: 199-270
[21] Sheridan SL, Crespo E. Does the routine use of global coronary heart disease risk scores translate into clinical benefits of harms? A systematic review of the literature [J] .BMC Health Services Research,2008,8:60
[22] Matthew W Knuiman, Hien V Vu. Prediction of coronary heart disease mortality in Busselton. Western Australia: an evaluation of the Framingham, national health epidemiologic follow up study, and WHO ERICA risk scores. J Epidemiol Community Health, 1997, 51: 515-519
[23] Liao Y, McGee DL, Cooper RS, et al. How generalizable are coronary risk prediction models? Comparison of Framingham and two national cohorts. Am Heart Journal,1999, 137:837-845
[24] Oxford JL, Sesso HO, Steelman M , et al. A comparison of the Framingham and European Society of cardiology coronary heart disease risk prediction models in the Normative aging Study. Am Heart J, 2002, 144:95-100
[25] Menotti A, Puddu PE, Lanti M. Comparison of the Framingham risk function-based coronary chart with risk function from an Italian population study. Eur Heart J, 2000, 21:365-370
[26] Gordon T, Carcia-Palmieri MR, Kagan A, et al. Differences in coronary heart disease in Framingham, Honoluu and Puerto Rico. J of Chronic Disease, 1974;27:329-344
[27] Troels F Thomsen, Dan McGee, Michael Davidsen, et al. A cross-validation of risk-scores for coronary heart disease mortality based on data from the Glostrup population studies and Framingham Heart Study. Int J Epidemiol, 2002;31:817-822.
[28] D’Agostino RB, Vasan RS, Pencina MJ, et al. General Cardiovascular Risk Profile for use in primary care: The Framingham heart study[J]. Circulation, 2008(12): 743-752
[29] Berry JD, Lloyd-Jones DM, Garside DB, et al. Framingham risk score and prediction of coronary heart disease death in young men. Am Heart J, 2007, 154(1):80-86
[30] Grundy SM, D’Agostino RB, Mosca L, et al. Cardiovascular risk assessment based on US Cohort studies: finding form a National Heart,Lung,and Blood Institute workshop. Circulation,2001,104: 491-496
[31] D’Agostino RB, Russell MW, Huse DM, et al. Primary and subsequent coronary risk appraisal: new results from the Framingham study. Am Heart J, 2000, 139: 272-281
[32] Tunstall-Pedoe H. The Dundee coronary risk-disk for management of change in risk factors. BMJ,1991,303:744-747
[33] Conroy RM. Pyorala K, Fitzgerald AP, et al. Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. Eur Heart J , 2003, 24: 987-1003
[34] Voss R, Cullen P, Schulte H, et al. Prediction of risk of coronary events in middle-aged men in the Prospective Cardiovascular Munster Study (PROCAM) using neural networks. Int j Epidemiol 2002, 31:1253-1262
[35] Pocock SJ, McCormack V,Gueyffier Francois,et al . A Score for predicting risk of death from cardiovascular disease in adults with raised blood pressure,based onindividual patient data from randomized controlled trials,BMJ,2001.323(7304):75-81
[36] D’Agostino RB, Grundy S, Sullivan LM, et al. Validation of the Framingham coronary heart disease prediction scores: results of a multiple ethnic groups investigation. JAMA,2001;286: 180-187
[37] Brindle P, May M, Gill PS, et al. Primary prevention of cardiovascular disease: a web-based risk score for seven British black and minority ethnic groups. Heart, hrt 2006
[38] Woodward M, Brindle P, Tunstall-Pedoe H. Adding social deprivation and family history to cardiovascular risk assessment: the ASSIGN score from the scottish Heart Health Extended Cohort (SHHEC). Heart,2007,93:172-176
[39] Julia Hippisley-Cox, Carol Coupland, Yana Vinogradova, et al. Derivation and validation of QRISK, a new cardiovascular disease risk score for the United Kingdom: prospective open cohort study, BMJ, 2007,335: I36
[40] Julia Hippisley-Cox, Carol Coupland, Yana Vinogradova, et al. Predicting cardiovascular risk in England and Wales: prospective derivation and validation of QRISK2, BMI, 2008;336: 1475-1482
[41]赵冬、吴兆苏、王薇等.中国11省市队列人群基线血压和7年累积心血管病发病危险的前瞻性研究应用研究.中华心血管病杂志,2001,29:612-617
[42] Wu Y, Liu X, Li Xian, et al. Estimation of 10-year risk of fatal and nonfatal ischemic cardiovascular disease in Chinese adults. Circulation, 2006, 114:2217-2225
[43] Charalambous C.Conjugate gradient algorithm for efficient training of artificial neural networks. IEEE Proceedings, 1992,(139): 301-310
[44] Grossberg S. Studies of the Mind and Brain. Holland: Reidel Press, 1982
[45] Hagan MT, Menhaj M. Training feed forward networks with the Marquardt algorthm. IEEE Transactions on Neural Networks, 1994,5(6): 6989-6993
[46] Hagan MT, Demuth HB, Beale. Neural Network Design.. Boston MA: PWS Publishing, 1996
[47] Funahshi K I., On the Approximate Realization of Continuous Mappings by Neutral Networks[J]. Neural Network, 1989, 2: 183-192
[48] Hornik K, Strinchcomber M, Whiter H., Multilayer Feedforward Networks Are 110Universal Approximators, Neural Networks. 1989,2: 359-366
[49] Honik K., Approximation Capabilities of Multilayer Feedforward Networks Neural, Neural Network, 1991, 4: 551-557
[50]陈天平,神经网络及其在系统识别应用中的逼近问题,中国科学(A辑), 1994, 24 (1): 1-7
[51] M. Pachter, P.R. Chandler, Challenges of Autonomous Control, IEEE Control Systems, Aug. 1998: 92-97
[52] Panos J. Antsaklis, Kevin M. Passino, S.J. Wang, An Introduction to Autonomous Control Systems, IEEE Control Systems, June 1991: 5-13
[53] Manu Sharma, Anthony J. Calise, J. Eric Corban, Application of An Adaptive Autopilot Design to A Family Guided Munitions, AIAA Guidance, Navigation and Control Conference, Denver CO. AIAA 2000-3969, Aug. 2000
[54] H. Jin Kim, David H. Shim, A Flight Control System for Aerial Robots: Algorithms and Experiments, Control Engineering Practice, 2003(11):1389–1400
[55] J. S. Brinker, K. A. Wise, Flight Testing of A Reconfigure Flight Control Law on the X-36 Tailless Flight Aircraft, In Proc. of the AIAA Guidance, Navigation and Control Conference, AIAA-00-3941, Aug. 2000
[56] Manu Sharma, A Neuro-Adaptive Autopilot Design for Guided Munitions, Ph. D. Thesis, Georgia Institute of Technology, Atlanta, 2001
[57] A. J. Calise, M. Sharma, E. Corban, An Adaptive Autopilot Design for Guided Munitions, AIAA J. Guidance, Control and Dynamics, 2000
[58] Perry Walter Stout, Combined Dynamic Inversion and QFT Flight Control of An Unstable High Performance Aircraft, Ph. D. Thesis, University of California, 1999
[59] Flavio Nardi, Neural Network Based Adaptive Algorithms for Nonlinear Control, Ph. D. Thesis, Georgia Institute of Technology, Atlanta, 2000
[60] C. H. Lee, M. H. Shin, M. J. Chung, A Design of Gain-Scheduled Control for A Linear Parameter Varying System: An Application to Flight Control, Control Engineering Practice, 2001(9): 11-21
[61] A. Isidori, Nonlinear Control Systems, Springer-Verlag, Ltd, London, UK, 3rd, edition, 1995
[62] Daniel Liberzon, A. Stephen Morse and Eduardo D. Sontag, Out-Input Stability andMinimum-Phase Nonlinear Systems, IEEE Trans. on Automatic Contr., 2002, 47(3): 422-436
[63] Emmanuel Hygounenc, Il-Kyun Jung, The Autonomous Blimp Project of LAAS-CNRS: Achievements in Flight Control and Terrain Mapping, The International Journal of Robotics Research, April-May 2004: 474-511
[64] Nazmi A. Mahmoud, Hassan K. Khalil, Asymptotic Regulation of Minimum Phase Nonlinear Systems using Output Feedback, IEEE Trans. on Automatic Contr., 1996, 41(10):1402-1412
[65] Alberto Isidori, Christopher I. Byrnes, Output Regulation of Nonlinear Systems, IEEE Trans. on Automatic Contr., 1990, 35(2):131-140
[66] Brianl. Stevens, Frank L. Lewis, Aircraft Control and Simulation, John Wiley and Sons, Inc., 2nd, edition, 2003.IEEE Trans. on Automatic Contr., 1998, 43(3): 386-391
[67] Ahmed Mohammed Dabroom, Hassan K. Khalil, Output Feedback Sampled-Data Control of Nonlinear Systems using High-Gain Observers, IEEE Trans. on Automatic Contr., 2001, 46(11): 1712-1725
[68] J?rg Mareczek, Martin Buss, Mark W. Spong, Invariance Control for A Class of Cascade Nonlinear Systems, IEEE Trans. on Automatic Control, 2002, 47(4): 636-640
[69] A. N. Atassi, H. K. Khalil, A Separation Principle for the Control of A Class of Nonlinear Systems, IEEE Trans. on Automatic Contr., 2001, 46(5): 742-746
[70] Raffaella De Santis, Alberto Isidori, On the Output Regulation for Linear Systems in the Presence of Input Saturation, IEEE Trans. on Automatic Contr., 2001, 46(1): 156-160
[71] Carlos E. T. D′orea , Bas′ylio E. A. Milani, Disturbance Decoupling in A Class of Linear Systems, IEEE Trans. on Automatic Contr., 1997, 42(10): 1427-1431
[72] Delin Chu, Volker Mehrmann, Disturbance Decoupling for Linear Time-Invariant Systems: A Matrix Pencil Approach, IEEE Trans. on Automatic Contr., 2001, 46(5): 802-808
[73] Wilson J. Rugha, Jeff S. Shamma, Research on Gain Scheduling, Automatica 36 2000: 1401-1425
[74] Widrow B,Hoff ME,Adaptive Switching circuits. 1960 IRE WESCON ConventionRecord. New York IRE,1960:96-104
[75] Widrow B, Sterms SD. Adaptive Signal Processing. New York: Prentine-Hall, 1985
[76]周礼果.人工神经网络在生物医学中的应用[J].国外医学生物医学工程分册,1996,19(1):40-45
[77] Edith Lahner, Marco Intraligi, Massimo Buscema, et al. Artificial neural networks in the recognition of the presence of thyroid disease in patients with atroplic body gastritis[J]. World Journal of Castroenterology, 2008, 14(4): 563-568
[78]阿伯基斯[美]著.神经网络模式识别及其实现[M].北京:电子工业出版社,1999
[79]陈明.神经网络模型[M].大连:大连理工大学出版社,1995
[80]袁曾任.人工神经网络及其应用[M].北京:清华大学出版社,1999
[81]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998
[82]王伟.人工神经网络原理:入门与应用[M].北京:北京航天航空大学出版社,1995
[83]姚敏.一种前向网络的多准则学习方法[J].通信学报,1996,17(4):113-117
[84]周继成.人工神经网络-第六代计算机的实现[M].北京:科学普及出版社,1993
[85]孙巧萍,姚敏.人工神经网络的模糊学习方法[J].计算机工程与设计,1999,20(6):14-16
[86] Alvager T, Graham G, Hutchison D. Neural Network Method to analyze data compression in DNA and RNA sequences[J]. J Chem Comput Sci, 1997, 37(2): 335-337
[87] Wu C, Shivakumars. Back-propagation and counter-propagation neural networks for phylogenetic classification of ribosomal RNA sequences[J]. Nucleic Acids Res, 1994, 22(20): 4291-4299
[88] Horton PB, Minoru Kanehisa. An assessment of neural network and statistical approches for prediction of E. Coli promoter sites[J].Nucleic Acids Research, 20(16):4331-4338
[89] Tetko IV, Tanchuk Vyu, Chentsova NP, et al. HIV-1 reverse transcriptase inhibitor design using artificial neural networks. J Med Chem, 1994, 37(16): 2520-2526
[90]耿新,陈光.人工神经网络解析紫外光度法同时测定复方制剂[J].理化检验:化学分册,2001,37(3):99-101
[91]李睿,相秉仁.人工神经网络在药动学/药效学研究中的应用药学进展[J],2000,24(2):97-100
[92] Tarkayama K, Fujikawa M, Magai T. Artificial neural network as a novel method to optimize pharmaceutical formulations[J]. Pharm Res, 1999, 16(1):1-6
[93] Koutsoukos AP, Rubinsten LV, David Faraggi. Discrimination techniques applied to the NCi IN VITRO anti-tumour drug screen: predicting biochemical mechanism of action. Stat in Med, 1994, 13:719-730
[94]耿利娜,李静.神经网络在使用裂解气象色谱鉴别中草药中的应用[J].分析化学,2000,28(5):549-553
[95] Richard M. Howard, et al., Survey of Unmanned Air Vehicles, Proc. of the ACC, Sealtla, Washington, June 1995: 2950-2953
[96] Eric N. Johnson, et al., Adaptive Flight Control for An Autonomous Unmanned Helicopter, In AIAA Guidance, Navigation and Control Conference, Number AIAA-2002-4439, Monterey, CA, August 2002
[97]于德浩,邓正栋,聂永平等.基于BP人工神经网络的野战给水装备性能的评估模型[J].解放军理工大学学报(自然科学版),7(5):476-479
[98]张俊锋.神经网络在数字化装甲部队指挥信息对抗中的应用[J].火力与指挥控制,2008,33(suppl):131-135
[99]南克勉,王心.武警卫生勤务学[M].北京:人民卫生出版社,2003年:9
[100]赵水平.血脂异常[M].上海:上海交通大学出版社,2009:9-10
[101] Abhijit S. Pandya,徐勇、荆涛等译,神经网络模式识别及其应用,北京:电子工业出版社,1999年6月
[102] Riedmiller, M., H. Braun, A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm, Proceedings of the IEEE International Conference on Neural Networks, 1993
[103] LI J, Michael AN, Porod W. Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercobe. IEEE Transactions on Circuits and Systems. 1989,36(11):1405-1422
[104] McCulloch WS, Pitts WH. A logical calculus of ideasimmanent in nervous activity. Bulletin of Mathematical Biophysics, 1943, (5): 115-133
[105] Powell MJD. Restart procedures for the conjugate gradient method. Mathematical Programming, 1977, (12): 241-254
[106] Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by errorprogation. Cambridge MA: The MIT Press, 1983: 533-536
[107] Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature,1986, 323: 533-536
[108] [13] Hanley JA, Mcneil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology. 1982; 143:29-36
[109] Hosmer DW, Hosmer T, Le Cessie S, et al. A comparison of goodness-of-fit tests for the logistic regression model. Stat Med, 1997, 16(9): 965-980
[110]闻新,周露,王丹力等.Matlab神经网络应用设计[M].北京:科学出版社,2000:i
[111]国家“九五”科技攻关课题组.我国中年人群心血管病主要危险因素流行现状及从80年代初至90年代末的变化趋势,中华心血管病杂志,2001,29(2):74-79
[112]高小平,高小红.39283名老年住院病人疾病构成分析[J].中国卫生统计,2006,23(6):516-517
[113] Martin S, Werner V, Reinhard R. Neural networks and logistic regression: Part I. Comp Stat Data Analy, 1996, 21:661
[114]颜虹.医学统计学[M].北京:人民卫生出版社,2005
[115]卫生部统计信息中心.第三次卫生服务调查分析报告[M].北京:中国协和医科大学出版社,2004:27
[116]何耀,常青,黄久仪等.军队男性中老年人脑卒中发病和死亡的队列研究[J].中华流行病学杂志,2003,24(6):476-479
[117]卫生部卫生经济研究所.中国卫生总费用研究报告.北京:中国协和医科大学出版社,2007:8
[118]毛瑛,李娇凤.人口老龄化呼唤城市社区卫生服务建设[J].中国卫生事业管理,2005,11:698-699.
[119]国家“八五”攻关课题协作组.90年代初期我国心血管病的总体形势和特点[J].中国慢性病预防和控制,1996,4:145-149
[120] Gaziano TA. Reducing the growing burden of cardiovascular disease in the developing world. Health Affair,2007,26(1): 13-24
[121] Critchley J, Liu J, Zhao D, et al. Explaining the increase in coronary heart disease mortality in Beijing between 1984 and 1999. Circulation,2004, 110(10): 1236-1244
[122] Wang L, Kong L, Wu F, et al. Preventing chronic disease in China. Lancet, 2005,366(9499):1821-1824
[123]段留法,郑秋甫.收缩压、舒张压和脉压对预测心血管疾病风险的临床评价[J].解放军保健医学杂志,2004,6(2):118-120
[124]何耀,黄久仪,倪彬等.军队老年人高血压及血压水平与心脑血管病死亡关系的前瞻性研究应用研究[J].中华老年心脑血管病杂志,2002,4(3):150-153
[125]国家“九五”攻关课题协作组.我国心血管病发病趋势预测及21世纪预防策略的研究[J].医学研究通讯,2003,32:2-5
[126]赵连成,武阳丰,周北凡等.体质指数与冠心病、脑卒中发病的前瞻性研究应用研究.中华心血管病杂志,2002,30(7):430-433
[127]李莹,陈志红,周北凡等.我国中年人群血清TC/HDL-C比值与缺血性和出血性脑卒中发病危险性[J].中华神经科杂志,2005,38(5):305-308
[128]王增武.心血管疾病预测预报的方法[J].中国循环杂志,2000,15(3):191-192
[129] Phillips SJ, O’Fallon WM, Whisnant JP. A population-based model for predicting blood pressure. Mayo Clin proc, 1988, 63: 700-706
[130] Brand RJ, Rosenman RH, Sholtz RJ, et al. Multivariate prediction of coronary heart disease in the Western Collaborative Group Study compared to the finding of Framingham Study. Circulation, 1975, 53:348-355
[131] Assmann G, Schult H, Von Eckardstein A. Hypertriglyceridemia and elevated lipoprotein(a) are risk factor for major coronary events in middle-aged men. Am J Cardiol, 1996,77:1179-1184
[132] Harrell FEJ. Regression Modeling Strategies. New York:Springer-Verlag, 2001
[133] Batti R. First and second order methods for learning: between steepest descent and Newton’s method. Neural Computation,1992,4(2):141-166
[134] Caudill M, Butler C. Understanding Neural Networks. Computer Explorations. Cambridge: The MIT Press,1992
[135]贺宪民.医学多元资料分析中的人工神经网络方法研究[D].第二军医大学,2001年4月
[1] Lv ZR. Prevention of Cardiovascular disease risk factors and Evidence-based Medcine. Huaxia Medicine,2002,(3):3-7 (in chinese)
[2] Truett J,Cornfield J,Kannel WB.A Multivariate Analysis of the Risk of Coronary Heart Disease in Framingham.J Chronic Dis.1967;(20):511-524
[3] American Heart Association.Coronary Risk Handbook:Estimating the Risk of Coronary Heart Disease in Daily Practice. Dallas: American Heart Association, 1973
[4] Kannel WB. Office Assessment of Coronary Candidates and risk factor insights from the Framingham Study. J Hypertens Suppl, 1991,9:S13-S19
[5] Anderson KM, Wilson PWF, Odell PM, et al. An updated coronary risk profile: a statement for health professionals. Circulation, 1991,83:356-362
[6] Wilson PWF, D’Agostiono RB, Levy D, et al. Prediction of Coronary Heart Disease using risk factor categories. Circulation, 1998,97:1837-1847
[7] Grundy SM, D’Agostino RB, Mosca L, et al. Cardiovascular risk assessment based on US Cohort Studies: findings from a National Heart,Lung,and Blood Institute workshop. Circulation, 2001, 104:491-496
[8] Tunstall-Pedoe H:.The Dundee Coronary risk-disk for management of change in risk factors.BMJ,1991,303:744-747
[9] Conroy RM. Pyorala K, Fitzgerald AP, et al. Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. Eur Heart J , 2003, 24: 987-1003
[10] Voss R, Cullen P, Schulte H, et al. Prediction of risk of coronary events in middle-aged men in the Prospective Cardiovascular Munster Study (PROCAM) using neural networks. Int j Epidemiol 2002, 31:1253-1262
[11] Pocock SJ, McCormack V. Gueyffier F, et al. A score for predicting risk of death from cardiovascular disease in adults with raised blood pressure,based on individual patient data from randomised controlled trials. BMJ 2001,323:75-81
[12] Brindle P, May M, Gill PS, et al. Primary prevention of cardiovascular disease: a web-based risk score for seven British black and minority ethnic groups. Heart, hrt 2006
[13] D’Agostino RB, Grundy S, Sullivan LM, et al. Validation of the Framingham Coronaryheart disease prediction scores. (Results of multiple ethnic groups investgation). JAMA,2001,286: 180-187
[14] Woodward M, Brindle P, Tunstall-Pedoe H. Adding social deprivation and family history to cardiovascular risk assessment: the ASSIGN score from the scottish Heart Health Extended Cohort (SHHEC). Heart,2007,93:172-176
[15] Hippisley-Cox J, Coupland C, Vinogradova Y, et al. Derivation and validation of QRISK, a new cardiovascular disease risk score for the United Kingdom: prospective open cohort study. BMJ 2007, 335:136
[16] Hippisley-Cox J, Coupland C, Vinogradova Y, et al. Predicting cardiovascular risk in England and Wales:Prospective derivation and validation of QRISK2. BMJ 2008,336:1475-1482
[17] Zhao D,Wu ZS,Wang W,et al. Association between blood pressure level and risk of cardiovascular disease in Chinese: a cohort study in 11 province of China. Chin J Cardiol, 29(10): 612-617
[18]赵冬,吴兆苏,王薇等.中国11省市队列人群基线血压和7年累计心血管病发病危险的前瞻性研究.中华心血管病杂志,2001,29(10):612-617
[19] The Collaborative Research group of the National 10 th Five Year Plan Project: A Study on Evaluation and Intervention of the Coronary Heart Disaese and Stroke Integrated Risk. A Study on evaluation of the risk of ischemic cardiovascular diseases in Chinese and the development of simplified tools for the evaluation,2003,31(12):893-901
[20]国家“十五”攻关“冠心病、脑卒中综合危险度评估及干预方案的研究”课题组.国人缺血性心血管病的评估方法及简易评估工具的开发研究,中华心血管病杂志,2003,31(12):893-901
[1] Colak MC, Colak C, Kocaturk H, et al. Predicting coronary artery disease using different artificial neural network models. Anadolu Kardiyol Derg, 2008,8(4):249-54.
[2] Baldassarre D, Grossi E, Buscema M, et al. Recognition of patients with cardiovascular disease by artificial neural networks. Ann Med, 2004,36(8):630-40.
[3] Scott JA, Aziz K, Yasuda T, et al. Integration of clinical and imaging data to predict the presence of coronary artery disease with the use of neural networks. Coron Artery Dis, 2004,15(7):427-34.
[4] Baxt WG. Use of an artificial neural network for the diagnosis of myocardial infarction. Ann Intern Med, 1991,115(11):843-8.
[5] OIu R, MIu M, Piradov MA. [The neural network algorithm for diagnosis of ischemic stroke pathogenetic subtypes]. Zh Nevrol Psikhiatr Im S S Korsakova, 2004,(Suppl 12):23-8.
[6] Edenbrandt L, Devine B, Macfarlane PW. Classification of electrocardiographic ST-T segments--human expert vs artificial neural network. Eur Heart J, 1993,14(4):464-8.
[7] Eggers KM, Ellenius J, Dellborg M, et al. Artificial neural network algorithms for early diagnosis of acute myocardial infarction and prediction of infarct size in chest pain patients. Int J Cardiol, 2007,114(3):366-74.
[8]杨军,王宏山,俞梦孙.心电图ST段测量的神经网络方法.北京生物医学工程, 2002,(02):106-108.
[9] Ohlsson M. WeAidU-a decision support system for myocardial perfusion images using artificial neural networks. Artif Intell Med, 2004,30(1):49-60.
[10] Stefaniak B, Cholewinski W, Tarkowska A. Prediction of left ventricular ejection fraction in patients with coronary artery disease based on an analysis of perfusionpatterns at rest. Assessment by an artificial neural network. Nucl Med Rev Cent East Eur, 2004,7(1):7-12.
[11] Allison JS, Heo J, Iskandrian AE. Artificial neural network modeling of stress single-photon emission computed tomographic imaging for detecting extensive coronary artery disease. Am J Cardiol, 2005,95(2):178-81.
[12] Solomon I, Maharshak N, Chechik G, et al. Applying an artificial neural network to warfarin maintenance dose prediction. Isr Med Assoc J, 2004,6(12):732-5.
[13] Linder R, Konig IR, Weimar C, et al. Two models for outcome prediction - a comparison of logistic regression and neural networks. Methods Inf Med, 2006,45(5):536-40.
[2] Zhou B, zhang H, Wu Y, et al. Ecological analysis of the association between incidence and risk factors of coronary heart disease and stroke in Chinese populations[J]. CVD Prevent, 1998,1: 207-216
[3] Yangfeng Wu, Xiaoqing Liu, Xian Li. et al. Estimation of 10-Year Risk of Fatal and Nonfatal Ischemic Cardiovascular Diseases in Chinese Adults[J]. Circulation, 2006, 114:2217-225
[4]李慧凤,王萍,王鸿雁等.“国人缺血性心血管病发病危险简易评估工具”在青岛地区的临床应用及分析[J].中华心血管病杂志,2005,33(2):178-180
[5]程宇宁,焦宝明,杨向阳.“国人缺血性心血管病发病危险简易评估工具”在我部男性体检人群中的应用分析[J].实用医学杂志,2007,23(19):3093-3095
[6]王征,向新生,徐华泉等.“国人缺血性心血管病发病危险简易评估工具”在疗养院的应用[J].中国疗养医学,2007,16(10):598-600
[7] Andrew Moran, Dong Zhao, Dongfeng Gu, etc. The future impact of population growth and aging on coronary heart disease in China: projections from the coronary heart disease policy model-China[J]. BMC Public Health, 2008, 8: 394
[8] Anderson KM, Odell PM, Wilson PWF, et al. Cardiovascular disease risk profiles[J]. Am Heart J, 1991 ;121:293-298
[9]国家“十五”攻关“冠心病、脑卒中综合危险度评估及干预方案的研究”课题组.国人缺血性心血管病发病危险的评估方法及简易评估工具的开发研究[J].中华心血管病杂志,2003,31(12):893-901
[10] Hansson L, Zanchetti A, Carruthers SG., et al. Effects of intensive blood-pressure lowering and low-dose aspirin in patients with hypertension: principle results of the Hypertension: principle results of the Hypertension Optimal Treatment (HOT) randomized trial. Lancer,1998,351:1755-1762
[11] WHO. Multination monitoring of treads and determinants in cardiovascular disease (MONICA project) and manual of operation. Geneva: WHO Cardiovascular Disease Unit,1993
[12]吕卓人.心血管病危险控制与循证医学[J].华夏医药,2002,(3):3-7
[13] Epstein FH, Ostrander LD Jr, Johnson BC, et al. Epidemiological studies of cardiovascular disease in a total community-Tecumeh, Michigan[J]. Ann Intern Med,1965;72:1170
[14] Truett J, Cornfield J, Kannel W. A Multivariate analysis of the risk of coronary heart disease in Framingham[J]. J Chron Dis, 1967,20: 511-524
[15] Kannel WB, McGee D, Gordon T. A general Cardiovascular risk profile: the Framingham Study. Am J Cardiol, 1976; 38: 46-51
[16] Anderson KM, Wilson PWF, Odell PM, et al. An updated coronary risk profile: a statement for health professionals. Circulation,1991,83: 356-362
[17] Wilson PWF, D’Agostino RB, Levy D,et al. Prediction of coronary heart disease using risk factor categories. Circulation,1998, 97: 1837-1847
[18] McGee D, Gordon T. The results of the Framingham study applied to four other US based studies of cardiovascular disease in: Kannel WB, Gordon T (eds).The Framingham study, an Epidemiology investigations of cardiovascular Disease. DHEW Publication No.(NIH) 76-1083, 1976. Washington DC, US Government Printing Office.
[19] Truelsen T, Lindenstorn E, Boysen G. Comparison of probability of stroke between the Copenhagen City Heart Study and the Framingham Study. Storke, 1994,25: 802-807
[20] Wood D, De Backer G, Faergeman D, et al. Prevention of coronary heart disease in clinical practice: recommendations of the second joint Task Force of European and other societies on Coronary Prevention. Atherosclerosis, 1998, 140: 199-270
[21] Sheridan SL, Crespo E. Does the routine use of global coronary heart disease risk scores translate into clinical benefits of harms? A systematic review of the literature [J] .BMC Health Services Research,2008,8:60
[22] Matthew W Knuiman, Hien V Vu. Prediction of coronary heart disease mortality in Busselton. Western Australia: an evaluation of the Framingham, national health epidemiologic follow up study, and WHO ERICA risk scores. J Epidemiol Community Health, 1997, 51: 515-519
[23] Liao Y, McGee DL, Cooper RS, et al. How generalizable are coronary risk prediction models? Comparison of Framingham and two national cohorts. Am Heart Journal,1999, 137:837-845
[24] Oxford JL, Sesso HO, Steelman M , et al. A comparison of the Framingham and European Society of cardiology coronary heart disease risk prediction models in the Normative aging Study. Am Heart J, 2002, 144:95-100
[25] Menotti A, Puddu PE, Lanti M. Comparison of the Framingham risk function-based coronary chart with risk function from an Italian population study. Eur Heart J, 2000, 21:365-370
[26] Gordon T, Carcia-Palmieri MR, Kagan A, et al. Differences in coronary heart disease in Framingham, Honoluu and Puerto Rico. J of Chronic Disease, 1974;27:329-344
[27] Troels F Thomsen, Dan McGee, Michael Davidsen, et al. A cross-validation of risk-scores for coronary heart disease mortality based on data from the Glostrup population studies and Framingham Heart Study. Int J Epidemiol, 2002;31:817-822.
[28] D’Agostino RB, Vasan RS, Pencina MJ, et al. General Cardiovascular Risk Profile for use in primary care: The Framingham heart study[J]. Circulation, 2008(12): 743-752
[29] Berry JD, Lloyd-Jones DM, Garside DB, et al. Framingham risk score and prediction of coronary heart disease death in young men. Am Heart J, 2007, 154(1):80-86
[30] Grundy SM, D’Agostino RB, Mosca L, et al. Cardiovascular risk assessment based on US Cohort studies: finding form a National Heart,Lung,and Blood Institute workshop. Circulation,2001,104: 491-496
[31] D’Agostino RB, Russell MW, Huse DM, et al. Primary and subsequent coronary risk appraisal: new results from the Framingham study. Am Heart J, 2000, 139: 272-281
[32] Tunstall-Pedoe H. The Dundee coronary risk-disk for management of change in risk factors. BMJ,1991,303:744-747
[33] Conroy RM. Pyorala K, Fitzgerald AP, et al. Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. Eur Heart J , 2003, 24: 987-1003
[34] Voss R, Cullen P, Schulte H, et al. Prediction of risk of coronary events in middle-aged men in the Prospective Cardiovascular Munster Study (PROCAM) using neural networks. Int j Epidemiol 2002, 31:1253-1262
[35] Pocock SJ, McCormack V,Gueyffier Francois,et al . A Score for predicting risk of death from cardiovascular disease in adults with raised blood pressure,based onindividual patient data from randomized controlled trials,BMJ,2001.323(7304):75-81
[36] D’Agostino RB, Grundy S, Sullivan LM, et al. Validation of the Framingham coronary heart disease prediction scores: results of a multiple ethnic groups investigation. JAMA,2001;286: 180-187
[37] Brindle P, May M, Gill PS, et al. Primary prevention of cardiovascular disease: a web-based risk score for seven British black and minority ethnic groups. Heart, hrt 2006
[38] Woodward M, Brindle P, Tunstall-Pedoe H. Adding social deprivation and family history to cardiovascular risk assessment: the ASSIGN score from the scottish Heart Health Extended Cohort (SHHEC). Heart,2007,93:172-176
[39] Julia Hippisley-Cox, Carol Coupland, Yana Vinogradova, et al. Derivation and validation of QRISK, a new cardiovascular disease risk score for the United Kingdom: prospective open cohort study, BMJ, 2007,335: I36
[40] Julia Hippisley-Cox, Carol Coupland, Yana Vinogradova, et al. Predicting cardiovascular risk in England and Wales: prospective derivation and validation of QRISK2, BMI, 2008;336: 1475-1482
[41]赵冬、吴兆苏、王薇等.中国11省市队列人群基线血压和7年累积心血管病发病危险的前瞻性研究应用研究.中华心血管病杂志,2001,29:612-617
[42] Wu Y, Liu X, Li Xian, et al. Estimation of 10-year risk of fatal and nonfatal ischemic cardiovascular disease in Chinese adults. Circulation, 2006, 114:2217-2225
[43] Charalambous C.Conjugate gradient algorithm for efficient training of artificial neural networks. IEEE Proceedings, 1992,(139): 301-310
[44] Grossberg S. Studies of the Mind and Brain. Holland: Reidel Press, 1982
[45] Hagan MT, Menhaj M. Training feed forward networks with the Marquardt algorthm. IEEE Transactions on Neural Networks, 1994,5(6): 6989-6993
[46] Hagan MT, Demuth HB, Beale. Neural Network Design.. Boston MA: PWS Publishing, 1996
[47] Funahshi K I., On the Approximate Realization of Continuous Mappings by Neutral Networks[J]. Neural Network, 1989, 2: 183-192
[48] Hornik K, Strinchcomber M, Whiter H., Multilayer Feedforward Networks Are 110Universal Approximators, Neural Networks. 1989,2: 359-366
[49] Honik K., Approximation Capabilities of Multilayer Feedforward Networks Neural, Neural Network, 1991, 4: 551-557
[50]陈天平,神经网络及其在系统识别应用中的逼近问题,中国科学(A辑), 1994, 24 (1): 1-7
[51] M. Pachter, P.R. Chandler, Challenges of Autonomous Control, IEEE Control Systems, Aug. 1998: 92-97
[52] Panos J. Antsaklis, Kevin M. Passino, S.J. Wang, An Introduction to Autonomous Control Systems, IEEE Control Systems, June 1991: 5-13
[53] Manu Sharma, Anthony J. Calise, J. Eric Corban, Application of An Adaptive Autopilot Design to A Family Guided Munitions, AIAA Guidance, Navigation and Control Conference, Denver CO. AIAA 2000-3969, Aug. 2000
[54] H. Jin Kim, David H. Shim, A Flight Control System for Aerial Robots: Algorithms and Experiments, Control Engineering Practice, 2003(11):1389–1400
[55] J. S. Brinker, K. A. Wise, Flight Testing of A Reconfigure Flight Control Law on the X-36 Tailless Flight Aircraft, In Proc. of the AIAA Guidance, Navigation and Control Conference, AIAA-00-3941, Aug. 2000
[56] Manu Sharma, A Neuro-Adaptive Autopilot Design for Guided Munitions, Ph. D. Thesis, Georgia Institute of Technology, Atlanta, 2001
[57] A. J. Calise, M. Sharma, E. Corban, An Adaptive Autopilot Design for Guided Munitions, AIAA J. Guidance, Control and Dynamics, 2000
[58] Perry Walter Stout, Combined Dynamic Inversion and QFT Flight Control of An Unstable High Performance Aircraft, Ph. D. Thesis, University of California, 1999
[59] Flavio Nardi, Neural Network Based Adaptive Algorithms for Nonlinear Control, Ph. D. Thesis, Georgia Institute of Technology, Atlanta, 2000
[60] C. H. Lee, M. H. Shin, M. J. Chung, A Design of Gain-Scheduled Control for A Linear Parameter Varying System: An Application to Flight Control, Control Engineering Practice, 2001(9): 11-21
[61] A. Isidori, Nonlinear Control Systems, Springer-Verlag, Ltd, London, UK, 3rd, edition, 1995
[62] Daniel Liberzon, A. Stephen Morse and Eduardo D. Sontag, Out-Input Stability andMinimum-Phase Nonlinear Systems, IEEE Trans. on Automatic Contr., 2002, 47(3): 422-436
[63] Emmanuel Hygounenc, Il-Kyun Jung, The Autonomous Blimp Project of LAAS-CNRS: Achievements in Flight Control and Terrain Mapping, The International Journal of Robotics Research, April-May 2004: 474-511
[64] Nazmi A. Mahmoud, Hassan K. Khalil, Asymptotic Regulation of Minimum Phase Nonlinear Systems using Output Feedback, IEEE Trans. on Automatic Contr., 1996, 41(10):1402-1412
[65] Alberto Isidori, Christopher I. Byrnes, Output Regulation of Nonlinear Systems, IEEE Trans. on Automatic Contr., 1990, 35(2):131-140
[66] Brianl. Stevens, Frank L. Lewis, Aircraft Control and Simulation, John Wiley and Sons, Inc., 2nd, edition, 2003.IEEE Trans. on Automatic Contr., 1998, 43(3): 386-391
[67] Ahmed Mohammed Dabroom, Hassan K. Khalil, Output Feedback Sampled-Data Control of Nonlinear Systems using High-Gain Observers, IEEE Trans. on Automatic Contr., 2001, 46(11): 1712-1725
[68] J?rg Mareczek, Martin Buss, Mark W. Spong, Invariance Control for A Class of Cascade Nonlinear Systems, IEEE Trans. on Automatic Control, 2002, 47(4): 636-640
[69] A. N. Atassi, H. K. Khalil, A Separation Principle for the Control of A Class of Nonlinear Systems, IEEE Trans. on Automatic Contr., 2001, 46(5): 742-746
[70] Raffaella De Santis, Alberto Isidori, On the Output Regulation for Linear Systems in the Presence of Input Saturation, IEEE Trans. on Automatic Contr., 2001, 46(1): 156-160
[71] Carlos E. T. D′orea , Bas′ylio E. A. Milani, Disturbance Decoupling in A Class of Linear Systems, IEEE Trans. on Automatic Contr., 1997, 42(10): 1427-1431
[72] Delin Chu, Volker Mehrmann, Disturbance Decoupling for Linear Time-Invariant Systems: A Matrix Pencil Approach, IEEE Trans. on Automatic Contr., 2001, 46(5): 802-808
[73] Wilson J. Rugha, Jeff S. Shamma, Research on Gain Scheduling, Automatica 36 2000: 1401-1425
[74] Widrow B,Hoff ME,Adaptive Switching circuits. 1960 IRE WESCON ConventionRecord. New York IRE,1960:96-104
[75] Widrow B, Sterms SD. Adaptive Signal Processing. New York: Prentine-Hall, 1985
[76]周礼果.人工神经网络在生物医学中的应用[J].国外医学生物医学工程分册,1996,19(1):40-45
[77] Edith Lahner, Marco Intraligi, Massimo Buscema, et al. Artificial neural networks in the recognition of the presence of thyroid disease in patients with atroplic body gastritis[J]. World Journal of Castroenterology, 2008, 14(4): 563-568
[78]阿伯基斯[美]著.神经网络模式识别及其实现[M].北京:电子工业出版社,1999
[79]陈明.神经网络模型[M].大连:大连理工大学出版社,1995
[80]袁曾任.人工神经网络及其应用[M].北京:清华大学出版社,1999
[81]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998
[82]王伟.人工神经网络原理:入门与应用[M].北京:北京航天航空大学出版社,1995
[83]姚敏.一种前向网络的多准则学习方法[J].通信学报,1996,17(4):113-117
[84]周继成.人工神经网络-第六代计算机的实现[M].北京:科学普及出版社,1993
[85]孙巧萍,姚敏.人工神经网络的模糊学习方法[J].计算机工程与设计,1999,20(6):14-16
[86] Alvager T, Graham G, Hutchison D. Neural Network Method to analyze data compression in DNA and RNA sequences[J]. J Chem Comput Sci, 1997, 37(2): 335-337
[87] Wu C, Shivakumars. Back-propagation and counter-propagation neural networks for phylogenetic classification of ribosomal RNA sequences[J]. Nucleic Acids Res, 1994, 22(20): 4291-4299
[88] Horton PB, Minoru Kanehisa. An assessment of neural network and statistical approches for prediction of E. Coli promoter sites[J].Nucleic Acids Research, 20(16):4331-4338
[89] Tetko IV, Tanchuk Vyu, Chentsova NP, et al. HIV-1 reverse transcriptase inhibitor design using artificial neural networks. J Med Chem, 1994, 37(16): 2520-2526
[90]耿新,陈光.人工神经网络解析紫外光度法同时测定复方制剂[J].理化检验:化学分册,2001,37(3):99-101
[91]李睿,相秉仁.人工神经网络在药动学/药效学研究中的应用药学进展[J],2000,24(2):97-100
[92] Tarkayama K, Fujikawa M, Magai T. Artificial neural network as a novel method to optimize pharmaceutical formulations[J]. Pharm Res, 1999, 16(1):1-6
[93] Koutsoukos AP, Rubinsten LV, David Faraggi. Discrimination techniques applied to the NCi IN VITRO anti-tumour drug screen: predicting biochemical mechanism of action. Stat in Med, 1994, 13:719-730
[94]耿利娜,李静.神经网络在使用裂解气象色谱鉴别中草药中的应用[J].分析化学,2000,28(5):549-553
[95] Richard M. Howard, et al., Survey of Unmanned Air Vehicles, Proc. of the ACC, Sealtla, Washington, June 1995: 2950-2953
[96] Eric N. Johnson, et al., Adaptive Flight Control for An Autonomous Unmanned Helicopter, In AIAA Guidance, Navigation and Control Conference, Number AIAA-2002-4439, Monterey, CA, August 2002
[97]于德浩,邓正栋,聂永平等.基于BP人工神经网络的野战给水装备性能的评估模型[J].解放军理工大学学报(自然科学版),7(5):476-479
[98]张俊锋.神经网络在数字化装甲部队指挥信息对抗中的应用[J].火力与指挥控制,2008,33(suppl):131-135
[99]南克勉,王心.武警卫生勤务学[M].北京:人民卫生出版社,2003年:9
[100]赵水平.血脂异常[M].上海:上海交通大学出版社,2009:9-10
[101] Abhijit S. Pandya,徐勇、荆涛等译,神经网络模式识别及其应用,北京:电子工业出版社,1999年6月
[102] Riedmiller, M., H. Braun, A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm, Proceedings of the IEEE International Conference on Neural Networks, 1993
[103] LI J, Michael AN, Porod W. Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercobe. IEEE Transactions on Circuits and Systems. 1989,36(11):1405-1422
[104] McCulloch WS, Pitts WH. A logical calculus of ideasimmanent in nervous activity. Bulletin of Mathematical Biophysics, 1943, (5): 115-133
[105] Powell MJD. Restart procedures for the conjugate gradient method. Mathematical Programming, 1977, (12): 241-254
[106] Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by errorprogation. Cambridge MA: The MIT Press, 1983: 533-536
[107] Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature,1986, 323: 533-536
[108] [13] Hanley JA, Mcneil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology. 1982; 143:29-36
[109] Hosmer DW, Hosmer T, Le Cessie S, et al. A comparison of goodness-of-fit tests for the logistic regression model. Stat Med, 1997, 16(9): 965-980
[110]闻新,周露,王丹力等.Matlab神经网络应用设计[M].北京:科学出版社,2000:i
[111]国家“九五”科技攻关课题组.我国中年人群心血管病主要危险因素流行现状及从80年代初至90年代末的变化趋势,中华心血管病杂志,2001,29(2):74-79
[112]高小平,高小红.39283名老年住院病人疾病构成分析[J].中国卫生统计,2006,23(6):516-517
[113] Martin S, Werner V, Reinhard R. Neural networks and logistic regression: Part I. Comp Stat Data Analy, 1996, 21:661
[114]颜虹.医学统计学[M].北京:人民卫生出版社,2005
[115]卫生部统计信息中心.第三次卫生服务调查分析报告[M].北京:中国协和医科大学出版社,2004:27
[116]何耀,常青,黄久仪等.军队男性中老年人脑卒中发病和死亡的队列研究[J].中华流行病学杂志,2003,24(6):476-479
[117]卫生部卫生经济研究所.中国卫生总费用研究报告.北京:中国协和医科大学出版社,2007:8
[118]毛瑛,李娇凤.人口老龄化呼唤城市社区卫生服务建设[J].中国卫生事业管理,2005,11:698-699.
[119]国家“八五”攻关课题协作组.90年代初期我国心血管病的总体形势和特点[J].中国慢性病预防和控制,1996,4:145-149
[120] Gaziano TA. Reducing the growing burden of cardiovascular disease in the developing world. Health Affair,2007,26(1): 13-24
[121] Critchley J, Liu J, Zhao D, et al. Explaining the increase in coronary heart disease mortality in Beijing between 1984 and 1999. Circulation,2004, 110(10): 1236-1244
[122] Wang L, Kong L, Wu F, et al. Preventing chronic disease in China. Lancet, 2005,366(9499):1821-1824
[123]段留法,郑秋甫.收缩压、舒张压和脉压对预测心血管疾病风险的临床评价[J].解放军保健医学杂志,2004,6(2):118-120
[124]何耀,黄久仪,倪彬等.军队老年人高血压及血压水平与心脑血管病死亡关系的前瞻性研究应用研究[J].中华老年心脑血管病杂志,2002,4(3):150-153
[125]国家“九五”攻关课题协作组.我国心血管病发病趋势预测及21世纪预防策略的研究[J].医学研究通讯,2003,32:2-5
[126]赵连成,武阳丰,周北凡等.体质指数与冠心病、脑卒中发病的前瞻性研究应用研究.中华心血管病杂志,2002,30(7):430-433
[127]李莹,陈志红,周北凡等.我国中年人群血清TC/HDL-C比值与缺血性和出血性脑卒中发病危险性[J].中华神经科杂志,2005,38(5):305-308
[128]王增武.心血管疾病预测预报的方法[J].中国循环杂志,2000,15(3):191-192
[129] Phillips SJ, O’Fallon WM, Whisnant JP. A population-based model for predicting blood pressure. Mayo Clin proc, 1988, 63: 700-706
[130] Brand RJ, Rosenman RH, Sholtz RJ, et al. Multivariate prediction of coronary heart disease in the Western Collaborative Group Study compared to the finding of Framingham Study. Circulation, 1975, 53:348-355
[131] Assmann G, Schult H, Von Eckardstein A. Hypertriglyceridemia and elevated lipoprotein(a) are risk factor for major coronary events in middle-aged men. Am J Cardiol, 1996,77:1179-1184
[132] Harrell FEJ. Regression Modeling Strategies. New York:Springer-Verlag, 2001
[133] Batti R. First and second order methods for learning: between steepest descent and Newton’s method. Neural Computation,1992,4(2):141-166
[134] Caudill M, Butler C. Understanding Neural Networks. Computer Explorations. Cambridge: The MIT Press,1992
[135]贺宪民.医学多元资料分析中的人工神经网络方法研究[D].第二军医大学,2001年4月
[1] Lv ZR. Prevention of Cardiovascular disease risk factors and Evidence-based Medcine. Huaxia Medicine,2002,(3):3-7 (in chinese)
[2] Truett J,Cornfield J,Kannel WB.A Multivariate Analysis of the Risk of Coronary Heart Disease in Framingham.J Chronic Dis.1967;(20):511-524
[3] American Heart Association.Coronary Risk Handbook:Estimating the Risk of Coronary Heart Disease in Daily Practice. Dallas: American Heart Association, 1973
[4] Kannel WB. Office Assessment of Coronary Candidates and risk factor insights from the Framingham Study. J Hypertens Suppl, 1991,9:S13-S19
[5] Anderson KM, Wilson PWF, Odell PM, et al. An updated coronary risk profile: a statement for health professionals. Circulation, 1991,83:356-362
[6] Wilson PWF, D’Agostiono RB, Levy D, et al. Prediction of Coronary Heart Disease using risk factor categories. Circulation, 1998,97:1837-1847
[7] Grundy SM, D’Agostino RB, Mosca L, et al. Cardiovascular risk assessment based on US Cohort Studies: findings from a National Heart,Lung,and Blood Institute workshop. Circulation, 2001, 104:491-496
[8] Tunstall-Pedoe H:.The Dundee Coronary risk-disk for management of change in risk factors.BMJ,1991,303:744-747
[9] Conroy RM. Pyorala K, Fitzgerald AP, et al. Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. Eur Heart J , 2003, 24: 987-1003
[10] Voss R, Cullen P, Schulte H, et al. Prediction of risk of coronary events in middle-aged men in the Prospective Cardiovascular Munster Study (PROCAM) using neural networks. Int j Epidemiol 2002, 31:1253-1262
[11] Pocock SJ, McCormack V. Gueyffier F, et al. A score for predicting risk of death from cardiovascular disease in adults with raised blood pressure,based on individual patient data from randomised controlled trials. BMJ 2001,323:75-81
[12] Brindle P, May M, Gill PS, et al. Primary prevention of cardiovascular disease: a web-based risk score for seven British black and minority ethnic groups. Heart, hrt 2006
[13] D’Agostino RB, Grundy S, Sullivan LM, et al. Validation of the Framingham Coronaryheart disease prediction scores. (Results of multiple ethnic groups investgation). JAMA,2001,286: 180-187
[14] Woodward M, Brindle P, Tunstall-Pedoe H. Adding social deprivation and family history to cardiovascular risk assessment: the ASSIGN score from the scottish Heart Health Extended Cohort (SHHEC). Heart,2007,93:172-176
[15] Hippisley-Cox J, Coupland C, Vinogradova Y, et al. Derivation and validation of QRISK, a new cardiovascular disease risk score for the United Kingdom: prospective open cohort study. BMJ 2007, 335:136
[16] Hippisley-Cox J, Coupland C, Vinogradova Y, et al. Predicting cardiovascular risk in England and Wales:Prospective derivation and validation of QRISK2. BMJ 2008,336:1475-1482
[17] Zhao D,Wu ZS,Wang W,et al. Association between blood pressure level and risk of cardiovascular disease in Chinese: a cohort study in 11 province of China. Chin J Cardiol, 29(10): 612-617
[18]赵冬,吴兆苏,王薇等.中国11省市队列人群基线血压和7年累计心血管病发病危险的前瞻性研究.中华心血管病杂志,2001,29(10):612-617
[19] The Collaborative Research group of the National 10 th Five Year Plan Project: A Study on Evaluation and Intervention of the Coronary Heart Disaese and Stroke Integrated Risk. A Study on evaluation of the risk of ischemic cardiovascular diseases in Chinese and the development of simplified tools for the evaluation,2003,31(12):893-901
[20]国家“十五”攻关“冠心病、脑卒中综合危险度评估及干预方案的研究”课题组.国人缺血性心血管病的评估方法及简易评估工具的开发研究,中华心血管病杂志,2003,31(12):893-901
[1] Colak MC, Colak C, Kocaturk H, et al. Predicting coronary artery disease using different artificial neural network models. Anadolu Kardiyol Derg, 2008,8(4):249-54.
[2] Baldassarre D, Grossi E, Buscema M, et al. Recognition of patients with cardiovascular disease by artificial neural networks. Ann Med, 2004,36(8):630-40.
[3] Scott JA, Aziz K, Yasuda T, et al. Integration of clinical and imaging data to predict the presence of coronary artery disease with the use of neural networks. Coron Artery Dis, 2004,15(7):427-34.
[4] Baxt WG. Use of an artificial neural network for the diagnosis of myocardial infarction. Ann Intern Med, 1991,115(11):843-8.
[5] OIu R, MIu M, Piradov MA. [The neural network algorithm for diagnosis of ischemic stroke pathogenetic subtypes]. Zh Nevrol Psikhiatr Im S S Korsakova, 2004,(Suppl 12):23-8.
[6] Edenbrandt L, Devine B, Macfarlane PW. Classification of electrocardiographic ST-T segments--human expert vs artificial neural network. Eur Heart J, 1993,14(4):464-8.
[7] Eggers KM, Ellenius J, Dellborg M, et al. Artificial neural network algorithms for early diagnosis of acute myocardial infarction and prediction of infarct size in chest pain patients. Int J Cardiol, 2007,114(3):366-74.
[8]杨军,王宏山,俞梦孙.心电图ST段测量的神经网络方法.北京生物医学工程, 2002,(02):106-108.
[9] Ohlsson M. WeAidU-a decision support system for myocardial perfusion images using artificial neural networks. Artif Intell Med, 2004,30(1):49-60.
[10] Stefaniak B, Cholewinski W, Tarkowska A. Prediction of left ventricular ejection fraction in patients with coronary artery disease based on an analysis of perfusionpatterns at rest. Assessment by an artificial neural network. Nucl Med Rev Cent East Eur, 2004,7(1):7-12.
[11] Allison JS, Heo J, Iskandrian AE. Artificial neural network modeling of stress single-photon emission computed tomographic imaging for detecting extensive coronary artery disease. Am J Cardiol, 2005,95(2):178-81.
[12] Solomon I, Maharshak N, Chechik G, et al. Applying an artificial neural network to warfarin maintenance dose prediction. Isr Med Assoc J, 2004,6(12):732-5.
[13] Linder R, Konig IR, Weimar C, et al. Two models for outcome prediction - a comparison of logistic regression and neural networks. Methods Inf Med, 2006,45(5):536-40.