[1] Ma Guangzhi, Lu Yansheng, Song Enmin, Nie Shaofa, et al. Neural network based online hypertension risk evaluation system [J]. Journal of Southeast University (English Edition), 2008, 24 (3): 267-271. [doi:10.3969/j.issn.1003-7985.2008.03.004]
Copy
Neural network based online hypertension risk evaluation system(
)
基于神经网络的高血压在线风险评估系统
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 24
- Issue:
- 2008 3
- Page:
- 267-271
- Research Field:
- Automation
- Publishing date:
- 2008-09-30
Info
- Title:
- Neural network based online hypertension risk evaluation system
- 基于神经网络的高血压在线风险评估系统
- Author(s):
- Ma Guangzhi, Lu Yansheng, Song Enmin, Nie Shaofa, Jing Weifeng, Zhang Wei
- College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
- Keywords:
- hypertension prediction; neural network; information gain
- PACS:
- TP183
- DOI:
- 10.3969/j.issn.1003-7985.2008.03.004
- Abstract:
- Since the previous research works are not synthetic and accurate enough for building a precise hypertension risk evaluation system, by ranking the significances for hypertension factors according to the information gains on 2 231 normotensive and 823 hypertensive samples, totally 42 different neural network models are built and tested.The prediction accuracy of a model whose inputs are 26 factors is found to be much higher than the 81.61% obtained by previous research work. The prediction matching rates of the model for “hypertension or not”, “systolic blood pressure”, and “diastolic blood pressure” are 95.79%, 98.22% and 98.41%, respectively.Based on the found model and the object oriented techniques, an online hypertension risk evaluation system is developed, being able to gather new samples, learn the new samples, and improve its prediction accuracy automatically.
- 由于先前的研究工作不够综合和精确, 不足于建立准确的高血压风险评估系统, 根据2 231个正常样本及823个高血压样本计算的信息增益, 对高血压致病因素的重要程度进行了排序, 总共建立和测试了42个不同的神经网络模型, 发现了一个输入为26个致病因素的神经网络模型, 其预测精度远高于先前研究取得的81.61%, 该模型关于“是否高血压”、“收缩压”、“舒张压”的预测符合率分别为95.79%, 98.22%和 98.41%.基于发现的神经网络模型及面向对象的技术, 开发了一个能自动收集新样本、学习新样本并能改进预测精度的高血压风险在线评估系统.
References:
[1] Walker J, MacKenzie A D, Dunning J.Does reducing your salt intake make you live longer? [J].Interactive CardioVascular and Thoracic Surgery, 2007, 6(6):793-798.
[2] He F J, MacGregor A.Effect of modest salt reduction on blood pressure:a meta-analysis of randomized trials.Implications for public health[J].Journal of Human Hypertension, 2002, 16(1):761-770.
[3] Bacquer D D, Clays E, Delanghe J, et al.Epidemiological evidence for an association between habitual tea consumption and markers of chronic inflammation [J].Atherosclerosis, 2006, 189(2):428-435.
[4] Geleijnse J M, Kok F J, Grobbee D E.Impact of dietary and lifestyle factors on the prevalence of hypertension in Western populations[J].European Journal of Public Health, 2004, 14(3):235-239.
[5] Lisboa P J G.Neural networks in medical journals:current trends and implications for biopattern[C]//Proc of the First European Workshop on Assessment of Diagnostic Performance (EWADP).Milan, 2004:99-112.
[6] Poli R, Cagnoni S, Livi R, et al.A neural network expert system for diagnosing and treating hypertension[J].Computer, 1991, 24(3):64-71.
[7] Ning G, Su J, Li Y, et al.Artificial neural network based model for cardiovascular risk stratification in hypertension[J].Medical and Biological Engineering and Computing, 2006, 44(3):202-208.
[8] Kent J T.Information gain and a general measure of correlation [J].Biometrika, 1983, 70(1):163-73.
[9] Rumelhart D E, Hinton G E, Williams R J.Learning representations by back-propagating errors [J].Nature, 1986, 323(9):533-536.
[10] Rumelhart D E.Parallel distributed processing[M].Cambridge, MA:MIT Press, 1986:318-362.
[11] Vogl T P, Mangis J K.Accelerating the convergence of the back-propagation method [J].Biological Cybernetics, 1988, 59(3):256-264.
[12] Patric P.Minimization method for training feedforward neural networks[J].Neural Networks, 1994, 7(1):1-11.
Memo
- Memo:
-
Biographies: Ma Guangzhi(1964—), male, associate professor, maguangzhi@hust.edu.cn;Lu Yansheng(corresponding author), male, professor, LYS@hust.edu.cn.
Foundation item: The National High Technology Research and Development Program of China(863 Program)(No.2006AA02Z347).
Citation: Ma Guangzhi, Lu Yansheng, Song Enmin, et al.Neural network based online hypertension risk evaluation system[J].Journal of Southeast University(English Edition), 2008, 24(3):267-271.