Full Text:   <1789>

Summary:  <481>

CLC number: TP273; R544

On-line Access: 2015-06-04

Received: 2014-08-18

Revision Accepted: 2014-12-20

Crosschecked: 2015-05-07

Cited: 1

Clicked: 2701

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Gurmanik Kaur

http://orcid.org/0000-0002-6384-4396

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2015 Vol.16 No.6 P.474-485

http://doi.org/10.1631/FITEE.1400295


Using hybrid models to predict blood pressure reactivity to unsupported back based on anthropometric characteristics


Author(s):  Gurmanik Kaur, Ajat Shatru Arora, Vijender Kumar Jain

Affiliation(s):  Sant Longowal Institute of Engineering and Technology, Deemed University, Punjab 148106, India

Corresponding email(s):   mannsliet@gmail.com, ajatsliet@yahoo.com, vkjain27@yahoo.com

Key Words:  Blood pressure (BP), Principal component analysis (PCA), Forward stepwise regression, Artificial neural network (ANN), Adaptive neuro-fuzzy inference system (ANFIS), Least squares support vector machine (LS-SVM)


Gurmanik Kaur, Ajat Shatru Arora, Vijender Kumar Jain. Using hybrid models to predict blood pressure reactivity to unsupported back based on anthropometric characteristics[J]. Frontiers of Information Technology & Electronic Engineering, 2015, 16(6): 474-485.

@article{title="Using hybrid models to predict blood pressure reactivity to unsupported back based on anthropometric characteristics",
author="Gurmanik Kaur, Ajat Shatru Arora, Vijender Kumar Jain",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="16",
number="6",
pages="474-485",
year="2015",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1400295"
}

%0 Journal Article
%T Using hybrid models to predict blood pressure reactivity to unsupported back based on anthropometric characteristics
%A Gurmanik Kaur
%A Ajat Shatru Arora
%A Vijender Kumar Jain
%J Frontiers of Information Technology & Electronic Engineering
%V 16
%N 6
%P 474-485
%@ 2095-9184
%D 2015
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1400295

TY - JOUR
T1 - Using hybrid models to predict blood pressure reactivity to unsupported back based on anthropometric characteristics
A1 - Gurmanik Kaur
A1 - Ajat Shatru Arora
A1 - Vijender Kumar Jain
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 16
IS - 6
SP - 474
EP - 485
%@ 2095-9184
Y1 - 2015
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1400295


Abstract: 
Accurate blood pressure (BP) measurement is essential in epidemiological studies, screening programmes, and research studies as well as in clinical practice for the early detection and prevention of high BP-related risks such as coronary heart disease, stroke, and kidney failure. Posture of the participant plays a vital role in accurate measurement of BP. Guidelines on measurement of BP contain recommendations on the position of the back of the participants by advising that they should sit with supported back to avoid spuriously high readings. In this work, principal component analysis (PCA) is fused with forward stepwise regression (SWR), artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), and the least squares support vector machine (LS-SVM) model for the prediction of BP reactivity to an unsupported back in normotensive and hypertensive participants. PCA is used to remove multi-collinearity among anthropometric predictor variables and to select a subset of components, termed ‘principal components’ (PCs), from the original dataset. The selected PCs are fed into the proposed models for modeling and testing. The evaluation of the performance of the constructed models, using appropriate statistical indices, shows clearly that a PCA-based LS-SVM (PCA-LS-SVM) model is a promising approach for the prediction of BP reactivity in comparison to others. This assessment demonstrates the importance and advantages posed by hybrid models for the prediction of variables in biomedical research studies.

The paper deals with the evaluation of the uncertainty of BP measurement in the case of unsupported back. The paper is well written.

基于体位特征使用混杂模型预测血压对于无支撑后背的反应

目的:准确测量血压(BP)对于流行病学研究、筛查规划、调研研究和高血压相关病变(冠心病、中风、肾衰竭等)的早期诊断及预防有重要意义。被测者体位对于准确测量血压有重要影响。血压测量指南建议测试时被测者应在后背有支撑的情况下保持坐姿,以避免血压读数偏高。本文使用混杂模型预测血压对于无支撑后背的反应。
创新点:本文考虑血压正常和高血压测试者的人体预测变量(如年龄、身高、体重、体块指数和上臂周长(AC)),使用基于PCA的前向逐步回归(PCA-SWR)、基于PCA的人工神经网络(PCA-ANN)、基于PCA的自适应神经模糊推理系统(PCA-ANFIS)和基于PCA的最小方差支持向量机(PCA-LS-SVM)等模型预测血压对无支撑后背的反应。
方法:使用PCA消除人体预测变量间的多重共线性,并在原始数据集中选取主元(PC)。所选主元被输入至所建立预测模型用于建模及测试。
结论:通过评估合适的统计指标(确定性系数、平均平方根误差、平均绝对百分比误差),得出较之其他模型,PCA-LS-SVM对于预测血压反应较有前景。此评估也展示了混杂模型在预测生物医学领域其他参数时的重要性和先进性。

关键词:血压(BP);主元分析(PCA);前向逐步回归;人工神经网络;自适应神经模糊推理系统;最小方差支持向量机

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Baba, R., Koketsu, M., Nagashima, M., et al., 2007. Adolescent obesity adversely affects blood pressure and resting heart rate. Circ. J., 71(5):722-726.

[2]Barbé, K., Kurylyak, Y., Lamonaca, F., 2014. Logistic ordinal regression for the calibration of oscillometric blood pressure monitors. Biomed. Signal Process., 11:89-96.

[3]Basheer, I.A., Hajmeer, M., 2000. Artificial neural networks: fundamentals, computing, design, and application. J. Microbiol. Methods, 43(1):3-31.

[4]British Hypertension Society, 1998. Blood Pressure Measurement (CD-ROM). BMJ Books, London, UK.

[5]Card, D.H., Peterson, D.L., Matson, P.A., 1988. Prediction of leaf chemistry by the use of visible and near infrared reflectance spectroscopy. Remote Sens. Environ., 26(2):123-147.

[6]Chiatti, C., Bustacchini, S., Furneri, G., et al., 2012. The economic burden of inappropriate drug prescribing, lack of adherence and compliance, adverse drug events in older people. Drug Saf., 35(1):73-87.

[7]Cushman, W.C., Cooper, K.M., Horne, R.A., et al., 1990. Effect of back support and stethoscope head on seated blood pressure determinations. Am. J. Hypertens., 3(3):240-241.

[8]de Hoog, M., van Eijsden, M., Stronks, K., et al., 2012. Association between body size and blood pressure in children from different ethnic origins. Cardiovasc. Diabetol., 11:136.1-136.10.

[9]Forouzanfar, M., Dajani, H.R., Groza, V.Z., et al., 2011. Feature-based neural network approach for oscillometric blood pressure estimation. IEEE Trans. Instrum. Meas., 60(8):2786-2796.

[10]Genc, S., 2011. Prediction of mean arterial blood pressure with linear stochastic models. Proc. IEEE Annual Int. Conf. on Engineering in Medicine and Biology Society, p.712-715.

[11]Golino, H.F., Amaral, L.S.B., Duarte, S.F.P., et al., 2014. Predicting increased blood pressure using machine learning. J. Obes., 2014:637635.1-637635.12.

[12]Gujarati, D.N., 1995. Basic Econometrics. McGraw-Hill, New York, USA.

[13]Hagan, M.T., Menhaj, M.B., 1994. Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neur. Netw., 5(6):989-993.

[14]Haynes, R.B., Sackett, D.L., Taylor, D.W., et al., 1978. Increased absenteeism from work after detection and labeling of hypertensive patients. New Engl. J. Med., 299(14):741-744.

[15]Huang, H.H., Xu, T., Yang, J., 2014. Comparing logistic regression, support vector machines, and permanental classification methods in predicting hypertension. BMC Proc., 8(Suppl. 1):S96.1-S96.5.

[16]Inoue, M., Minami, M., Yano, E., 2014. Body mass index, blood pressure, and glucose and lipid metabolism among permanent and fixed-term workers in the manufacturing industry: a cross-sectional study. BMC Pub. Health, 14:207.1-207.8.

[17]Jang, J.S.R., 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans. Syst. Man Cybern., 23(3):665-685.

[18]Jolliffe, I.T., 2002. Principal Component Analysis. Springer-Verlag, New York, USA.

[19]Kaiser, H.F., 1960. The application of electronic computers to factor analysis. Educ. Psychol. Meas., 20:141-151.

[20]Khan, S.M.U., Manzoor, J.S., Lee, S.U.J., 2014. Predicting student blood pressure by support vector machine using Facebook. Proc. IEEE World Congress on Services, p.486-492.

[21]Kolade, O.O., O’Moore-Sullivan, T.M., Stowasser, M., et al., 2012. Arterial stiffness, central blood pressure and body size in health and disease. Int. J. Obes., 36(1):93-99.

[22]Kurylyak, Y., Lamonaca, F., Grimaldi, D., 2013. A neural network-based method for continuous blood pressure estimation from a PPG signal. Proc. IEEE Int. Conf. on Instrumentation and Measurement Technology, p.280-283.

[23]Lynn, S., Ringwood, J., Ragnoli, E., et al., 2009. Virtual metrology for plasma etch using tool variables. Proc. IEEE/SEMI Advanced Semiconductor Manufacturing Conf., p.143-148.

[24]Monte-Moreno, E., 2011. Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques. Artif. Intell. Med., 53(2):127-138.

[25]Moser, D.C., Giuliano, I.C.B., Titski, A.C.K., et al., 2013. Anthropometric measures and blood pressure in school children. J. Pediatr., 89(3):243-249.

[26]Nauck, D., 1997. Neuro-Fuzzy Systems. John Wiley & Sons, Inc., New York, USA.

[27]Noori, R., Khakpour, A., Omidvar, B., et al., 2010. Comparison of ANN and principal component analysis— multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistics. Expert Syst. Appl., 37(8):5856-5862.

[28]O’Brien, E., Asmar, R., Beilin, L., et al., 2003. European society of hypertension recommendations for conventional, ambulatory and home blood pressure measurement. J. Hypertens., 21(5):821-848.

[29]Pickering, T.G., Hall, J.E., Appel, L.J., et al., 2005. Recommendations for blood pressure measurement in humans and experimental animals. Part 1: Blood pressure measurement in humans: a statement for professionals from the Subcommittee of Professional and Public Education of the American Heart Association Council on High Blood Pressure Research. Hypertension, 45:142-161.

[30]Schölkopf, B., Smola, A.J., 2002. Learning with Kernels. MIT Press, Cambridge, MA, USA.

[31]Sharma, S., 1995. Applied Multivariate Techniques. John Wiley & Sons, Inc., Canada.

[32]Smith, K.W., Sasaki, M.S., 1979. Decreasing multicollinearity: a method for models with multiplicative functions. Sociol. Methods Res., 8(1):35-56.

[33]Suykens, J.A.K., Vandewalle, J., 1999. Least squares support vector machine classifiers. Neur. Process. Lett., 9(3):293-300.

[34]Tobias, S., Carlson, J.E., 1969. Brief report: Bartlett’s test of sphericity and chance findings in factor analysis. Multivar. Behav. Res., 4(3):375-377.

[35]Williams, B., Brown, T., Onsman, A., 2010. Exploratory factor analysis: a five-step guide for novices. Aust. J. Paramed., 8(3):1.1-1.13.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE