Crossing the legs at the knees, during BP measurement, is one of the several physiological stimuli that considerably influence the accuracy of BP measurements. Therefore, it is paramount to develop an appropriate prediction model for interpreting influence of crossed legs on BP. This research work described the use of principal component analysis (PCA) fused forward stepwise regression (FSWR), artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS), and least squares support vector machine (LSSVM) models for prediction of BP reactivity to crossed legs among the normotensive and hypertensive participants. The evaluation of the performance of the proposed prediction models using appropriate statistical indices showed that the PCAbased LSSVM (PCALSSVM) model has the highest prediction accuracy with coefficient of determination (
Accurate measurement of blood pressure (BP) is indispensable for the diagnosis of hypertension at its early stage. Hypertension appears as a top risk factor for lifethreatening conditions such as coronary artery disease, stroke, and kidney failure [
Recommendations of several international organisations including the AHA [
Correct positioning of a subject’s legs is often neglected during BP measurement. As it seems a comfortable position, subjects spontaneously cross their legs at the knees. Several clinical and research studies have been proved that crossing the legs at knee level during BP measurement has a potential effect on the accuracy of measurements. FosterFitzpatrick et al. demonstrated a significant increase in BP taken with the legs crossed at the knee level in hypertensive subjects [
Despite studies confirming the importance of leg position on BP measurement, it is likely that leg position varies markedly in clinical practice and also in published studies [
Moreover, there is growing evidence that anthropometric indices are a major determinant of BP. Several studies have been conducted in the past to identify anthropometric characteristics that can be used as markers of BP [
The various methods utilized for prediction of biological variables range from the traditional statistical models to the complicated artificial intelligencebased models [
HsinHsiuang et al. compared logistic regression, SVM, and permanental classification methods in predicting hypertension by using the genotype information. They used logistic regression analysis in the first step to detect significant singlenucleotide polymorphisms (SNPs). In the second step, they used the significant SNPs with logistic regression, SVM, and permanental classification methods for prediction purposes. The results showed that SVM and permanental classification both outperformed logistic regression [
To perform a better training process and improve the forecasting accuracy, hybrid computing models in medical diagnosis are being developed to support physicians in successful decision making regarding clinical admission, early prevention, early clinical diagnosis, and application of clinical therapies by allowing calculation of disease likelihood based on known subject characteristics and clinical test results [
The present study is a continuation of our previous studies [
A total of 40 normotensive and 30 hypertensive subjects among the students, staff, and faculty of Sant Longowal Institute of Engineering and Technology, Deemed University, Longowal, Distt. Sangrur, Punjab, INDIA, were included in this study. Participants were aged over 18 years. Exclusion criteria were pregnant subjects, arrhythmic subjects, and the subjects who had a history of any condition that would interfere with positioning of lower extremity of the subjects. The institutional research committee approved the research protocol and all participants gave written informed consent before participation.
A standard questionnaire was administrated for the collection of anthropometric data including age, height, weight, BMI, and midupper arm circumference (MUAC) of the participants. The mean and standard deviation (SD) of the collected anthropometric data is given in Table
Descriptive statistics of anthropometric characteristics of study samples.
Anthropometric characteristics  Normotensives  Hypertensives  

Mean  SD  Mean  SD  
Age (years)  23.1  1.24  42.83  6.665 
Height (cm)  1.61  0.03  1.583  0.035 
Weight (kg)  55.96  7.29  62.48  10.89 
BMI (kg/m^{2})  21.55  2.504  23.57  3.497 
MUAC (cm)  26.56  2.45  26.72  2.4 
A specially separated room was used to conduct this study. This ensured minimal interference within the room while the tests were being carried out. The observers involved in the study were trained using the BHS’s BP measurement training materials [
To eliminate the observer bias, BP was measured using a validated, newly purchased, and fully automated sphygmomanometer OMRON HEM7203 (OMRON HEALTHCARE Co. Ltd., Kyoto, Japan) that uses the oscillometric method of measurement. The BP monitor is available with a small cuff (17–22 cm), medium cuff (22–32 cm), and large cuff (32–42 cm). BP measurement was preceded by selection of the appropriate size cuff according to the MUAC of the subjects.
Subjects were advised to avoid alcohol, cigarette smoking, coffee/tea intake, and exercise for at least 30 minutes prior to their BP measurement. They were instructed to empty their bladder prior to measurements. Subjects were also instructed to sit upright on a chair with a supported back, kept the feet flat on the floor and the upper arm (under measurement) at heart level, as they are the potential confounding factors. Moreover, they were asked not to talk and move during measurement [
After a rest period of 5 minutes [
PCA is the first step of counteracting multicollinearity. It is a dimension reduction technique that does not take the correlation between the input variables into account. Thus, PCA is considered as an unsupervised dimension reduction method [
FSWR is a traditional statistical modeling technique used for developing an optimum prediction model by extracting the best anthropometric characteristics or predictor variables depending upon their statistical significance or probability (
To achieve the best architecture of ANN, various structures of feedforward ANN with different numbers of hidden layers and neurons in each hidden layer were investigated. Finally, in light of the performance indices obtained from investigations, an ANN structure with two hidden layers and six nodes in each hidden layer was selected for further analysis. In addition, the architecture of ANN also consisted of one input layer with four input nodes (representing four PCs) and one output layer with one output node (representing BP reactivity to crossed legs). The choice of hyperbolic tangent sigmoid activation function for hidden layer and linear activation function for output layer trained the network in lesser number of epochs with better performance criteria and also yielded the best outcome predictions. The back propagation learning algorithm based on the LevenbergMarquardt technique was used to find the local minimum of the error function. It blends the steepest descent method and the GaussNewton algorithm and inherits the speed advantage of the GaussNewton algorithm and the stability of the steepest descent method. It is more powerful and faster than the conventional gradient descent technique [
A Sugenotype FIS model was developed using “genfis1” with grid partitioning on data for prediction of BP reactivity to crossed legs. Different ANFIS parameters including numbers of membership functions (MFs) and types of input and output MF were tested to achieve the perfect training and maximum prediction accuracy. Input membership function “psigmf” and output membership function “linear” were used to develop the prediction model [
Other parameters of the trained ANFIS model were as follows: number of MFs = 16, number of nodes = 55, number of linear parameters = 80, number of nonlinear parameters = 32, total number of parameters = 112, and number of fuzzy rules = 16.
The most important steps to develop a LSSVM model are as follows: selection of a kernel and its parameters. After many experimental observations, radial basis function (RBF) kernel and grid search optimization algorithm (with 2fold crossvalidation) were selected to obtain the optimal combination of regularization parameter (
The results of the paired
A visual inspection of the Pearson’s correlation coefficients revealed the existence of multicollinearity, as correlation coefficient > 0.6 [
Pearson’s correlation coefficients between each pair of anthropometric characteristics in normotensive and hypertensive subjects.
Anthropometric characteristics  Height  Weight  BMI  MUAC 

Age (years)  0.535

0.784 
0.701 
0.668 
Height (cm)  0.543

0.237

0.619 

Weight (kg)  0.934 
0.743 

BMI (kg/m^{2})  0.617 
In the next step, PCA was used to omit the multicollinearity between pairs of anthropometric characteristics and simplify the complexity of the relationship between them [
To verify the applicability of PCA, Bartlett’s test of sphericity was applied [
Out of 5 PCs, only the first four PCs (PC1–PC4), explaining more than 5% of variations, were retained for further analysis. In normotensive subjects, the selected PCs explained 99.8% of the total variation. Variance proportions explained by PC1, PC2, PC3, and PC4 were found as 71.84%, 16.58%, 6.34%, and 5.04%, respectively. In hypertensive subjects, the selected PCs explained 98.04% of the total variation. Variance proportion accounted for by PC1, PC2, PC3, and PC4 was estimated to be 61.10%, 22.5%, 8.78%, and 5.66%, respectively. Loadings of anthropometric characteristics after varimax rotation give an indication of the extent to which the original variables are influential in forming new variables. For both normotensive and hypertensive subjects, weight and BMI were the characteristics having the highest correlation with PC1 and height had the highest correlation with PC2.
Moreover, Pearson’s correlation between pairs of PCs, as shown in Table
Pearson’s correlation coefficient between each pair of PCs in normotensive and hypertensive subjects.
PC  PC2  PC3  PC4 


−0.00000225

0.0000000798

−0.0000167


−7.237 
5.808 


−7.557 
Bold values indicate correlation in anthropometric characteristics of hypertensive subjects.
To develop PCAbased prediction models, principal score values obtained from the principle score coefficients were used as independent variables and BP reactivity was used as dependent variable. Moreover, 80% data were used for training while the entire data set was used for testing. Data were normalized before training to achieve more accurate predictions. MATLAB (version 7.5) was used to develop the prediction models.
When probabilities were taken into consideration, the regressions of standardized SBP reactivity on PC1 (composed of weight and BMI) were found statistically significant in normotensive subjects. Whereas, PC3 (composed of age) was found statistically significant for SBP and DBP reactivity in hypertensive subjects. Figures
Scatter plot between observed and predicted values of BP reactivity using the PCAFSWR model.
For normotensive SBP
For hypertensive SBP
For hypertensive DBP
The final model equations for prediction of BP reactivity in normotensive and hypertensive subjects are given as follows:
Model equation obtained for prediction of SBP reactivity in normotensive subjects:
Model equation obtained for prediction of SBP reactivity in hypertensive subjects:
Model equation obtained for prediction of DBP reactivity in hypertensive subjects:
The scatter plots between the observed and predicted values of BP reactivity from the PCAANN model, as illustrated in Figures
Scatter plot between observed and predicted values of BP reactivity using the PCAANN model.
For normotensive SBP
For hypertensive SBP
For hypertensive DBP
As presented in Figures
Scatter plot between observed and predicted values of BP reactivity using the PCAANFIS model.
For normotensive SBP
For hypertensive SBP
For hypertensive DBP
The optimal values of regularization parameter (
The scatter plots between the observed and predicted values of BP reactivity from PCALSSVM as shown in Figures
Scatter plot between observed and predicted values of BP reactivity using the PCALSSVM model.
For normotensive SBP
For hypertensive SBP
For hypertensive DBP
The comparison of statistical indices of the models, as shown in Table
Statistical indices for the proposed models.
Model  Normotensive subjects  Hypertensive subjects  

SBP  SBP  DBP  

RMSE  MAPE (%) 

RMSE  MAPE (%) 

RMSE  MAPE (%)  
PCAFSWR  29.05  2.21  40.33  38.35  3.66  48.35  37.21  1.49  22.72 
PCAANN  55.67  0.67  26.25  60.11  0.74  30.39  67.91  0.57  14.63 
PCAANFIS  75.42  0.67  17.39  84.81  0.44  6.74  84.26  0.44  5.06 
PCALSSVM  93.16  0.27  5.71  96.46  0.19  1.76  95.44  0.21  2.78 
Accurate prediction of BP is integral to successful decision making and leads to better patient care. Overestimation of BP would increase the number of patients with hypertension. They may experience adverse effects of medication and have increased insurance and treatment cost. Furthermore, the inaccurate labeling leads to an increased perception of disease and absenteeism from work [
The marked elevation in BP with the crossed leg position may be due to isometric activity of the leg muscles. Isometric activity increases vascular resistance or total peripheral resistance (TPR) and BP [
Evidently, this work demonstrates that crossed legs in sitting position significantly elevated SBP of normotensive subjects and SBP and DBP of hypertensive subjects. Similar conclusions were found by previous studies [
Furthermore, PCAbased hybrid computing models for predictions of BP reactivity to crossed legs are proposed in this paper. To the best of our knowledge, this is the first study that focused specifically on prediction of BP reactivity to crossed legs using the PCAFSWR, PCAANN, PCAANFIS, and PCALSSVM models. Therefore, the results were compared with indirectly related prediction studies, as shown in Table
Comparison of results with other studies.
Ref.  Model developed  Predicted parameter  Results 

[ 
Ridge linear regression, ANN, SVM, and random forest  BGL, BP  Random forest technique outperformed ridge linear regression, ANN, and SVM. 
[ 
ANN (raw input), ANN (feature based), MAA, and ANFIS (feature based)  SBP, DBP  ANN (feature based) achieved the best performance compared to other models. For SBP predictions: MAE = 6.28, SDE = 8.58. For DBP predictions: MAE = 5.73, SDE = 7.33 
[ 
ANN  SBP, DBP  The experimental results confirmed the correctness of the ANN when compared with the linear regression model. Mean ± 
[ 
SVM with RBF and polynomial kernel  SBP, DBP  SVM (RBF kernel) outperformed SVM (polynomial kernel). Coefficient of correlation ( 
[ 
PCAANN, PCAANFIS, and PCALSSVM  SBP, DBP  PCALSSVM outperformed PCAANN and PCAANFIS.

[ 
PCASWR, PCAANN, PCAANFIS, and PCALSSVM  DBP  PCALSSVM outperformed PCAFSWR, PCAANN, and PCAANFIS. For normotensive subjects: 
[ 
ANN, ANFIS, and SVM  River flow in the semiarid mountain region  In comparing the results of the ANN, ANFIS, and SVM models, it was seen that the values of 
[ 
ANN, ANFIS  To predict depthstowater table one month in advance, at three wells located at different distances from the river  Both models can be used with a high level of precision to the model water tables without a significant effect of the distance of the well from the river, as model precision expressed via RMSE was roughly the same in all three cases (0.14154–0.15248). 
[ 
ANN, ANFIS, and SVM  Longitudinal dispersion coefficient (LDC)  The SVM model was found to be superior ( 
[ 
Multilayer perceptron (MLP), ANN, fuzzy genetic (FG), LSSVM, multivariate adaptive regression spline (MARS), ANFIS, multiple linear regression (MLR), and Stephens and Stewart models (SS)  Evaporation in different climates  The accuracies of the applied models were rank as: MLP, GRNN, LSSVM, FG, ANFISGP, MARS, and MLR 
Present study  PCAFSWR, PCAANN, PCAANFIS, and PCALSSVM  BP reactivity to crossed legs  PCALSSVM outperformed PCAFSWR, PCAANN, and PCAANFIS. For normotensive subjects: SBP: 
In all studies, the higher performance of the soft computing models was sourced from a greater degree of robustness and fault tolerance than traditional models. The results of present research work illustrated that the PCALSSVM hybrid model obtained the best prediction results because LSSVM is firmly based on the theory of statistical learning; therefore, it can attain a global optimal solution and has good generalization ability and low dependency on sample data.
The present study has a number of merits. We used small, medium, and large size cuffs to cover the entire MUAC range demanded by participants. Inappropriate cuff size results in underestimation or overestimation of BP. Moreover, to strengthen the accuracy of measurements, we took the mean of three readings per leg position for seven days [
However, any single comparison between the prediction models might not reliably represent the true end results. It is essential to assess the performance of prediction models in external validation studies using larger database.
This paper has detailed an examination of hybrid computing models in an effort to predict BP reactivity to crossed legs using anthropometric predictor variables. By eliminating the multicollinearity problem, PCA provided more objective interpretation of anthropometric predictor variables used for prediction. Then, the PCAFSWR, PCAANN, PCAANFIS, and PCALSSVM models were tested for prediction of BP from PCs. It was found that the PCALSSVM model achieves substantial improvements in terms of
All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1975, as revised in 2008 (5).
Informed consent was obtained from all participants for being included in the study.
The authors declare that there is no conflict of interests regarding the publication of this paper.