A Novel Continuous Blood Pressure Estimation Approach Based on Data Mining Techniques

Abstract

Continuous blood pressure (BP) estimation using pulse transit time (PTT) is a promising method for unobtrusive BP measurement. However, the accuracy of this approach must be improved for it to be viable for a wide range of applications. This study proposes a novel continuous BP estimation approach that combines data mining techniques with a traditional mechanism-driven model. First, 14 features derived from simultaneous electrocardiogram and photoplethysmogram signals were extracted for beat-to-beat BP estimation. A genetic algorithm-based feature selection method was then used to select BP indicators for each subject. Multivariate linear regression and support vector regression were employed to develop the BP model. The accuracy and robustness of the proposed approach were validated for static, dynamic, and follow-up performance. Experimental results based on 73 subjects showed that the proposed approach exhibited excellent accuracy in static BP estimation, with a correlation coefficient and mean error of 0.852 and -0.001 ± 3.102 mmHg for systolic BP, and 0.790 and -0.004 ± 2.199 mmHg for diastolic BP. Similar performance was observed for dynamic BP estimation. The robustness results indicated that the estimation accuracy was lower by a certain degree one day after model construction but was relatively stable from one day to six months after construction. The proposed approach is superior to the state-of-the-art PTT-based model for an approximately 2-mmHg reduction in the standard derivation at different time intervals, thus providing potentially novel insights for cuffless BP estimation.

Continuous Blood Pressure Measurement From Invasive to Unobtrusive: Celebration of 200th Birth Anniversary of Carl Ludwig

“…A feature selection method was then employed to eliminate irrelevant and redundant features to avoid over fitting. For instance, A genetic algorithm-based feature selection method was proposed [104] to find the optimal feature set before model development for BP estimation and thus achieved good accuracy. Machine learning methods such as linear regression, neural network, Bayesian network, and support vector machine can be used to develop the BP model.…”

Flick Fortune: Movie Gross Prediction using Data Analysis and Prediction

“…In 2006, Sharda and Delen worked with predicting financial success of movies even before the movie is released [3]. Classification ©IJRASET (UGC Approved Journal): All Rights are Reserved approach is used where the movies were categorized from flop to blockbuster.…”

“…Information filtering methods are mostly researched among related methods. The research direction of recommendation system is divided by content-based recommendation and collaborative filtering [3] [4]. And, it is easy excessively to characterize and restrict if system is usually following similar item with user preference [5]- [7].…”

“…Databases which originate from transactions in a supermarket, bank, department stores and, etc., are all inherently related to time. These are called temporal databases which are databases that contain time-stamping information [3]. One important extension to frequent pattern mining is to include a temporal dimension [4].…”

Deep learning for prediction of cardiac indices from photoplethysmographic waveform: A virtual database approach

“…Artificial neural networks (ANNs) were applied by Wu et al, 15 who predicted SBP from body mass index, age, exercise, alcohol, and smoke level data, and We et al, 16 who predicted SBP using data consisting of gender, serum cholesterol, fasting blood sugar, and features from electrocardiogram (ECG) signal. There are also several studies considering prediction of SBP and DBP using features extracted from ECG and PPG signals (eg, PAT times, peak widths, and positions) applying, for example, linear regression, 17,18 support vector machine regression, [17][18][19][20] decision trees, 17 random forests, 17,21 and ANNs. 22 In our previous work, 23 we carried out a numerical study to assess the accuracy of aortic pulse wave velocity (aPWV), DBP/SBP, and SV predictions based on PTT or PAT measurements.…”