A computational intelligence tool for the detection of hypertension using empirical mode decomposition

Soh, Desmond Chuang Kiat; Ng, E. Y. K.; Vicnesh, Jahmunah; Oh, Shu Lih; San, Tan Ru; Acharya, U. Rajendra

doi:10.1016/j.compbiomed.2020.103630

Cited by 45 publications

(46 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of author’s knowledge, this is the first study that uses the PuPG signals for discriminating among normal and hypertension with high precision. The current method achieves better performance than the existing ECG- [ 15 , 17 , 18 ], PPG- [ 12 , 19 ], HRV- [ 14 , 16 ], and BCG-based [ 20 ] approaches. Our method also outperforms the fusion-based method for detection of hypertension that utlized a combination of PPG and ECG [ 13 ].…”

Section: Discussionmentioning

confidence: 92%

“…In contrast, our work is targeted towards the classification of Normal and Hypertension classes through PuPG signals. In another study, [ 18 ] developed a computational intelligence tool based on ECG signals for the classification of normal and hypertension. EMD was employed in the signal preprocessing stage, followed by nonlinear feature extraction from the decomposed IMFs.…”

Section: Discussionmentioning

confidence: 99%

“…Despite promising results, this work suffers from a data imbalance problem. The authors in [ 18 ] proposed a method to detect ECG hypertensive signals using empirical mode decomposition (EMD) for preprocessing of the signals, yielding an accuracy of 97.7% through the KNN classifier. The extracted features were selected physically, making this process laborious.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Expert Hypertension Detection System Featuring Pulse Plethysmograph Signals and Hybrid Feature Selection and Reduction Scheme

Khan

Aziz

Akram

et al. 2021

Sensors

View full text Add to dashboard Cite

Hypertension is an antecedent to cardiac disorders. According to the World Health Organization (WHO), the number of people affected with hypertension will reach around 1.56 billion by 2025. Early detection of hypertension is imperative to prevent the complications caused by cardiac abnormalities. Hypertension usually possesses no apparent detectable symptoms; hence, the control rate is significantly low. Computer-aided diagnosis based on machine learning and signal analysis has recently been applied to identify biomarkers for the accurate prediction of hypertension. This research proposes a new expert hypertension detection system (EHDS) from pulse plethysmograph (PuPG) signals for the categorization of normal and hypertension. The PuPG signal data set, including rich information of cardiac activity, was acquired from healthy and hypertensive subjects. The raw PuPG signals were preprocessed through empirical mode decomposition (EMD) by decomposing a signal into its constituent components. A combination of multi-domain features was extracted from the preprocessed PuPG signal. The features exhibiting high discriminative characteristics were selected and reduced through a proposed hybrid feature selection and reduction (HFSR) scheme. Selected features were subjected to various classification methods in a comparative fashion in which the best performance of 99.4% accuracy, 99.6% sensitivity, and 99.2% specificity was achieved through weighted k-nearest neighbor (KNN-W). The performance of the proposed EHDS was thoroughly assessed by tenfold cross-validation. The proposed EHDS achieved better detection performance in comparison to other electrocardiogram (ECG) and photoplethysmograph (PPG)-based methods.

show abstract

Section: Discussionmentioning

confidence: 92%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Expert Hypertension Detection System Featuring Pulse Plethysmograph Signals and Hybrid Feature Selection and Reduction Scheme

Khan

Aziz

Akram

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…This could be due to the larger number of training features that was inputted into the k-NN classifier, versus the number of training features inputted into the DT classifier. For the LDA classifier, the accuracy decreases due to a larger number of features inputted to train the classifier[84].…”

mentioning

confidence: 99%

“…A special hypertension diagnosis index (HDI) was therefore developed to differentiate between low-risk and high-risk HPY classes using two feature sets from SFD and LOGE. The developed index system using a sample size of 51 patient was able to achieve classification of the high and low-risk HPY classes with 100% accuracy[84].Simjanoska et al[86] processed the ECG signals after acquisition. Six intricacy features were then extracted from the signals to form a feature vector, after which they were classified using two approaches: flat machine learning (ML) and stacking ML design.…”

mentioning

confidence: 99%