A New Method for Cardiac Diseases Diagnosis

Salah, R. Ben; Alhadidi, Tareq; Mansouri, S.; Naouar, Mounir

doi:10.4236/abb.2015.64030

Cited by 15 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On average, each source provides 35. 6 features, suggesting that all signals contain valuable information for the binary classification.…”

Section: Feature Analysis and Selection Results For Conventional ML Mmentioning

confidence: 99%

“…Wearable, noninvasive modalities can be promising in addressing the need for an out-of-the-clinic device. For instance, impedance cardiography (ICG) has been studied for evaluating the health status of heart valves 6 , 7 . Cardio-mechanical signals, the vibrations created by heart activities that propagate to the chest wall, are another category of modalities that have been used in the literature.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of aortic stenosis using conventional machine learning and deep learning methods based on multi-dimensional cardio-mechanical signals

Yang

Ojha

Aranoff

et al. 2020

Sci Rep

View full text Add to dashboard Cite

This paper introduces a study on the classification of aortic stenosis (AS) based on cardio-mechanical signals collected using non-invasive wearable inertial sensors. Measurements were taken from 21 AS patients and 13 non-AS subjects. A feature analysis framework utilizing Elastic Net was implemented to reduce the features generated by continuous wavelet transform (CWT). Performance comparisons were conducted among several machine learning (ML) algorithms, including decision tree, random forest, multi-layer perceptron neural network, and extreme gradient boosting. In addition, a two-dimensional convolutional neural network (2D-CNN) was developed using the CWT coefficients as images. The 2D-CNN was made with a custom-built architecture and a CNN based on Mobile Net via transfer learning. After the reduction of features by 95.47%, the results obtained report 0.87 on accuracy by decision tree, 0.96 by random forest, 0.91 by simple neural network, and 0.95 by XGBoost. Via the 2D-CNN framework, the transfer learning of Mobile Net shows an accuracy of 0.91, while the custom-constructed classifier reveals an accuracy of 0.89. Our results validate the effectiveness of the feature selection and classification framework. They also show a promising potential for the implementation of deep learning tools on the classification of AS.

show abstract

“…On average, each source provides 35. 6 features, suggesting that all signals contain valuable information for the binary classification.…”

Section: Feature Analysis and Selection Results For Conventional ML Mmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification of aortic stenosis using conventional machine learning and deep learning methods based on multi-dimensional cardio-mechanical signals

Yang

Ojha

Aranoff

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Valvular heart disease (VHD) [ 40 ] is characterized by the affection of one or more heart valves: mitral [ 41 , 42 , 43 ], aortic [ 44 ], tricuspid or pulmonary valves and it is usually diagnosed using Doppler echocardiography.…”

Section: Valvular Heart Diseasementioning

confidence: 99%

Cardiovascular diseases diagnosis by impedance cardiography

Mansouri

Alharbi

Alshrouf

et al. 2022

Journal of Electrical Bioimpedance

View full text Add to dashboard Cite

Cardiovascular disease (CVD) represents the leading cause of mortality worldwide. In order to diagnose CVDs, there are a range of detection methods, among them, the impedance cardiography technique (ICG). It is a non-invasive and low-cost method. In this paper, we highlight recent advances and developments of the CDVs diagnosis mainly by the ICG method. We considered papers published during the last five years (from 2017 until 2022). Based on this study, we expressed the need for an ICG database for the different CDVs.

show abstract

“…They worked with the normal and abnormal ICG signal for the cardiovascular diseases detection, using a CAD system (Computer Aided Diagnosis system) for that. This study based on (1) Temporal, (2) spectral features, and (3) classification with the linear discriminant method [44]. The ICG technique solves the Doppler ultrasound problem which is used to examine cardiovascular diseases as valve heart disease (VHD) but it is expensive, and requires expertise to perform it and discontinuity.…”

Section: T Bmentioning

confidence: 99%

The impedance cardiography technique in medical diagnosis

Benabdallah

Kerai

2018

Mèd Technologies J.

View full text Add to dashboard Cite

Background: Thoracic Electrical Bioimpedance (TEB) Technology sometimes called the Impedance Cardiography (ICG). In 1940, the Impedance Cardiography emerged; the studies of this technique are realized to the cardiovascular diseases detection which used hemodynamic parameters measurements based on the skin electrodes contact by injecting a low amplitude alternating signal. The objective of this article is to review the various studies based on this signal type and to present the multiple methods used for the treatment and to have a correct analysis. Methods: This ICG technique consists for applying an electric field longitudinally across a segment of the thorax with amplitude in mean, high frequency and low amplitude current. To analyze the ICG signal, the signal denoising is necessary that’s why a multiple filters are proposed, and the Discrete Wavelet Transform (DWT) denoising is also used. Results: The ICG is considered advantageous compared to other invasive conventional techniques; it gives a good correlation, and solves the Doppler ultrasound and Thermodilution problems. According to the studies, the Daubechies wavelet family (db8) is the best DWT to eliminate the noises. There are several algorithms for the signal characteristic point’s detection. Conclusion: For the purpose of cardiovascular disease diagnosis and monitoring, the non-invasive ICG technique comes to solve the complexity problem for measurement and analyzing heart disease based on the thoracic electrical impedance change assessment that is due to blood velocity and resistivity changes (blood volume changes) in order to estimate several hemodynamic parameters. Keywords: ICG, cardiovascular disease, hemodynamic parameters, diagnosis and monitoring, correct analysis.

show abstract

A New Method for Cardiac Diseases Diagnosis

Cited by 15 publications

References 8 publications

Classification of aortic stenosis using conventional machine learning and deep learning methods based on multi-dimensional cardio-mechanical signals

Classification of aortic stenosis using conventional machine learning and deep learning methods based on multi-dimensional cardio-mechanical signals

Cardiovascular diseases diagnosis by impedance cardiography

The impedance cardiography technique in medical diagnosis

Contact Info

Product

Resources

About