Automatic diagnosis of valvular heart diseases by impedance cardiography signal processing

Salah, Ihsen Ben; Rosa, R. de la; Ouni, Kaïs; Salah, R. Ben

doi:10.1016/j.bspc.2019.101758

Cited by 16 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, [27] shows that the SG filter is the most relevant for denoising ICG signals with better signal shape preservation, particularly the C peak amplitudes. Since the SG filter usage is very simple and efficient [28], we selected it for our methodology.…”

Section: B State-of-the-art Icg Preprocessing and Filtering Methodsmentioning

confidence: 99%

“…Most of the available methods, especially those using an assembling averaging step, utilize the R-peak from the ECG signal to define the beat-to-beat time interval in which to search for C peak, defined as the highest point of ICG signal. Many of them apply known R-peak detection algorithms (e.g., the Pan-Tompkins algorithm [28], [29]) to detect the C point due to the similarity between ECG and ICG signals.…”

Section: State-of-the-art Icg Delineation Methodsmentioning

confidence: 99%

“…They range from complex ones [22], [31] (e.g., time-frequency analysis and wavelet-based) to simple condition checking. The simplest approach to detect the X point is as the first minimum after C wave [13], [28], [32] or the lowest minimum within a given interval (i.e., in the first one-third of the C-C interval) [7]. However, since the X point is defined as the onset of steep rise towards the O point, some algorithms apply different conditions to detect the X-O pair [11], [29].…”

Section: State-of-the-art Icg Delineation Methodsmentioning

confidence: 99%

“…However, to properly denoise the signal, the polynomial degree should be selected. Authors in [13], [28] found that the SG filter with a polynomial of order 3 has the lowest error rate for different ICG Signal to Noise Ratios (SNRs). Further, the filter length ("the smoothing window") strongly influences filter effectiveness.…”

Section: A Icg Preprocessing Using the Sg Filtermentioning

confidence: 99%

See 3 more Smart Citations

ReBeatICG: Real-time Low-Complexity Beat-to-beat Impedance Cardiogram Delineation Algorithm

Pale¹,

Müller²,

Arza³

et al. 2021

Preprint

View full text Add to dashboard Cite

This work presents ReBeatICG, a real-time, lowcomplexity beat-to-beat impedance cardiography (ICG) delineation algorithm that allows hemodynamic parameters monitoring. The proposed procedure relies only on the ICG signal compared to most algorithms found in the literature that rely on synchronous electrocardiogram signal (ECG) recordings. ReBeatICG was designed with implementation on an ultra-lowpower microcontroller (MCU) in mind. The detection accuracy of the developed algorithm is tested against points manually labeled by cardiologists. It achieves a detection Gmean accuracy of 94.9%, 98.6%, 90.3%, and 84.3% for the B, C, X, and O points, respectively. Furthermore, several hemodynamic parameters were calculated based on annotated characteristic points and compared with values generated from the cardiologists' annotations. ReBeatICG achieved mean error rates of 0.11 ms, 9.72 ms, 8.32 ms, and 3.97% for HR, LVET, IVRT, and relative C-point amplitude, respectively.

show abstract

Section: B State-of-the-art Icg Preprocessing and Filtering Methodsmentioning

confidence: 99%

Section: State-of-the-art Icg Delineation Methodsmentioning

confidence: 99%

Section: State-of-the-art Icg Delineation Methodsmentioning

confidence: 99%

Section: A Icg Preprocessing Using the Sg Filtermentioning

confidence: 99%

See 2 more Smart Citations

ReBeatICG: Real-time Low-Complexity Beat-to-beat Impedance Cardiogram Delineation Algorithm

Pale¹,

Müller²,

Arza³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Here, we explore an alternative route that could be useful if big data are available and good scalability or a highly non-linear classifier is desired. Other related work is that of [ 20 ], who studied various machine learning algorithms (e.g., random forests and support vector machines) in combination with data pre-processing of ICG signals for the detection of valvular diseases. ICG has also been used to estimate hemodynamic parameters, e.g., cardiac output [ 21 , 22 , 23 ].…”

Section: Introductionmentioning

confidence: 99%

Cross-Entropy Learning for Aortic Pathology Classification of Artificial Multi-Sensor Impedance Cardiography Signals

Spindelböck

Ranftl

Linden

2021

Entropy

View full text Add to dashboard Cite

An aortic dissection, a particular aortic pathology, occurs when blood pushes through a tear between the layers of the aorta and forms a so-called false lumen. Aortic dissection has a low incidence compared to other diseases, but a relatively high mortality that increases with disease progression. An early identification and treatment increases patients’ chances of survival. State-of-the-art medical imaging techniques have several disadvantages; therefore, we propose the detection of aortic dissections through their signatures in impedance cardiography signals. These signatures arise due to pathological blood flow characteristics and a blood conductivity that strongly depends on the flow field, i.e., the proposed method is, in principle, applicable to any aortic pathology that changes the blood flow characteristics. For the signal classification, we trained a convolutional neural network (CNN) with artificial impedance cardiography data based on a simulation model for a healthy virtual patient and a virtual patient with an aortic dissection. The network architecture was tailored to a multi-sensor, multi-channel time-series classification with a categorical cross-entropy loss function as the training objective. The trained network typically yielded a specificity of (93.9±0.1)% and a sensitivity of (97.5±0.1)%. A study of the accuracy as a function of the size of an aortic dissection yielded better results for a small false lumen with larger noise, which emphasizes the question of the feasibility of detecting aortic dissections in an early state.

show abstract

Monitoring of false lumen thrombosis in type B aortic dissection by impedance cardiography – A multiphysics simulation study

Badeli

Jafarinia

Melito

et al. 2022

Numer Methods Biomed Eng

View full text Add to dashboard Cite

Aortic dissection is caused by a tear on the aortic wall that allows blood to flow through the wall layers. Usually, this tear involves the intimal and partly the medial layer of the aortic wall. As a result, a new false lumen develops besides the original aorta, denoted then as the true lumen. The local hemodynamic conditions such as flow disturbances, recirculations and low wall shear stress may cause thrombus formation and growth in the false lumen. Since the false lumen status is a significant predictor for late-dissection-related deaths, it is of great importance in the medical management of patients with aortic dissection. The hemodynamic changes in the aorta also alter the electrical conductivity of blood. Since the blood is much more conductive than other tissues in the body, such changes can be identified with non-invasive methods such as impedance cardiography. Therefore, in this study, the capability of impedance cardiography in monitoring thrombosis in the false lumen is studied by multiphysics simulations to assist clinicians in the medical management of patients under treatment.To tackle this problem, a 3D computational fluid dynamics simulation has been set up to model thrombosis in the false lumen and its impact on the blood flow-induced conductivity changes. The electrical conductivity changes of blood have been assigned as material properties of the blood-filled aorta in a 3D finite element electric simulation model to investigate the impact of conductivity changes on the measured impedance from the body's surface.The results show remarkable changes in the electrical conductivity distribution in the measurement region due to thrombosis in the false lumen, which significantly impacts the morphology of the impedance cardiogram. Thus, frequent † Vahid Badeli and Alireza Jafarinia contributed equally to this work

show abstract

Automatic diagnosis of valvular heart diseases by impedance cardiography signal processing

Cited by 16 publications

References 35 publications

ReBeatICG: Real-time Low-Complexity Beat-to-beat Impedance Cardiogram Delineation Algorithm

ReBeatICG: Real-time Low-Complexity Beat-to-beat Impedance Cardiogram Delineation Algorithm

Cross-Entropy Learning for Aortic Pathology Classification of Artificial Multi-Sensor Impedance Cardiography Signals

Monitoring of false lumen thrombosis in type B aortic dissection by impedance cardiography – A multiphysics simulation study

Contact Info

Product

Resources

About