Umeå University's logo

umu.sePublications
Change search
Link to record
Permanent link

Direct link
Benouar, Sara
Publications (10 of 11) Show all publications
Benouar, S., Kedir-Talha, M. & Seoane, F. (2023). Time-series NARX feedback neural network for forecasting impedance cardiography ICG missing points: a predictive model. Frontiers in Physiology, 14, Article ID 1181745.
Open this publication in new window or tab >>Time-series NARX feedback neural network for forecasting impedance cardiography ICG missing points: a predictive model
2023 (English)In: Frontiers in Physiology, E-ISSN 1664-042X, Vol. 14, article id 1181745Article in journal (Other academic) Published
Abstract [en]

One of the crucial steps in assessing hemodynamic parameters using impedance cardiography (ICG) is the detection of the characteristic points in the dZ/dt ICG complex, especially the X point. The most often estimated parameters from the ICG complex are stroke volume and cardiac output, for which is required the left ventricular pre-ejection time. Unfortunately, for beat-to-beat calculations, the accuracy of detection is affected by the variability of the ICG complex subtypes. Thus, in this work, we aim to create a predictive model that can predict the missing points and decrease the previous work percentages of missing points to support the detection of ICG characteristic points and the extraction of hemodynamic parameters according to several existing subtypes. Thus, a time-series non-linear autoregressive model with exogenous inputs (NARX) feedback neural network approach was implemented to forecast the missing ICG points according to the different existing subtypes. The NARX was trained on two different datasets with an open-loop mode to ensure that the network is fed with correct feedback inputs. Once the training is satisfactory, the loop can be closed for multi-step prediction tests and simulation. The results show that we can predict the missing characteristic points in all the complexes with a success rate ranging between 75% and 88% in the evaluated datasets. Previously, without the NARX predictive model, the successful detection rate was 21%–30% for the same datasets. Thus, this work indicates a promising method and an accuracy increase in the detection of X, Y, O, and Z points for both datasets.

Place, publisher, year, edition, pages
Frontiers Media S.A., 2023
Keywords
artificial neural networks, NARX, impedance cardiography, machine learning, time-series predictive model, characteristic point detection
National Category
Computer Sciences Other Engineering and Technologies
Identifiers
urn:nbn:se:umu:diva-213012 (URN)10.3389/fphys.2023.1181745 (DOI)001015238500001 ()37346485 (PubMedID)2-s2.0-85162206317 (Scopus ID)
Available from: 2023-08-18 Created: 2023-08-18 Last updated: 2024-01-17Bibliographically approved
Benouar, S., Hafid, A., Kedir-Talha, M. & Seoane, F. (2021). Classification of impedance cardiography dZ/dt complex subtypes using pattern recognition artificial neural networks. Biomedizinische Technik (Berlin. Zeitschrift), 66(5), 515-527
Open this publication in new window or tab >>Classification of impedance cardiography dZ/dt complex subtypes using pattern recognition artificial neural networks
2021 (English)In: Biomedizinische Technik (Berlin. Zeitschrift), ISSN 1862-278X, E-ISSN 0013-5585, Vol. 66, no 5, p. 515-527Article in journal (Refereed) Published
Abstract [en]

In impedance cardiography (ICG), the detection of dZ/dt signal (ICG) characteristic points, especially the X point, is a crucial step for the calculation of hemodynamic parameters such as stroke volume (SV) and cardiac output (CO). Unfortunately, for beat-to-beat calculations, the accuracy of the detection is affected by the variability of the ICG complex subtypes. Thus, in this work, automated classification of ICG complexes is proposed to support the detection of ICG characteristic points and the extraction of hemodynamic parameters according to several existing subtypes. A novel pattern recognition artificial neural network (PRANN) approach was implemented, and a divide-and-conquer strategy was used to identify the five different waveforms of the ICG complex waveform with output nodes no greater than 3. The PRANN was trained, tested and validated using a dataset from four volunteers from a measurement of eight electrodes. Once the training was satisfactory, the deployed network was validated on two other datasets that were completely different from the training dataset. As an additional performance validation of the PRANN, each dataset included four volunteers for a total of eight volunteers. The results show an average accuracy of 96% in classifying ICG complex subtypes with only a decrease in the accuracy to 83 and 80% on the validation datasets. This work indicates that the PRANN is a promising method for automated classification of ICG subtypes, facilitating the investigation of the extraction of hemodynamic parameters from beat-to-beat dZ/dt complexes.

Place, publisher, year, edition, pages
Walter de Gruyter, 2021
Keywords
artificial neural networks, feedforward backpropagation, impedance cardiography, machine learning, pattern recognition, synthetic data
National Category
Engineering and Technology
Identifiers
urn:nbn:se:umu:diva-213082 (URN)10.1515/bmt-2020-0267 (DOI)000705925800007 ()34162027 (PubMedID)2-s2.0-85109074049 (Scopus ID)
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-08-22Bibliographically approved
Hafid, A., Benouar, S., Cherrih, H., Ali, B. & Talha, M. K. (2021). EMG & EIMG measurement for Arm & Hand motions using custom made instrumentation based on Raspberry PI. In: 2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH): . Paper presented at IHSH 2020, 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being, Boumerdes, Algeria, February 9-10, 2021 (pp. 54-58). IEEE
Open this publication in new window or tab >>EMG & EIMG measurement for Arm & Hand motions using custom made instrumentation based on Raspberry PI
Show others...
2021 (English)In: 2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH), IEEE, 2021, p. 54-58Conference paper, Published paper (Refereed)
Abstract [en]

Recording and processing physiological signal that give intrinsic characteristics information is one of scientific community needs. Electromyography (EMG) and Electrical Impedance Myography (EIMG) are both non-invasive approaches to measure and evaluate the muscle conditions and activity. Z-RPI device is a custom-made measurement device developed basically for ECG and ICG records. This paper presents the feasibility of acquiring surface EMG and EIMG signal of biceps and forearm muscle contractions using the Z-RPI device. The results obtained are acceptable, encouraging and converge to literature result. Thus, it shows that the Z-RPI device can be used for relatively several biomedical applications other than the ECG and ICG measurement. For supporting developers in research and engineering education.

Place, publisher, year, edition, pages
IEEE, 2021
Keywords
Electromyiography, Eelctrical impedance myography, Rapsberry PI, Biomedical System, motions detection
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:umu:diva-213091 (URN)10.1109/ihsh51661.2021.9378716 (DOI)2-s2.0-85103832073 (Scopus ID)978-1-6654-4084-4 (ISBN)978-1-6654-3125-5 (ISBN)
Conference
IHSH 2020, 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being, Boumerdes, Algeria, February 9-10, 2021
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-08-22Bibliographically approved
Hafid, A., Benouar, S., Kedir-Talha, M. & Seoane, F. (2020). Evaluation of dZ/dt complex subtypes vs ensemble averaging method for estimation of left ventricular ejection time from ICG recording. In: Tomaz Jarm; Aleksandra Cvetkoska; Samo Mahnič-Kalamiza; Damijan Miklavcic (Ed.), 8th European Medical and Biological Engineering Conference: Proceedings of the EMBEC 2020, November 29 – December 3, 2020 Portorož, Slovenia. Paper presented at 8th European Medical and Biological Engineering Conference EMBEC 2020, Portorož, Slovenia, November 29 – December 3, 2020. (pp. 502-509). Springer, 80
Open this publication in new window or tab >>Evaluation of dZ/dt complex subtypes vs ensemble averaging method for estimation of left ventricular ejection time from ICG recording
2020 (English)In: 8th European Medical and Biological Engineering Conference: Proceedings of the EMBEC 2020, November 29 – December 3, 2020 Portorož, Slovenia / [ed] Tomaz Jarm; Aleksandra Cvetkoska; Samo Mahnič-Kalamiza; Damijan Miklavcic, Springer, 2020, Vol. 80, p. 502-509Conference paper, Published paper (Refereed)
Abstract [en]

Impedance cardiography (ICG) was discovered nearly half a century ago, being proposed as noninvasive monitoring method for estimation of several hemodynamics parameter. Despite of nearly 5 decades of clinical research and use there is still certain controversy about its performance when estimating Left Ventricular Ejection Time (LVET). This work present a comparison between using the different ICG subtype waveform and the ensemble averaged (EA) method to calculate the LVET. The ICG has been recorded from four volunteers, and the LVET parameter has been calculated using the two approaches. The result shows that each volunteer have different percentage of subtypes, and the mean relative error between the two approaches for estimation of LVET varied between 0.62 to 2.9% with an average mean absolute percentage error of 18,02% ranging between 13.82 to 18.42%.

Place, publisher, year, edition, pages
Springer, 2020
Series
IFMBE Proceedings, ISSN 1680-0737, E-ISSN 1433-9277 ; 80
Keywords
Impedance, cardiography, X point, LVET, Ensemble averaging, Subtype waveform
National Category
Engineering and Technology Computer Sciences
Identifiers
urn:nbn:se:umu:diva-213093 (URN)10.1007/978-3-030-64610-3_57 (DOI)2-s2.0-85097594826 (Scopus ID)978-3-030-64610-3 (ISBN)978-3-030-64609-7 (ISBN)
Conference
8th European Medical and Biological Engineering Conference EMBEC 2020, Portorož, Slovenia, November 29 – December 3, 2020.
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-08-23Bibliographically approved
Benouar, S., Hafid, A., Kedir-Talha, M. & Seoane, F. (2020). First steps toward automated classification of impedance cardiography dZ/dt complex subtypes. In: Tomaz Jarm; Aleksandra Cvetkoska; Samo Mahnič-Kalamiza; Damijan Miklavcic (Ed.), 8th European Medical and Biological Engineering Conference: Proceedings of the EMBEC 2020, November 29 – December 3, 2020 Portorož, Slovenia. Paper presented at 8th European Medical and Biological Engineering Conference, EMBEC 2020, Portorož, Slovenia, 29 November - 3 December 2020. (pp. 563-573). Springer, 80
Open this publication in new window or tab >>First steps toward automated classification of impedance cardiography dZ/dt complex subtypes
2020 (English)In: 8th European Medical and Biological Engineering Conference: Proceedings of the EMBEC 2020, November 29 – December 3, 2020 Portorož, Slovenia / [ed] Tomaz Jarm; Aleksandra Cvetkoska; Samo Mahnič-Kalamiza; Damijan Miklavcic, Springer, 2020, Vol. 80, p. 563-573Conference paper, Published paper (Refereed)
Abstract [en]

The detection of the characteristic points of the complex of the impedance cardiography (ICG) is a crucial step for the calculation of hemodynamical parameters such as left ventricular ejection time, stroke volume and cardiac output. Extracting the characteristic points from the dZ/dt ICG signal is usually affected by the variability of the ICG complex and assembling average is the method of choice to smooth out such variability. To avoid the use of assembling average that might filter out information relevant for the hemodynamic assessment requires extracting the characteristics points from the different subtypes of the ICG complex. Thus, as a first step to automatize the extraction parameters, the aim of this work is to detect automatically the kind of dZ/dt complex present in the ICG signal. To do so artificial neural networks have been designed with two different configurations for pattern matching (PRANN) and tested to identify the 6 different ICG complex subtypes. One of the con figurations implements a 6-classes classifier and the other implemented the divide and conquer approach classifying in two stages. The data sets used in the training, validation and testing process of the PRANNs includes a matrix of 1 s windows of the ICG complexes from the 60 s long recordings of dZ/dt signal for each of the 4 healthy male volunteers. A total of 240 s. As a result, the divide and conquer approach improve the overall classification obtained with the one stage approach on +26% reaching and average classification ration of 82%.

Place, publisher, year, edition, pages
Springer, 2020
Series
IFMBE Proceedings, ISSN 1680-0737, E-ISSN 1433-9277 ; 80
Keywords
Bioimpedance, Impedance cardiography, dZ/dt signal, ABEXYOZ complex, Classifi cation, Pattern recognition, Artificial neural networks, Feed-forward backpropagation
National Category
Engineering and Technology Computer Sciences
Identifiers
urn:nbn:se:umu:diva-213089 (URN)10.1007/978-3-030-64610-3_64 (DOI)2-s2.0-85097612077 (Scopus ID)978-3-030-64610-3 (ISBN)978-3-030-64609-7 (ISBN)
Conference
8th European Medical and Biological Engineering Conference, EMBEC 2020, Portorož, Slovenia, 29 November - 3 December 2020.
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-08-23Bibliographically approved
Acef, L., Bouzergui, F., Benouar, S., Hafid, A. & Ferroukhi, M. (2019). Low cost electronic instrumentation solutions for cardiovascular parameters measurement. In: 2019 International Conference on Advanced Electrical Engineering (ICAEE): . Paper presented at 2019 International Conference on Advanced Electrical Engineering (ICAEE), Algiers, Algeria, November 19-21, 2019 (pp. 1-5). IEEE
Open this publication in new window or tab >>Low cost electronic instrumentation solutions for cardiovascular parameters measurement
Show others...
2019 (English)In: 2019 International Conference on Advanced Electrical Engineering (ICAEE), IEEE, 2019, p. 1-5Conference paper, Published paper (Refereed)
Abstract [en]

Cardiovascular activity is one of the primordial physiological phenomena of human life. However, it is subject to many pathologies due to various factors such as: lifestyle, age, diabetes, cholesterol or heredity. As a consequence, there are different kinds of examination and methods used to enable the diagnostic. In this paper cardiovascular parameters are calculated due to the acquisition of simultaneous electrocardiography (ECG) and photoplethysmography (PPG) signals and the high limb peripheral arterial stiffness is evaluated by the calculation of the Pulse Wave Velocity (PWV) parameter. Those measurements are performed by two different low-cost systems based on Arduino board. The acquired waveforms form each device prototype present a satisfactory result, and the cardiovascular parameters are in the range of the value found in the literature. The developed prototype devices could easily be used for engineering educational purposes, hobby or first steps research.

Place, publisher, year, edition, pages
IEEE, 2019
Keywords
Cardiovascular activity, arterial stiffness, ECG, PPG, pulse transit time, Pulse Wave Velocity, biomedical instrumentation, embedded system
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:umu:diva-213094 (URN)10.1109/icaee47123.2019.9014818 (DOI)000559804400099 ()2-s2.0-85079225766 (Scopus ID)978-1-7281-2220-5 (ISBN)978-1-7281-2219-9 (ISBN)978-1-7281-2221-2 (ISBN)
Conference
2019 International Conference on Advanced Electrical Engineering (ICAEE), Algiers, Algeria, November 19-21, 2019
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-08-22Bibliographically approved
Hafid, A., Benouar, S., Kedir-Talha, M., Abtahi, F., Attari, M. & Seoane, F. (2018). Full impedance cardiography measurement device using raspberry PI3 and system-on-chip biomedical instrumentation solutions. IEEE journal of biomedical and health informatics, 22(6), 1883-1894
Open this publication in new window or tab >>Full impedance cardiography measurement device using raspberry PI3 and system-on-chip biomedical instrumentation solutions
Show others...
2018 (English)In: IEEE journal of biomedical and health informatics, ISSN 2168-2194, E-ISSN 2168-2208, Vol. 22, no 6, p. 1883-1894Article in journal (Refereed) Published
Abstract [en]

Impedance cardiography (ICG) is a noninvasive method for monitoring cardiac dynamics using electrical bioimpedance (EBI) measurements. Since its appearance more than 40 years ago, ICG has been used for assessing hemodynamic parameters. This paper presents a measurement system based on two System on Chip (SoC) solutions and Raspberry PI, implementing both a full three-lead ECG recorder and an impedance cardiographer, for educational and research development purposes. Raspberry PI is a platform supporting Do-It-Yourself project and education applications across the world. The development is part of Biosignal PI, an open hardware platform focusing in quick prototyping of physiological measurement instrumentation. The SoC used for sensing cardiac biopotential is the ADAS1000, and for the EBI measurement is the AD5933. The recordings were wirelessly transmitted through Bluetooth to a PC, where the waveforms were displayed, and hemodynamic parameters such as heart rate, stroke volume, ejection time and cardiac output were extracted from the ICG and ECG recordings. These results show how Raspberry PI can be used for quick prototyping using relatively widely available and affordable components, for supporting developers in research and engineering education. The design and development documents will be available on www.BiosignalPI.com, for open access under a Non Commercial-Share A like 4.0 International License.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
AD5933, ADAS1000, bioimpedance, biosignal PI, biomedical instrumentation, cardiac monitoring, personalized healthcare, portable ECG, ICG, Raspberry PI3
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:umu:diva-213079 (URN)10.1109/jbhi.2017.2783949 (DOI)000447833100019 ()29990025 (PubMedID)2-s2.0-85038859857 (Scopus ID)
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-08-21Bibliographically approved
Hafid, A., Benouar, S., Kedir-Talha, M., Attari, M. & Seoane, F. (2018). Simultaneous Recording of ICG and ECG Using Z-RPI Device with Minimum Number of Electrodes. Journal of Sensors, 2018, Article ID 3269534.
Open this publication in new window or tab >>Simultaneous Recording of ICG and ECG Using Z-RPI Device with Minimum Number of Electrodes
Show others...
2018 (English)In: Journal of Sensors, ISSN 1687-725X, E-ISSN 1687-7268, Vol. 2018, article id 3269534Article in journal (Refereed) Published
Abstract [en]

Impedance cardiography (ICG) is a noninvasive method for monitoring mechanical function of the heart with the use of electrical bioimpedance measurements. This paper presents the feasibility of recording an ICG signal simultaneously with electrocardiogram signal (ECG) using the same electrodes for both measurements, for a total of five electrodes rather than eight electrodes. The device used is the Z-RPI. The results present good performance and show waveforms presenting high similarity with the different signals reported using different electrodes for acquisition; the heart rate values were calculated and they present accurate evaluation between the ECG and ICG heart rates. The hemodynamics and cardiac parameter results present similitude with the physiological parameters for healthy people reported in the literature. The possibility of reducing number of electrodes used for ICG measurement is an encouraging step to enabling wearable and personal health monitoring solutions.

Place, publisher, year, edition, pages
Hindawi Publishing Corporation, 2018
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:umu:diva-213086 (URN)10.1155/2018/3269534 (DOI)000453004900001 ()2-s2.0-85062625652 (Scopus ID)
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-08-24Bibliographically approved
Benouar, S., Hafid, A., Attari, M., Kedir-Talha, M. & Seoane, F. (2018). Systematic variability in ICG recordings results in ICG complex subtypes: steps towards the enhancement of ICG characterization. Journal of Electrical Bioimpedance, 9(1), 72-82
Open this publication in new window or tab >>Systematic variability in ICG recordings results in ICG complex subtypes: steps towards the enhancement of ICG characterization
Show others...
2018 (English)In: Journal of Electrical Bioimpedance, E-ISSN 1891-5469, Vol. 9, no 1, p. 72-82Article in journal (Refereed) Published
Abstract [en]

The quality of an impedance cardiography (ICG) signal critically impacts the calculation of hemodynamic parameters. These calculations depend solely on the identification of ICG characteristic points on the ABEXYOZ complex. Unfortunately, contrary to the relatively constant morphology of the PQRST complex in electrocardiography, the waveform morphology of ICG data is far from stationary, which causes difficulties in the accuracy of the automated detection of characteristic ICG points. This study evaluated ICG recordings obtained from 10 volunteers. The results indicate that there are several different waveforms for the ABEXYOZ complex; there are up to five clearly distinct waveforms for the ABEXYOZ complex in addition to those that are typically reported. The differences between waveform types increased the difficulty of detecting ICG points. To accurately detect all ICG points, the ABEXYOZ complex should be analyzed according to the corresponding waveform type.

Place, publisher, year, edition, pages
Walter de Gruyter, 2018
Keywords
bioimpedance, impedance cardiography, dZ/dt signal, ABEXYOZ complex, characteristic points, waveform analysis
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:umu:diva-213080 (URN)10.2478/joeb-2018-0012 (DOI)2-s2.0-85068998347 (Scopus ID)
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-10-13Bibliographically approved
Benouar, S., Hafid, A., Attari, M., Kedir-Talha, M. & Seoane, F. (2018). Where to be from the typical ICG waveform. In: Proceedings of IC2EM-2018: . Paper presented at ICEEM’2018, International Conference on Electronics, Energy and Measurement, Algiers, Algeria, November 27-29, 2018 (pp. 227-232).
Open this publication in new window or tab >>Where to be from the typical ICG waveform
Show others...
2018 (English)In: Proceedings of IC2EM-2018, 2018, p. 227-232Conference paper, Published paper (Refereed)
Abstract [en]

The ICG characteristic points are crucialfor the calculation of hemodynamic parameters. However, in opposite of the relatively constant morphology of the PQRST waves in electrocardiography. The waveform morphology of the ABEXYOZ complex of the ICG is far from stationary, which yields to difficulties in the automated detection of characteristic ICG points. This study evaluates ICG recordings obtained from 4volunteers. The results indicate that there are atypical ABEXYOZ complex in addition to the known typical complex. These atypical waveforms increase the difficulty of ICG signal analysis. To accurately and automatically detect the characteristic ICGpoints, and as a perspective of a future work, the targeted waveform must be known. In apurpose of classifying the atypical waveform into several types of the ABEXYOZ complex. This waveform types should be identified before the analysis of the dZ/dt ICG signal.

Keywords
Bioimpedance, Impedance cardiography, ICG, Z-RPI, Characteristic ICG points, ECG, Biomedical Instrumentation
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:umu:diva-213087 (URN)9789931954804 (ISBN)
Conference
ICEEM’2018, International Conference on Electronics, Energy and Measurement, Algiers, Algeria, November 27-29, 2018
Available from: 2023-08-21 Created: 2023-08-21 Last updated: 2023-08-22Bibliographically approved
Organisations

Search in DiVA

Show all publications