Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005933
A. Khawaja
The ECG analysis system, presented in this paper, provides beat-to-beat localization, classification and measurements in real time. Besides, numbers of rhythm analysis events can be detected instantly by the system, including critical ventricular and atrial arrhythmia events. Using the system will increase the cardiac safety for patients in many cardiac applications, including home-monitoring, ambulatory monitoring and cardiac drug safety. The algorithms used by the system are validated and tested. Furthermore, the system can be deployed on different computing hardware targets and operation systems.
{"title":"A Highly-Reliable Full-Automatic System for Analyzing ECG Waveforms in Real Time Applications","authors":"A. Khawaja","doi":"10.23919/CinC49843.2019.9005933","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005933","url":null,"abstract":"The ECG analysis system, presented in this paper, provides beat-to-beat localization, classification and measurements in real time. Besides, numbers of rhythm analysis events can be detected instantly by the system, including critical ventricular and atrial arrhythmia events. Using the system will increase the cardiac safety for patients in many cardiac applications, including home-monitoring, ambulatory monitoring and cardiac drug safety. The algorithms used by the system are validated and tested. Furthermore, the system can be deployed on different computing hardware targets and operation systems.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"11 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82820695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005819
J. Hagenah, Mohamad Mehdi, F. Ernst
In valve-sparing aortic root reconstruction surgery, estimating the individual healthy shape of the aortic root as it was before pathological deformation is a challenging task. However, exactly this estimation is necessary to develop personalized aortic root prostheses. To support the surgeon in this decision making, we present a novel approach to reconstruct the healthy shape of an aortic root based on ultrasound images of its pathologically dilated state using representation learning.The idea is to identify a suitable representation of healthy and pathological aortic root shapes using a supervised variational autoencoder. Then, an image of the dilated root can be encoded, manipulated in the latent space, i.e. shifted towards the distribution of healthy valves, and a synthetic image of this resulting shape can be generated using the decoder.We evaluate our method on an ex-vivo porcine data set and provide a proof-of-concept of our method in a qualitative and quantitavie way. Our results indicate the great potential of reducing a complex shape deformation task to a simple and intuitive shifting towards a specific class. Hence, our method could play an important role in the shaping of personalized implants and is, due to its data-driven nature, not limited to cardiovascular applications but also for other organs.
{"title":"Generating Healthy Aortic Root Geometries From Ultrasound Images of the Individual Pathological Morphology Using Deep Convolutional Autoencoders","authors":"J. Hagenah, Mohamad Mehdi, F. Ernst","doi":"10.23919/CinC49843.2019.9005819","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005819","url":null,"abstract":"In valve-sparing aortic root reconstruction surgery, estimating the individual healthy shape of the aortic root as it was before pathological deformation is a challenging task. However, exactly this estimation is necessary to develop personalized aortic root prostheses. To support the surgeon in this decision making, we present a novel approach to reconstruct the healthy shape of an aortic root based on ultrasound images of its pathologically dilated state using representation learning.The idea is to identify a suitable representation of healthy and pathological aortic root shapes using a supervised variational autoencoder. Then, an image of the dilated root can be encoded, manipulated in the latent space, i.e. shifted towards the distribution of healthy valves, and a synthetic image of this resulting shape can be generated using the decoder.We evaluate our method on an ex-vivo porcine data set and provide a proof-of-concept of our method in a qualitative and quantitavie way. Our results indicate the great potential of reducing a complex shape deformation task to a simple and intuitive shifting towards a specific class. Hence, our method could play an important role in the shaping of personalized implants and is, due to its data-driven nature, not limited to cardiovascular applications but also for other organs.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"45 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91544427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005802
Linda M. Eerikäinen, A. Bonomi, Fons Schipper, L. Dekker, R. Vullings, H. M. Morree, Ronald M. Aarts
Photoplethysmography (PPG) is an unobtrusive measurement modality recently explored for the detection of atrial fibrillation (AF). When used in wrist-worn applications, PPG-monitoring can be used for long-term monitoring in daily life, which is beneficial when aiming to detect AF. The objective of this study was to investigate whether the performance of an AF detection model trained and tested on short measurements is generalizable to measurements in daily life. PPG, accelerometer, as well as reference ECG data were measured from 32 subjects (13 continuous AF, 19 no AF) in 24-hour monitoring in daily life. An AF detection model combining inter-pulse interval features was trained to classify AF or non-AF. Short measurements were obtained by selecting a 5-minute segment from each 24-hour recording and used for training the model. The accuracy was tested on both 5-minute segments and 24-hour data. Sensitivity, specificity, and accuracy of the model were 98.90%, 99.03%, and 98.98% with 5-minute data and 96.94%, 91.99%, and 93.91% with 24-hour data. False positive detections per patient worsened from being on average none during short recordings to (mean ± sd) 467 ± 328 in daily life. Thus, testing the AF detection models intended for long-term PPG-monitoring is essential with data from daily life in order to obtain a realistic estimate of the accuracy.
{"title":"How Accurately Can We Detect Atrial Fibrillation Using Photoplethysmography Data Measured in Daily Life?","authors":"Linda M. Eerikäinen, A. Bonomi, Fons Schipper, L. Dekker, R. Vullings, H. M. Morree, Ronald M. Aarts","doi":"10.23919/CinC49843.2019.9005802","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005802","url":null,"abstract":"Photoplethysmography (PPG) is an unobtrusive measurement modality recently explored for the detection of atrial fibrillation (AF). When used in wrist-worn applications, PPG-monitoring can be used for long-term monitoring in daily life, which is beneficial when aiming to detect AF. The objective of this study was to investigate whether the performance of an AF detection model trained and tested on short measurements is generalizable to measurements in daily life. PPG, accelerometer, as well as reference ECG data were measured from 32 subjects (13 continuous AF, 19 no AF) in 24-hour monitoring in daily life. An AF detection model combining inter-pulse interval features was trained to classify AF or non-AF. Short measurements were obtained by selecting a 5-minute segment from each 24-hour recording and used for training the model. The accuracy was tested on both 5-minute segments and 24-hour data. Sensitivity, specificity, and accuracy of the model were 98.90%, 99.03%, and 98.98% with 5-minute data and 96.94%, 91.99%, and 93.91% with 24-hour data. False positive detections per patient worsened from being on average none during short recordings to (mean ± sd) 467 ± 328 in daily life. Thus, testing the AF detection models intended for long-term PPG-monitoring is essential with data from daily life in order to obtain a realistic estimate of the accuracy.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"1 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91117386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005822
Mahesh Kumar Mulimani, Jaya Kumar Alageshan, R. Pandit
Defibrillation, the elimination of pathological waves of electrical activation in cardiac tissue, plays an important role in the elimination of life-threatening cardiac arrhythmias like ventricular tachycardia (VT) and ventricular fibrillation (VF). We develop a deep-learning method, which uses a convolution neural network (CNN), to develop a new defibrillation scheme applicable in 2D tisue. We begin by training our CNN with a huge dataset of spiral waves $left( mathcal{S} right)$ and non-spiral waves $left( {mathcal{N}mathcal{S}} right)$ that we obtain from our direct numerical simulations (DNSs) of a variety of mathematical models for the propagation of electrical waves of activation in cardiac tissue. Our trained CNN can distinguish between $mathcal{S}$ and $mathcal{N}mathcal{S}$ patterns; in particular, it also detects a broken spiral wave as $mathcal{S}$. We demonstrate how to use our CNN to develop a heat map, from a broken-spiral-wave image, that yields the approximate locations of these spiral cores. We develop a defibrillation scheme that applies current, with two-dimensional (2D) Gaussian profiles of standard deviation (σ), centred at square lattice sites (NG × NG) imposed on the simulation domain (N ×N); the amplitudes of these Gaussians are taken from the heatmap. We explore the dependence of our Gaussian defibrillation scheme on a noisy image, which closely mimics the noisy optical image data.
{"title":"Detection and Termination of Broken-Spiral-Waves in Mathematical Models for Cardiac Tissue: A Deep-Learning Approach","authors":"Mahesh Kumar Mulimani, Jaya Kumar Alageshan, R. Pandit","doi":"10.23919/CinC49843.2019.9005822","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005822","url":null,"abstract":"Defibrillation, the elimination of pathological waves of electrical activation in cardiac tissue, plays an important role in the elimination of life-threatening cardiac arrhythmias like ventricular tachycardia (VT) and ventricular fibrillation (VF). We develop a deep-learning method, which uses a convolution neural network (CNN), to develop a new defibrillation scheme applicable in 2D tisue. We begin by training our CNN with a huge dataset of spiral waves $left( mathcal{S} right)$ and non-spiral waves $left( {mathcal{N}mathcal{S}} right)$ that we obtain from our direct numerical simulations (DNSs) of a variety of mathematical models for the propagation of electrical waves of activation in cardiac tissue. Our trained CNN can distinguish between $mathcal{S}$ and $mathcal{N}mathcal{S}$ patterns; in particular, it also detects a broken spiral wave as $mathcal{S}$. We demonstrate how to use our CNN to develop a heat map, from a broken-spiral-wave image, that yields the approximate locations of these spiral cores. We develop a defibrillation scheme that applies current, with two-dimensional (2D) Gaussian profiles of standard deviation (σ), centred at square lattice sites (NG × NG) imposed on the simulation domain (N ×N); the amplitudes of these Gaussians are taken from the heatmap. We explore the dependence of our Gaussian defibrillation scheme on a noisy image, which closely mimics the noisy optical image data.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"15 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90470290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005759
F. Plesinger, I. Viscor, P. Nejedly, V. Bulkova, J. Halámek, P. Jurák
Background: Atrial fibrillation (AF) is a dysfunction of heart atriums shown as irregular heart activity leading to a higher risk of heart failure. Since AF may occur episodically, it is usually diagnosed using ECG Holter recordings. However, the presence of other pathologies and noise makes the automated processing of ECG Holter recordings complicated. Here, we present a new feature to distinguish AF from sinus rhythm as well as from other pathologies: Clustered Standard Deviation (CSTD).Method: QRS complexes are extracted from the ECG signal, and inter-beat intervals (RR) are ordered by their length. Then, RR clusters are found and the mean RR value is computed for each RR cluster. CSTD is computed using a formula for standard deviation using cluster-specific mean values instead of a global mean.Results: CSTD was evaluated for 7,254 ECG segments from a private dataset (MDT company, Brno, Czechia), 60 seconds length, 1-lead, 250 Hz sampling frequency. CSTD showed high values for AF while remaining low for other pathologies and sinus rhythm. CSTD between AF and other classes showed AUC 0.95. For comparison, a standard deviation of RR intervals leads to AUC 0.65 due to its sensitivity to other pathologies. Test on public MIT-AFDB dataset shown AUC and AUPRC 0.98 and 0.97, respectively.
{"title":"Clustered Standard Deviation and Its Benefit to Identify Atrial Fibrillation","authors":"F. Plesinger, I. Viscor, P. Nejedly, V. Bulkova, J. Halámek, P. Jurák","doi":"10.23919/CinC49843.2019.9005759","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005759","url":null,"abstract":"Background: Atrial fibrillation (AF) is a dysfunction of heart atriums shown as irregular heart activity leading to a higher risk of heart failure. Since AF may occur episodically, it is usually diagnosed using ECG Holter recordings. However, the presence of other pathologies and noise makes the automated processing of ECG Holter recordings complicated. Here, we present a new feature to distinguish AF from sinus rhythm as well as from other pathologies: Clustered Standard Deviation (CSTD).Method: QRS complexes are extracted from the ECG signal, and inter-beat intervals (RR) are ordered by their length. Then, RR clusters are found and the mean RR value is computed for each RR cluster. CSTD is computed using a formula for standard deviation using cluster-specific mean values instead of a global mean.Results: CSTD was evaluated for 7,254 ECG segments from a private dataset (MDT company, Brno, Czechia), 60 seconds length, 1-lead, 250 Hz sampling frequency. CSTD showed high values for AF while remaining low for other pathologies and sinus rhythm. CSTD between AF and other classes showed AUC 0.95. For comparison, a standard deviation of RR intervals leads to AUC 0.65 due to its sensitivity to other pathologies. Test on public MIT-AFDB dataset shown AUC and AUPRC 0.98 and 0.97, respectively.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"17 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84764915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005940
Soodabeh Sarafrazi, R. Choudhari, Chiral Mehta, H. Mehta, Omid K. Japalaghi, Jie Han, Kinjal A Mehta, H. Han, P. Francis-Lyon
On a yearly basis, sepsis costs US hospitals more than any other health condition. A majority of patients who suffer from sepsis are not diagnosed at the time of admission. Early detection and antibiotic treatment of sepsis are vital to improve outcomes for these patients, as each hour of delayed treatment is associated with increased mortality. In this study our goal is to predict sepsis 12 hours before its diagnosis using vitals and blood tests routinely taken in the ICU. We have investigated the performance of several machine learning algorithms including XGBoost, CNN, CNN-LSTM and CNN-XGBoost. Contrary to our expectations, XGBoost outperforms all of the sequential models and yields the best hour-by-hour prediction, perhaps due to the way we imputed missing values, losing signal that relates to the time-series nature of the EHR data. We added feature engineering to detect change points in tests and vitals, resulting in 5% improvement in XGBoost. Our team, USF-Sepsis-Phys, achieved a utility score of 0.22 (untuned threshold) and an average of the three reported AUCs (test sets A, B, C) of 0.82. As expected with this AUC, the same model with tuned threshold (not run in the PhysioNet challenge) performed significantly better, as evaluated with 3-fold cross-validation of the entire PhyisoNet training set.
{"title":"Cracking the “Sepsis” Code: Assessing Time Series Nature of EHR Data, and Using Deep Learning for Early Sepsis Prediction","authors":"Soodabeh Sarafrazi, R. Choudhari, Chiral Mehta, H. Mehta, Omid K. Japalaghi, Jie Han, Kinjal A Mehta, H. Han, P. Francis-Lyon","doi":"10.23919/CinC49843.2019.9005940","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005940","url":null,"abstract":"On a yearly basis, sepsis costs US hospitals more than any other health condition. A majority of patients who suffer from sepsis are not diagnosed at the time of admission. Early detection and antibiotic treatment of sepsis are vital to improve outcomes for these patients, as each hour of delayed treatment is associated with increased mortality. In this study our goal is to predict sepsis 12 hours before its diagnosis using vitals and blood tests routinely taken in the ICU. We have investigated the performance of several machine learning algorithms including XGBoost, CNN, CNN-LSTM and CNN-XGBoost. Contrary to our expectations, XGBoost outperforms all of the sequential models and yields the best hour-by-hour prediction, perhaps due to the way we imputed missing values, losing signal that relates to the time-series nature of the EHR data. We added feature engineering to detect change points in tests and vitals, resulting in 5% improvement in XGBoost. Our team, USF-Sepsis-Phys, achieved a utility score of 0.22 (untuned threshold) and an average of the three reported AUCs (test sets A, B, C) of 0.82. As expected with this AUC, the same model with tuned threshold (not run in the PhysioNet challenge) performed significantly better, as evaluated with 3-fold cross-validation of the entire PhyisoNet training set.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"42 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85151091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005889
M. Potse
Previous work has shown that fibrillation can be induced by rapid pacing in a model of the human atria without fibrosis or repolarization heterogeneity. The purpose of this study was to investigate how sensitive this type of arrhythmia induction is to model parameters.Simulations were performed with a monodomain reaction-diffusion model with Courtemanche dynamics on a volumetric atrial mesh with all the major bundle structures and layered fiber orientation. The ionic model parameters were modified to represent electrically remodeled atria, uniformly. The model was stimulated with decreasing cycle length to drive the atria to maximum rate, and simulated over 10 seconds. This was tried with 10 different pacing locations and 46 different values of the conductivity, gCaL, of the L-type calcium current.For gCaL values up to 130% of the initial value, on average 4 out of 10 pacing sites induced AF. However, the positive sites were different for each tested gCaL level, even at 1% increments. Beyond 130%, the AF induction rate decreased. Every pacing site yielded AF for a subset of parameter values, but some sites more frequently.In conclusion, AF induction is highly sensitive to parameter values. The global decrease in induction seen for large gCaL may be due to the increased wavelength.
{"title":"Inducibility of Atrial Fibrillation Depends Chaotically on Ionic Model Parameters","authors":"M. Potse","doi":"10.23919/CinC49843.2019.9005889","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005889","url":null,"abstract":"Previous work has shown that fibrillation can be induced by rapid pacing in a model of the human atria without fibrosis or repolarization heterogeneity. The purpose of this study was to investigate how sensitive this type of arrhythmia induction is to model parameters.Simulations were performed with a monodomain reaction-diffusion model with Courtemanche dynamics on a volumetric atrial mesh with all the major bundle structures and layered fiber orientation. The ionic model parameters were modified to represent electrically remodeled atria, uniformly. The model was stimulated with decreasing cycle length to drive the atria to maximum rate, and simulated over 10 seconds. This was tried with 10 different pacing locations and 46 different values of the conductivity, gCaL, of the L-type calcium current.For gCaL values up to 130% of the initial value, on average 4 out of 10 pacing sites induced AF. However, the positive sites were different for each tested gCaL level, even at 1% increments. Beyond 130%, the AF induction rate decreased. Every pacing site yielded AF for a subset of parameter values, but some sites more frequently.In conclusion, AF induction is highly sensitive to parameter values. The global decrease in induction seen for large gCaL may be due to the increased wavelength.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"17 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83975362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005816
Nolwenn Tan, L. Bear, M. Potse, Stéphane Puyo, M. Meo, R. Dubois
To test the performance of signal averaging on body surface electrocardiograms (SAECG), a comparative analysis of four sources of perturbation, 1) uncorrelated noise, 2) beat alignment, 3) physiological variability and 4) respiratory movement was performed. The first two cases were assessed using a computer model of a ventricular beat. The other two cases were tested using high resolution body surface signals recorded from a torso tank (N=2) and patient data (N=4) respectively. In the first case, SAECG successfully removed a high level of noise made up of white Gaussian noise (WGN) with σ = 10 µV and 50 Hz noise with a signal to noise ratio (SNR) of 9 dB since the root mean square error of the noise (RMSEnoise) was 0.65 ± 0.01 µV and 1.30 ± 0.01 µV, respectively. The RMSE of the averaged QRS (RMSESAQRS) was slightly changed by physiological variability (RMSESAQRS =4.18 ± 1.38 µV) when comparing the SAQRS resulting from the average of 100 different beats taken from the same recording. While SAQRS are distorted by respiration artefacts, the beats selected during the exhalation phase produced the least distortion to the SAQRS with a RMSESAQRS = 16.28 ± 12.58 µV. To conclude, SAECG can efficiently de-noise signals in presence of uncorrelated noise without distorting the SAQRS. However, respiration motion introduces amplitude shift between SAQRS.
{"title":"Analysis of Signal-Averaged Electrocardiogram Performance for Body Surface Recordings","authors":"Nolwenn Tan, L. Bear, M. Potse, Stéphane Puyo, M. Meo, R. Dubois","doi":"10.23919/CinC49843.2019.9005816","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005816","url":null,"abstract":"To test the performance of signal averaging on body surface electrocardiograms (SAECG), a comparative analysis of four sources of perturbation, 1) uncorrelated noise, 2) beat alignment, 3) physiological variability and 4) respiratory movement was performed. The first two cases were assessed using a computer model of a ventricular beat. The other two cases were tested using high resolution body surface signals recorded from a torso tank (N=2) and patient data (N=4) respectively. In the first case, SAECG successfully removed a high level of noise made up of white Gaussian noise (WGN) with σ = 10 µV and 50 Hz noise with a signal to noise ratio (SNR) of 9 dB since the root mean square error of the noise (RMSEnoise) was 0.65 ± 0.01 µV and 1.30 ± 0.01 µV, respectively. The RMSE of the averaged QRS (RMSESAQRS) was slightly changed by physiological variability (RMSESAQRS =4.18 ± 1.38 µV) when comparing the SAQRS resulting from the average of 100 different beats taken from the same recording. While SAQRS are distorted by respiration artefacts, the beats selected during the exhalation phase produced the least distortion to the SAQRS with a RMSESAQRS = 16.28 ± 12.58 µV. To conclude, SAECG can efficiently de-noise signals in presence of uncorrelated noise without distorting the SAQRS. However, respiration motion introduces amplitude shift between SAQRS.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"2 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88914172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005771
L. Cavinato, Annie Cardinaux, Wasifa Jamal, M. Kjelgaard, P. Sinha, R. Barbieri
Defined as the ability of the nervous systems to reduce their response over repeated stimulation, habituation inflects its parameters in terms of frequency, intensity, recovery and anticipation of responses. Although its concepts have developed from the study of the Central Nervous System (CNS) in processing stimuli at the cortical level, we aim at defining habituation from an autonomic point of view, via heart rate and heart rate variability assessments. To this extent, by using a point-process approach, we devise a novel Autonomic Reactivity Function (ARF) describing the time-varying Autonomic Nervous System (ANS) response in terms of intensity and anticipation, whose reduction (or increment) over repeated stimuli can be ascribed to habituating (or sensitizating) patterns. We tested the mathematical formalization of such metrics in both neurotypical subjects and children with autism spectrum disorder. By eliciting autonomic responses via multisensory stimulation, we collected electrocardiography (ECG) signals, pulled ARFs out from them and performed the Persons coefficient between autonomic habituation metrics and participants sensory profiles and disorder severeness. Results show a relevant positive correlation with Short Sensory Profile (SSP-2) questionnaire (60%) and with Autism Diagnostic Observation Schedule (ADOS-2) questionnaire (76%).
{"title":"Assessment of the Autonomic Response to Sensory Stimulation in Autism Spectrum Disorder","authors":"L. Cavinato, Annie Cardinaux, Wasifa Jamal, M. Kjelgaard, P. Sinha, R. Barbieri","doi":"10.23919/CinC49843.2019.9005771","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005771","url":null,"abstract":"Defined as the ability of the nervous systems to reduce their response over repeated stimulation, habituation inflects its parameters in terms of frequency, intensity, recovery and anticipation of responses. Although its concepts have developed from the study of the Central Nervous System (CNS) in processing stimuli at the cortical level, we aim at defining habituation from an autonomic point of view, via heart rate and heart rate variability assessments. To this extent, by using a point-process approach, we devise a novel Autonomic Reactivity Function (ARF) describing the time-varying Autonomic Nervous System (ANS) response in terms of intensity and anticipation, whose reduction (or increment) over repeated stimuli can be ascribed to habituating (or sensitizating) patterns. We tested the mathematical formalization of such metrics in both neurotypical subjects and children with autism spectrum disorder. By eliciting autonomic responses via multisensory stimulation, we collected electrocardiography (ECG) signals, pulled ARFs out from them and performed the Persons coefficient between autonomic habituation metrics and participants sensory profiles and disorder severeness. Results show a relevant positive correlation with Short Sensory Profile (SSP-2) questionnaire (60%) and with Autism Diagnostic Observation Schedule (ADOS-2) questionnaire (76%).","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"56 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87326821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005848
P. Nabeel, V. R. Kiran, J. Joseph, M. Sivaprakasam
Background and Aim: Given the knowledge of the non-invasive assessment of local pulse wave velocity (PWV) for cardiovascular risk stratification, it is apparent that it is necessary to develop a practically feasible solution to measure and trace instantaneous variations in local PWV (incremental local PWV) from the target arteries.Methods: From the arterial blood pulse propagation characteristics, wave nature of the transmural pressure, and the distending vessel wall geometry, a mathematical model was developed to evaluate incremental local PWV using arterial diameter waveform. Its practical feasibility and the measurement accuracy were demonstrated in-vivo using a custom image-free ultrasound device, with the Bramwell-Hill method as the reference.Results: The proposed technique and developed device reliably captured incremental local PWV from the carotid artery. The locus of instantaneous variations in carotid local PWV obtained using the developed model traced the reference values, with a root-mean-square-error lesser than 0.05 m/s. Study results further established the practical feasibility and accuracy of this novel approach.Conclusion: The theoretical basis and measurement method of this work is a solution for non-invasive, real-time assessment of incremental local PWV and its locus.
{"title":"Determination of Incremental Local Pulse Wave Velocity Using Arterial Diameter Waveform: Mathematical Modeling and Practical Implementation","authors":"P. Nabeel, V. R. Kiran, J. Joseph, M. Sivaprakasam","doi":"10.23919/CinC49843.2019.9005848","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005848","url":null,"abstract":"Background and Aim: Given the knowledge of the non-invasive assessment of local pulse wave velocity (PWV) for cardiovascular risk stratification, it is apparent that it is necessary to develop a practically feasible solution to measure and trace instantaneous variations in local PWV (incremental local PWV) from the target arteries.Methods: From the arterial blood pulse propagation characteristics, wave nature of the transmural pressure, and the distending vessel wall geometry, a mathematical model was developed to evaluate incremental local PWV using arterial diameter waveform. Its practical feasibility and the measurement accuracy were demonstrated in-vivo using a custom image-free ultrasound device, with the Bramwell-Hill method as the reference.Results: The proposed technique and developed device reliably captured incremental local PWV from the carotid artery. The locus of instantaneous variations in carotid local PWV obtained using the developed model traced the reference values, with a root-mean-square-error lesser than 0.05 m/s. Study results further established the practical feasibility and accuracy of this novel approach.Conclusion: The theoretical basis and measurement method of this work is a solution for non-invasive, real-time assessment of incremental local PWV and its locus.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"5 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88405096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：