Pub Date : 2021-09-13DOI: 10.23919/cinc53138.2021.9662893
Jaroslav Vondrák, M. Cerný, F. Jurek
Electrocardiogram (ECG) is currently the most widely used in clinical practice for the diagnosis of heart disease. However, there is a vectorcardiography (VCG) method that in certain cases can detect some pathologies with higher accuracy than a 12 lead ECG. In this work, we present a new method of QRS complex detection based on the octant theory introduced by Laufberger. The presented algorithm is based on the principle of numerical sequence analysis. This search algorithm consists of three main parts: Window search in number series, Modification of window search in number series due to a longer search window, and modification of number series due to a shorter search window. These individual parts form one whole of the whole algorithm. The accuracy of the presented algorithm was tested on 80 physiological records from the PTB database by calculating accuracy, sensitivity and specificity. The percentage accuracy for healthy records was 98.28% sensitivity 98.2% and specificity 98.1%. This algorithm has low computational complexity and can be a useful tool to simplify the work of cardiologists in the analysis of long records.
{"title":"A Novel Method for the Detection of QRS Complex Using Vectorcardiographic Octants","authors":"Jaroslav Vondrák, M. Cerný, F. Jurek","doi":"10.23919/cinc53138.2021.9662893","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662893","url":null,"abstract":"Electrocardiogram (ECG) is currently the most widely used in clinical practice for the diagnosis of heart disease. However, there is a vectorcardiography (VCG) method that in certain cases can detect some pathologies with higher accuracy than a 12 lead ECG. In this work, we present a new method of QRS complex detection based on the octant theory introduced by Laufberger. The presented algorithm is based on the principle of numerical sequence analysis. This search algorithm consists of three main parts: Window search in number series, Modification of window search in number series due to a longer search window, and modification of number series due to a shorter search window. These individual parts form one whole of the whole algorithm. The accuracy of the presented algorithm was tested on 80 physiological records from the PTB database by calculating accuracy, sensitivity and specificity. The percentage accuracy for healthy records was 98.28% sensitivity 98.2% and specificity 98.1%. This algorithm has low computational complexity and can be a useful tool to simplify the work of cardiologists in the analysis of long records.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128672447","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662859
E. M. Polo, Maximiliano Mollura, M. Zanet, Marta Lenatti, A. Paglialonga, Riccardo Barbieri
Emotions play an important role in our everyday life, influencing our decision-making process, and also affecting our physiology. Several studies in literature have proposed successful classification models for emotion recognition combining multimodal physiological measures without dwelling on the physiological significance of the measures. Our study aims at finding cardiovascular indices related to the autonomic nervous system that can explain how autonomic control of the heart responds with respect to specific emotions: happiness, fear, relaxation and boredom. Pulse arrival time and pulse pressure measurements have been shown to be significantly separating the 4 emotions, especially along the arousal dimension as expected from previous findings. Importantly, these blood pressure related indices also yielded relevant insights into characterizing the valence dimension when looking at high and low arousal subsets. In addition, these measures were found to be correlated with classical autonomic indices and explanatory in the cardiovascular and autonomic changes elicited by different emotions. Autonomic indices were then used to train a basic support vector machine model obtaining four-class test accuracy in discriminating happiness, relaxation, boredom and fear equal to 44%, 67%, 55%, 44% respectively.
{"title":"Analysis of the Effect of Emotion Elicitation on the Cardiovascular System","authors":"E. M. Polo, Maximiliano Mollura, M. Zanet, Marta Lenatti, A. Paglialonga, Riccardo Barbieri","doi":"10.23919/cinc53138.2021.9662859","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662859","url":null,"abstract":"Emotions play an important role in our everyday life, influencing our decision-making process, and also affecting our physiology. Several studies in literature have proposed successful classification models for emotion recognition combining multimodal physiological measures without dwelling on the physiological significance of the measures. Our study aims at finding cardiovascular indices related to the autonomic nervous system that can explain how autonomic control of the heart responds with respect to specific emotions: happiness, fear, relaxation and boredom. Pulse arrival time and pulse pressure measurements have been shown to be significantly separating the 4 emotions, especially along the arousal dimension as expected from previous findings. Importantly, these blood pressure related indices also yielded relevant insights into characterizing the valence dimension when looking at high and low arousal subsets. In addition, these measures were found to be correlated with classical autonomic indices and explanatory in the cardiovascular and autonomic changes elicited by different emotions. Autonomic indices were then used to train a basic support vector machine model obtaining four-class test accuracy in discriminating happiness, relaxation, boredom and fear equal to 44%, 67%, 55%, 44% respectively.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128978395","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662853
A. Verkerk, R. Wilders
We recently reported patch clamp data on the voltage dependence of HCN4 channels expressed in human cardiomyocyte progenitor cells. Their half-activation voltage was 15 mV less negative than previously observed for the HCN4 encoded hyperpolarization-activated funny current’ $(I_{f})$ in isolated human sinus node cells. The time constant of (de)activation vs. voltage relationship showed a similar less negative voltage dependence as well as a 38% higher peak. We assessed the functional effects of these differences in $I_{f}$ kinetics in the Fabbri-Severi model of a single human sinus node pacemaker cell. The $+15 mV$ shift in half-activation voltage per se resulted in a substantial increase in $I_{f}$, carrying 85 vs. 59% of the net diastolic depolarizing charge, and a 14% shortening of the cycle length from 813 to 699 ms. This effect was counteracted by the time constant vs. voltage relationship, which caused a slower activation of $I_{f}$ in the diastolic membrane potential range. The resulting net effect was a 5.4% shortening of the cycle length from 813 to 770 ms, with $I_{f}$ carrying 59% of the net diastolic charge, and limited effects on the autonomic modulation of pacing rate by isoprenaline and acetylcholine. We conclude that the absolute value of the half-activation voltage of $I_{f}$ may be less indicative of the functional role of $I_{f}$ than commonly assumed.
{"title":"Functional Role of the HCN4 Encoded ‘Funny Current’ in Human Sinus Node Pacemaker Cells","authors":"A. Verkerk, R. Wilders","doi":"10.23919/cinc53138.2021.9662853","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662853","url":null,"abstract":"We recently reported patch clamp data on the voltage dependence of HCN4 channels expressed in human cardiomyocyte progenitor cells. Their half-activation voltage was 15 mV less negative than previously observed for the HCN4 encoded hyperpolarization-activated funny current’ $(I_{f})$ in isolated human sinus node cells. The time constant of (de)activation vs. voltage relationship showed a similar less negative voltage dependence as well as a 38% higher peak. We assessed the functional effects of these differences in $I_{f}$ kinetics in the Fabbri-Severi model of a single human sinus node pacemaker cell. The $+15 mV$ shift in half-activation voltage per se resulted in a substantial increase in $I_{f}$, carrying 85 vs. 59% of the net diastolic depolarizing charge, and a 14% shortening of the cycle length from 813 to 699 ms. This effect was counteracted by the time constant vs. voltage relationship, which caused a slower activation of $I_{f}$ in the diastolic membrane potential range. The resulting net effect was a 5.4% shortening of the cycle length from 813 to 770 ms, with $I_{f}$ carrying 59% of the net diastolic charge, and limited effects on the autonomic modulation of pacing rate by isoprenaline and acetylcholine. We conclude that the absolute value of the half-activation voltage of $I_{f}$ may be less indicative of the functional role of $I_{f}$ than commonly assumed.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126660652","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662705
K. Gillette, M. Gsell, A. Prassl, G. Plank
Introduction: Multiple clinical studies have aimed to assess the influence of electrode placement on 12 lead electrocardiogram (ECG) morphology. However, a study has not yet been conducted in silico. We therefore aim to systemically investigate the influence of electrode positioning on the morphology of the 12 lead ECG using a cardiac model of electrophysiology under both healthy sinus rhythm and right bundle branch block (RBBB). Methods: A biophysically-detailed model of ventricular electrophysiology of a single subject was used to model body surface potential maps during healthy sinus rhythm and RBBB. A systematic automatic perturbation of all electrodes from the original subject configuration was performed to replicate clinical variation. For each variation in electrode placement, the 12 lead ECG was computed under both conditions. Quantitative differences were assessed using a time-averaged normalized $L_{2}$ norm. Results: The precordial leads that lie in closer proximity to the heart, primarily V2 and V3, experienced the largest morphological changes from vertical electrode movement. Morphological variation in the augmented Goldberger and Einthoven leads resulted predominantly from LA electrode placement. The possibility of a false diagnosis of RBBB during sinus rhythm due to improper electrode placement was also demonstrated.
{"title":"Influence of Electrode Placement on the Morphology of In Silico 12 Lead Electrocardiograms","authors":"K. Gillette, M. Gsell, A. Prassl, G. Plank","doi":"10.23919/cinc53138.2021.9662705","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662705","url":null,"abstract":"Introduction: Multiple clinical studies have aimed to assess the influence of electrode placement on 12 lead electrocardiogram (ECG) morphology. However, a study has not yet been conducted in silico. We therefore aim to systemically investigate the influence of electrode positioning on the morphology of the 12 lead ECG using a cardiac model of electrophysiology under both healthy sinus rhythm and right bundle branch block (RBBB). Methods: A biophysically-detailed model of ventricular electrophysiology of a single subject was used to model body surface potential maps during healthy sinus rhythm and RBBB. A systematic automatic perturbation of all electrodes from the original subject configuration was performed to replicate clinical variation. For each variation in electrode placement, the 12 lead ECG was computed under both conditions. Quantitative differences were assessed using a time-averaged normalized $L_{2}$ norm. Results: The precordial leads that lie in closer proximity to the heart, primarily V2 and V3, experienced the largest morphological changes from vertical electrode movement. Morphological variation in the augmented Goldberger and Einthoven leads resulted predominantly from LA electrode placement. The possibility of a false diagnosis of RBBB during sinus rhythm due to improper electrode placement was also demonstrated.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123957575","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662830
Philipp Sodmann, M. Vollmer, L. Kaderali
As part of the Physionet 2021 Challenge, “Will Two Do? Varying Dimensions in Electrocardiography: The PhysioNet/Computing in Cardiology Challenge 2021”, we have developed a neural network to classify pathologies and changes in the ECG. Our team HeartlyAI has developed a novel multitask learning based network that combines classification with segmentation and extrasystole detection. To obtain segmentation annotations, we developed an annotation tool in Angular and have manually annotated 1,789 ECGs from all challenge data sources for a gold standard of P wave, QRS, and T wave segments. Each extrasystole was annotated as supraventricular or ventricular. In the first step of our classification workflow, the ECG is segmented using a U-Net. This segmentation is used to calculate within-net features such as the PQ, QTc time, and Q-Q interval. The bottleneck layer of the U-Net is used along with the computed features as an embedding for the classification. We have used the recent Perceiver architecture to perform the classification of the ECG. Our classifiers received scores of 0.40, 0.31, 0.34, 0.34, and 0.25 (ranked 18th, 24th, 23rd, 23rd, and27th) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden validation set with the Challenge evaluation metric.
{"title":"Segment, Perceive and Classify - Multitask Learning of the Electrocardiogram in a Single Neural Network","authors":"Philipp Sodmann, M. Vollmer, L. Kaderali","doi":"10.23919/cinc53138.2021.9662830","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662830","url":null,"abstract":"As part of the Physionet 2021 Challenge, “Will Two Do? Varying Dimensions in Electrocardiography: The PhysioNet/Computing in Cardiology Challenge 2021”, we have developed a neural network to classify pathologies and changes in the ECG. Our team HeartlyAI has developed a novel multitask learning based network that combines classification with segmentation and extrasystole detection. To obtain segmentation annotations, we developed an annotation tool in Angular and have manually annotated 1,789 ECGs from all challenge data sources for a gold standard of P wave, QRS, and T wave segments. Each extrasystole was annotated as supraventricular or ventricular. In the first step of our classification workflow, the ECG is segmented using a U-Net. This segmentation is used to calculate within-net features such as the PQ, QTc time, and Q-Q interval. The bottleneck layer of the U-Net is used along with the computed features as an embedding for the classification. We have used the recent Perceiver architecture to perform the classification of the ECG. Our classifiers received scores of 0.40, 0.31, 0.34, 0.34, and 0.25 (ranked 18th, 24th, 23rd, 23rd, and27th) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden validation set with the Challenge evaluation metric.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124163346","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662735
F. M. Dias, N. Samesima, A. Ribeiro, R. A. Moreno, C. Pastore, J. Krieger, M. A. Gutierrez
Atrial fibrillation (AF) is a common arrhythmia (0.5% worldwide prevalence) associated with an increased risk of various cardiovascular disorders, including stroke. Automated routine AF detection by Electrocardiogram (ECG) is based on the analysis of one-dimensional ECG signals and requires dedicated software for each type of device, limiting its wide use, especially with the rapid incorporation of telemedicine into the healthcare system. Here, we implement a machine learning method for AF classification using the region of interest (ROI) corresponding to the long DII lead automatically extracted from DI-COM 12-lead ECG images. We observed 94.3%, 98.9%, 99.1%, and 92.2% for sensitivity, specificity, AUC, and F1 score, respectively. These results indicate that the proposed methodology performs similar to one-dimensional ECG signals as input, but does not require a dedicated software facilitating the integration into clinical practice, as ECGs are typically stored in PACS as 2D images.
{"title":"2D Image-Based Atrial Fibrillation Classification","authors":"F. M. Dias, N. Samesima, A. Ribeiro, R. A. Moreno, C. Pastore, J. Krieger, M. A. Gutierrez","doi":"10.23919/cinc53138.2021.9662735","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662735","url":null,"abstract":"Atrial fibrillation (AF) is a common arrhythmia (0.5% worldwide prevalence) associated with an increased risk of various cardiovascular disorders, including stroke. Automated routine AF detection by Electrocardiogram (ECG) is based on the analysis of one-dimensional ECG signals and requires dedicated software for each type of device, limiting its wide use, especially with the rapid incorporation of telemedicine into the healthcare system. Here, we implement a machine learning method for AF classification using the region of interest (ROI) corresponding to the long DII lead automatically extracted from DI-COM 12-lead ECG images. We observed 94.3%, 98.9%, 99.1%, and 92.2% for sensitivity, specificity, AUC, and F1 score, respectively. These results indicate that the proposed methodology performs similar to one-dimensional ECG signals as input, but does not require a dedicated software facilitating the integration into clinical practice, as ECGs are typically stored in PACS as 2D images.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128191904","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662701
Diego García, S. Kontaxis, A. Hernández-Vicente, D. Hernando, Javier Milagro, E. Pueyo, N. Garatachea, R. Bailón, J. Lázaro
The purpose of this work is to study the feasibility of estimating the first and second ventilatory thresholds (VT1 and VT2, respectively) by using electrocardiogram (ECG)-derived respiratory rate during exercise testing. The ECGs of 25 healthy volunteers during cycle ergometer exercise test with increasing workload were analyzed. Time-varying respiratory rate was estimated from an ECG-derived respiration signal obtained from QRS slopes' range method. VT1 and VT2 were estimated as the points of maximum change in respiratory rate slope using polynomial spline smoothing. Reference VT1 and VT2 were determined from the ventilatory equivalents of $O_{2}$ and $CO_{2}$. Estimation errors (in watts) of -13.96 (54.84) W for VT1 and -8.06 (39.63) Wfor VT2 (median (interquartile range)) were obtained, suggesting that ventilatory thresholds can be estimated from solely the ECG signal.
{"title":"Ventilatory Thresholds Estimation Based on ECG-derived Respiratory Rate","authors":"Diego García, S. Kontaxis, A. Hernández-Vicente, D. Hernando, Javier Milagro, E. Pueyo, N. Garatachea, R. Bailón, J. Lázaro","doi":"10.23919/cinc53138.2021.9662701","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662701","url":null,"abstract":"The purpose of this work is to study the feasibility of estimating the first and second ventilatory thresholds (VT1 and VT2, respectively) by using electrocardiogram (ECG)-derived respiratory rate during exercise testing. The ECGs of 25 healthy volunteers during cycle ergometer exercise test with increasing workload were analyzed. Time-varying respiratory rate was estimated from an ECG-derived respiration signal obtained from QRS slopes' range method. VT1 and VT2 were estimated as the points of maximum change in respiratory rate slope using polynomial spline smoothing. Reference VT1 and VT2 were determined from the ventilatory equivalents of $O_{2}$ and $CO_{2}$. Estimation errors (in watts) of -13.96 (54.84) W for VT1 and -8.06 (39.63) Wfor VT2 (median (interquartile range)) were obtained, suggesting that ventilatory thresholds can be estimated from solely the ECG signal.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115946227","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662652
A. Ahola, J. Hyttinen
Stem cell derived cardiomyocytes provide a platform for a variety of studies. The typically performed electrophysiological measurements do not describe the primary function of these cells, contraction and its biomechanics. Video microscopy-based analysis of motion has become a feasible option for these studies. Here, we demonstrate methods for spatiotemporal quantification of stem cell derived cardiomyocytes, implemented in an in-house developed MATLAB-based software tool. The tool is capable of characterizing cardiomyocyte contraction with minimal user bias. The results show that automatic segmentation using a power spectral density -based measure enables segmentation based on contractile function. Further, based on segmented boundaries, we introduce automatically calculated parameters for quantification the contractile function and its propagation through the cell culture based on timings of different contraction phases. The methods presented here form a basis for quantifying and understanding the contraction dynamics and the propagation of contraction in cultures involving cardiomyocytes.
{"title":"Spatiotemporal Quantification of In Vitro Cardiomyocyte Contraction Dynamics Using Video Microscopy-based Software Tool","authors":"A. Ahola, J. Hyttinen","doi":"10.23919/cinc53138.2021.9662652","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662652","url":null,"abstract":"Stem cell derived cardiomyocytes provide a platform for a variety of studies. The typically performed electrophysiological measurements do not describe the primary function of these cells, contraction and its biomechanics. Video microscopy-based analysis of motion has become a feasible option for these studies. Here, we demonstrate methods for spatiotemporal quantification of stem cell derived cardiomyocytes, implemented in an in-house developed MATLAB-based software tool. The tool is capable of characterizing cardiomyocyte contraction with minimal user bias. The results show that automatic segmentation using a power spectral density -based measure enables segmentation based on contractile function. Further, based on segmented boundaries, we introduce automatically calculated parameters for quantification the contractile function and its propagation through the cell culture based on timings of different contraction phases. The methods presented here form a basis for quantifying and understanding the contraction dynamics and the propagation of contraction in cultures involving cardiomyocytes.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134064310","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662690
R. Fadil, A. Huether, Robert Brunnemer, A. Blaber, J. Lou, K. Tavakolian
The purpose of this study is to investigate if impairments in leg muscle contractions affect blood pressure (BP) regulation in patients with Parkinson's disease (PD). Simultaneous BP, electrocardiogram, and bilateral electromyogram (EMG) of the tibialis anterior, lateral and medial gastrocnemius, and soleus muscles were recorded from 16 patients with PD and 12 healthy controls in supine (5 minutes), head-up tilt test (15 minutes), and standing positions (5 minutes). Convergent Cross Mapping was used to examine the causal relationship of the muscle pump baroreflex $(SBPrightarrow EMG_{imp})$ and the effect of muscle activity on systolic blood pressure $(EMG_{imp}rightarrow SBP)$. Preliminary results showed that PD participants have less effective lower leg skeletal muscle pump compared to the control group while no difference was found in the muscle pump baroreflex. Muscle pump causality was lower for all muscles in PD patients compared to the control group. Our data suggest that PD patients show a reduced causal effect of skeletal muscle pump on blood pressure. The obtained results also highlight the impairment of the ability of muscle pump to effectively control blood pressure in PD patients. The findings of this study can assist in the development of an effective system for monitoring orthostatic tolerance via muscle pump to prevent syncope and falls in PD.
{"title":"Skeletal Muscle Pump Impairment in Parkinson's Disease: Preliminary Results","authors":"R. Fadil, A. Huether, Robert Brunnemer, A. Blaber, J. Lou, K. Tavakolian","doi":"10.23919/cinc53138.2021.9662690","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662690","url":null,"abstract":"The purpose of this study is to investigate if impairments in leg muscle contractions affect blood pressure (BP) regulation in patients with Parkinson's disease (PD). Simultaneous BP, electrocardiogram, and bilateral electromyogram (EMG) of the tibialis anterior, lateral and medial gastrocnemius, and soleus muscles were recorded from 16 patients with PD and 12 healthy controls in supine (5 minutes), head-up tilt test (15 minutes), and standing positions (5 minutes). Convergent Cross Mapping was used to examine the causal relationship of the muscle pump baroreflex $(SBPrightarrow EMG_{imp})$ and the effect of muscle activity on systolic blood pressure $(EMG_{imp}rightarrow SBP)$. Preliminary results showed that PD participants have less effective lower leg skeletal muscle pump compared to the control group while no difference was found in the muscle pump baroreflex. Muscle pump causality was lower for all muscles in PD patients compared to the control group. Our data suggest that PD patients show a reduced causal effect of skeletal muscle pump on blood pressure. The obtained results also highlight the impairment of the ability of muscle pump to effectively control blood pressure in PD patients. The findings of this study can assist in the development of an effective system for monitoring orthostatic tolerance via muscle pump to prevent syncope and falls in PD.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"49 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115524704","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 : 2021-09-13DOI: 10.23919/cinc53138.2021.9662778
I. Isasi, E. Alonso, U. Irusta, E. Aramendi, M. Zabihi, Ali Bahrami Rad, T. Eftestøl, J. Kramer-Johansen, L. Wik
Resuscitation guidelines mandate pausing chest compressions (CCs) during cardiopulmonary resuscitation (CPR) to check for the presence of pulse. However, interrupting CPR during a pulseless rhythm adversely affects survival. The aim of this study was to develop a pulse detection algorithm during CPR using the ECG and thoracic impedance (TI) signals. Data were collected from 116 out-of-hospital cardiac arrest (OHCA) patients during CCs and pulse/no-pulse annotations were carried out in artefact-free intervals by clinicians. CC artefacts were first removed from ECG and TI using recursive least-squares (RLS) filters. The impedance circulation component (ICC) was then derived from the filtered TI using a RLS-based adaptive scheme. The wavelet decomposition of the ECG and ICC was carried out to obtain the different subband components and the reconstruced ECG and ICC. A total of 124 discrimination features were extracted from those signals andfed into a random forest (RF) classifier that made the pulse/no-pulse decision. A repeated cross-validation procedure was used for feature selection, parameter tuning, and model assessment. Pulse/no-pulse diagnoses obtained through the RF were compared with the annotations to obtain the sensitivity (SE), specificity (SP) and balanced accuracy (BAC) of the method. The results obtained were: 76.2% (SE), 66.2% (SP) and 71.2% (BAC).
{"title":"A Machine Learning-Based Pulse Detection Algorithm for Use During Cardiopulmonary Resuscitation","authors":"I. Isasi, E. Alonso, U. Irusta, E. Aramendi, M. Zabihi, Ali Bahrami Rad, T. Eftestøl, J. Kramer-Johansen, L. Wik","doi":"10.23919/cinc53138.2021.9662778","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662778","url":null,"abstract":"Resuscitation guidelines mandate pausing chest compressions (CCs) during cardiopulmonary resuscitation (CPR) to check for the presence of pulse. However, interrupting CPR during a pulseless rhythm adversely affects survival. The aim of this study was to develop a pulse detection algorithm during CPR using the ECG and thoracic impedance (TI) signals. Data were collected from 116 out-of-hospital cardiac arrest (OHCA) patients during CCs and pulse/no-pulse annotations were carried out in artefact-free intervals by clinicians. CC artefacts were first removed from ECG and TI using recursive least-squares (RLS) filters. The impedance circulation component (ICC) was then derived from the filtered TI using a RLS-based adaptive scheme. The wavelet decomposition of the ECG and ICC was carried out to obtain the different subband components and the reconstruced ECG and ICC. A total of 124 discrimination features were extracted from those signals andfed into a random forest (RF) classifier that made the pulse/no-pulse decision. A repeated cross-validation procedure was used for feature selection, parameter tuning, and model assessment. Pulse/no-pulse diagnoses obtained through the RF were compared with the annotations to obtain the sensitivity (SE), specificity (SP) and balanced accuracy (BAC) of the method. The results obtained were: 76.2% (SE), 66.2% (SP) and 71.2% (BAC).","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"245 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117012431","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：