Pub Date : 2019-09-01DOI: 10.23919/CinC49843.2019.9005815
T. Panula, J. Blomster, Mikko Pänkäälä, T. Koivisto, M. Kaisti
The aim of the study was to develop an automated device for recording peripheral arterial pulse wave, in order to assess cardiovascular health. Recent studies have shown that photoplethysmography (PPG) is a viable technique to measure peripheral pressure waveform. We developed a small motorized device that can measure pulse waveform from a finger. The device targets the distal transverse palmar arch (DTPA) artery using infrared wavelength PPG. Measurements were taken from healthy subjects (n = 8).The device was validated by performing HR detection and waveform analysis. The device was able to record high quality blood pressure calibrated arterial waveforms and detect beat-to-beat heart rate allowing the assessment of cardiovascular health status.
{"title":"An Automated Device for Recording Peripheral Arterial Waveform","authors":"T. Panula, J. Blomster, Mikko Pänkäälä, T. Koivisto, M. Kaisti","doi":"10.23919/CinC49843.2019.9005815","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005815","url":null,"abstract":"The aim of the study was to develop an automated device for recording peripheral arterial pulse wave, in order to assess cardiovascular health. Recent studies have shown that photoplethysmography (PPG) is a viable technique to measure peripheral pressure waveform. We developed a small motorized device that can measure pulse waveform from a finger. The device targets the distal transverse palmar arch (DTPA) artery using infrared wavelength PPG. Measurements were taken from healthy subjects (n = 8).The device was validated by performing HR detection and waveform analysis. The device was able to record high quality blood pressure calibrated arterial waveforms and detect beat-to-beat heart rate allowing the assessment of cardiovascular health status.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"26 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":"73885006","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/CinC49843.2019.9005762
C. Xanthis, K. Haris, D. Filos, A. Aletras
Machine learning techniques have become increasingly successful over the last few years in medical image analysis and radiology. However, the low availability, relativeness and size of the training data sets required by the associated learning algorithms prevents their further development or delays their application in clinical practice.This study presented for the first time the development of artificially generated training datasets for supervised learning techniques through the incorporation of a realistic simulation framework in the field of Magnetic Resonance Imaging (MRI). An example in left-ventricle segmentation was utilized and the performance of a fully convolutional network on true cardiac MR data was evaluated.
{"title":"Artificially Generated Training Datasets for Supervised Machine Learning Techniques in Magnetic Resonance Imaging: An Example in Myocardial Segmentation","authors":"C. Xanthis, K. Haris, D. Filos, A. Aletras","doi":"10.23919/CinC49843.2019.9005762","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005762","url":null,"abstract":"Machine learning techniques have become increasingly successful over the last few years in medical image analysis and radiology. However, the low availability, relativeness and size of the training data sets required by the associated learning algorithms prevents their further development or delays their application in clinical practice.This study presented for the first time the development of artificially generated training datasets for supervised learning techniques through the incorporation of a realistic simulation framework in the field of Magnetic Resonance Imaging (MRI). An example in left-ventricle segmentation was utilized and the performance of a fully convolutional network on true cardiac MR data was evaluated.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"11 1","pages":"Page 1-Page 2"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74760184","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/CinC49843.2019.9005805
James Morrill, A. Kormilitzin, A. Nevado-Holgado, S. Swaminathan, Sam, Howison, Terry Lyons
Optimal feature selection leads to enhanced efficiency and accuracy when developing both supervised and unsupervised machine-learning models. In this work, a new signature-based regression model is proposed to automatically identify a patient's risk of sepsis based on physiological data streams and to make a positive or negative prediction ofsepsis for every time interval since admission to the intensive care unit. The gradient boosting machine algorithm that uses the features at the current time-points and the signature features extracted from the time-series to model the longitudinal effects ofsepsis yields the utility function score of 0.360 (officially ranked 1st, team name: ‘Can I get your Signature?’) on the full test set. The signature method shows a systematic and competitive approach to model sepsis by learning from health data streams.
在开发有监督和无监督机器学习模型时，最优特征选择可以提高效率和准确性。在这项工作中，提出了一种新的基于特征的回归模型，可以根据生理数据流自动识别患者的脓毒症风险，并在进入重症监护室后的每个时间间隔内对脓毒症进行阳性或阴性预测。梯度增强机算法使用当前时间点的特征和从时间序列中提取的签名特征来模拟脓毒症的纵向影响，在完整的测试集上，效用函数得分为0.360(官方排名第一，团队名称:Can I get your signature ?)签名方法显示了一种通过从健康数据流中学习来模拟败血症的系统和竞争性方法。
{"title":"The Signature-Based Model for Early Detection of Sepsis From Electronic Health Records in the Intensive Care Unit","authors":"James Morrill, A. Kormilitzin, A. Nevado-Holgado, S. Swaminathan, Sam, Howison, Terry Lyons","doi":"10.23919/CinC49843.2019.9005805","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005805","url":null,"abstract":"Optimal feature selection leads to enhanced efficiency and accuracy when developing both supervised and unsupervised machine-learning models. In this work, a new signature-based regression model is proposed to automatically identify a patient's risk of sepsis based on physiological data streams and to make a positive or negative prediction ofsepsis for every time interval since admission to the intensive care unit. The gradient boosting machine algorithm that uses the features at the current time-points and the signature features extracted from the time-series to model the longitudinal effects ofsepsis yields the utility function score of 0.360 (officially ranked 1st, team name: ‘Can I get your Signature?’) on the full test set. The signature method shows a systematic and competitive approach to model sepsis by learning from health data streams.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"9 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":"75078478","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/CinC49843.2019.9005925
S. Luo, Hong Wei, P. Macfarlane
ECGs from neonates are known to have a higher frequency content than adult ECGs.The aim of the study was to determine the effect of using different filter bandwidths on neonatal ECGs initially sampled at a rate of 8000 samples per second (which permits the use of a signal bandwidth much higher than 150 Hz) and to consider the implications for routine ECG recording.48 ECGs were recorded from newly born term infants (0-48 hours postnatal) at Princess Royal Maternity Hospital, Glasgow on a Burdick 8500 electrocardiograph. The frequency response of the machine was carefully checked. Peak to peak QRS amplitudes of average beats of the 10 second recordings were measured in all 8 independent leads with the results obtained at the full bandwidth of the ECG machine regarded as the reference.The full bandwidth of the 8500 was verified as 0.05 – 540Hz. It was found that the recommended upper frequency cutoff of 250Hz in the current guideline does not meet the goal of amplitude errors <25 μV in >95% of the cases in this data set. The clinical significance of high frequency components in pediatric ECGs is currently unclear.
{"title":"A Review of Bandwidth for Pediatric ECGs","authors":"S. Luo, Hong Wei, P. Macfarlane","doi":"10.23919/CinC49843.2019.9005925","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005925","url":null,"abstract":"ECGs from neonates are known to have a higher frequency content than adult ECGs.The aim of the study was to determine the effect of using different filter bandwidths on neonatal ECGs initially sampled at a rate of 8000 samples per second (which permits the use of a signal bandwidth much higher than 150 Hz) and to consider the implications for routine ECG recording.48 ECGs were recorded from newly born term infants (0-48 hours postnatal) at Princess Royal Maternity Hospital, Glasgow on a Burdick 8500 electrocardiograph. The frequency response of the machine was carefully checked. Peak to peak QRS amplitudes of average beats of the 10 second recordings were measured in all 8 independent leads with the results obtained at the full bandwidth of the ECG machine regarded as the reference.The full bandwidth of the 8500 was verified as 0.05 – 540Hz. It was found that the recommended upper frequency cutoff of 250Hz in the current guideline does not meet the goal of amplitude errors <25 μV in >95% of the cases in this data set. The clinical significance of high frequency components in pediatric ECGs is currently unclear.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"329 2-3 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":"77294559","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/CinC49843.2019.9005751
Yale Chang, Jonathan Rubin, G. Boverman, S. Vij, Asif Rahman, A. Natarajan, S. Parvaneh
Early prediction of sepsis onset can notify clinicians to provide timely interventions to patients to improve their clinical outcomes. The key question motivating this work is: given a retrospective patient cohort consisting of multivariate clinical time series (e.g., vital signs and lab measurement) and patients' demographics, how to build a model to predict the onset of sepsis six hours earlier? To tackle this challenge, we first used a recurrent imputation for time series (RITS) approach to impute missing values in multivariate clinical time series. Second, we applied temporal convolutional networks (TCN) to the RITS-imputed data. Compared to other sequence prediction models, TCN can effectively control the size of sequence history. Third, when defining the loss function, we assigned custom time- dependent weights to different types of errors. We achieved 9th place (team name = prna, utility score = 0.328) at the 2019 PhysioNet Computing in Cardiology Challenge, which evaluated our proposed model on a real-world sepsis patient cohort. At a follow-up ‘hackathon’ event, held by the challenge organizers, an improved version of our algorithm achieved 2nd place (utility score = 0.342).
{"title":"A Multi-Task Imputation and Classification Neural Architecture for Early Prediction of Sepsis from Multivariate Clinical Time Series","authors":"Yale Chang, Jonathan Rubin, G. Boverman, S. Vij, Asif Rahman, A. Natarajan, S. Parvaneh","doi":"10.23919/CinC49843.2019.9005751","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005751","url":null,"abstract":"Early prediction of sepsis onset can notify clinicians to provide timely interventions to patients to improve their clinical outcomes. The key question motivating this work is: given a retrospective patient cohort consisting of multivariate clinical time series (e.g., vital signs and lab measurement) and patients' demographics, how to build a model to predict the onset of sepsis six hours earlier? To tackle this challenge, we first used a recurrent imputation for time series (RITS) approach to impute missing values in multivariate clinical time series. Second, we applied temporal convolutional networks (TCN) to the RITS-imputed data. Compared to other sequence prediction models, TCN can effectively control the size of sequence history. Third, when defining the loss function, we assigned custom time- dependent weights to different types of errors. We achieved 9th place (team name = prna, utility score = 0.328) at the 2019 PhysioNet Computing in Cardiology Challenge, which evaluated our proposed model on a real-world sepsis patient cohort. At a follow-up ‘hackathon’ event, held by the challenge organizers, an improved version of our algorithm achieved 2nd place (utility score = 0.342).","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"81 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":"76713456","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/CinC49843.2019.9005743
T. Dietenbeck, Sophia Houriez--Gombaud-Saintonge, U. Gencer, A. Giron, G. Soulat, É. Mousseaux, P. Cluzel, A. Redheuil, N. Kachenoura
Aim: The diagnosis of thoracic aortic aneurysm is based on local aortic deformation associated to excessive aortic diameter (D). Maximal local aortic diameter was shown to be below the recommended surgical threshold in 30% of patients who ultimately developed aortic dissection. Aortic volumes integrate both dilation and elongation and may be more sensitive to changes in aortic geometry and less dependent on slice orientation and obliquity than diameter measurements. Methods: We studied 278 asymptomatic individuals with 3D aortic MRI: 119 healthy volunteers (hC), 53 hypertensive patients (HT) and 106 patients with dilated ascending aorta of which 62 with tricuspid (APt) and 44 with bicuspid (APb) aortic valve. Automated 3D aortic segmentation was performed and aortic lengths, maximal diameters and volumes were measured from sino-tubular junction to the brachiocephalic trunk for the ascending aorta (AAo) and from the left subclavian artery to the diaphragm for the descending aorta (DAo). Results: While AAo D increased by 40% between APt and HC, AAo volume increased by 170%. Moreover, when comparing HT patients with controls, AAo volume difference was significant (p < 0.05) even after adjustment to BSA while AAo D was not. Conclusion: Aortic volumes measured automatically from 3D MRI were able to characterize subclinical and pathological dilation more accurately than maximal diameters.
{"title":"Automated 3D MRI Aortic Morphometry Demonstrates the Added Value of Volumes as Compared to Diameters","authors":"T. Dietenbeck, Sophia Houriez--Gombaud-Saintonge, U. Gencer, A. Giron, G. Soulat, É. Mousseaux, P. Cluzel, A. Redheuil, N. Kachenoura","doi":"10.23919/CinC49843.2019.9005743","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005743","url":null,"abstract":"Aim: The diagnosis of thoracic aortic aneurysm is based on local aortic deformation associated to excessive aortic diameter (D). Maximal local aortic diameter was shown to be below the recommended surgical threshold in 30% of patients who ultimately developed aortic dissection. Aortic volumes integrate both dilation and elongation and may be more sensitive to changes in aortic geometry and less dependent on slice orientation and obliquity than diameter measurements. Methods: We studied 278 asymptomatic individuals with 3D aortic MRI: 119 healthy volunteers (hC), 53 hypertensive patients (HT) and 106 patients with dilated ascending aorta of which 62 with tricuspid (APt) and 44 with bicuspid (APb) aortic valve. Automated 3D aortic segmentation was performed and aortic lengths, maximal diameters and volumes were measured from sino-tubular junction to the brachiocephalic trunk for the ascending aorta (AAo) and from the left subclavian artery to the diaphragm for the descending aorta (DAo). Results: While AAo D increased by 40% between APt and HC, AAo volume increased by 170%. Moreover, when comparing HT patients with controls, AAo volume difference was significant (p < 0.05) even after adjustment to BSA while AAo D was not. Conclusion: Aortic volumes measured automatically from 3D MRI were able to characterize subclinical and pathological dilation more accurately than maximal diameters.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"331 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":"80506238","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/CinC49843.2019.9005844
Muhammad Haziq Kamarul Azman, Olivier Meste, D. Latcu, K. Kadir
Atrial flutter presents quasi-periodic atrial activity due to circular depolarization. Given the different structure of right and left atria, spatiotemporal variability should be different. This was analyzed using recurrence quantification analysis. Autocorrelation signals were estimated from the unthresholded recurrence plot, calculated with a properly processed ECG to remove variability related to external sources (noise, respiratory motion, T wave overlap). Simple features were considered from the autocorre-lation that attempts to describe the atrial activity in terms of range of recurrence and periodicity. Linear classification using support vector machines and logistic regression both allowed good classification performance (max accuracy 0.8 for both). Feature selection showed that right and left AFL have significantly different cycle lengths (right vs. left: 230.63 ms vs. 206.50 ms, p < 0.01).
心房扑动由于圆去极化而呈现准周期性心房活动。由于左右心房结构不同，其时空变异性也不同。使用递归定量分析进行分析。从无阈值递归图中估计自相关信号，并使用经过适当处理的ECG进行计算，以去除与外部源(噪声、呼吸运动、T波重叠)相关的变异性。简单的特征是考虑自相关，试图描述心房活动的复发和周期性的范围。使用支持向量机的线性分类和逻辑回归都有很好的分类性能(两者的最大准确率为0.8)。特征选择结果显示，左、右AFL的周期长度存在显著差异(左、右分别为230.63 ms和206.50 ms, p < 0.01)。
{"title":"Non-Invasive Localization of Atrial Flutter Circuit Using Recurrence Quantification Analysis and Machine Learning","authors":"Muhammad Haziq Kamarul Azman, Olivier Meste, D. Latcu, K. Kadir","doi":"10.23919/CinC49843.2019.9005844","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005844","url":null,"abstract":"Atrial flutter presents quasi-periodic atrial activity due to circular depolarization. Given the different structure of right and left atria, spatiotemporal variability should be different. This was analyzed using recurrence quantification analysis. Autocorrelation signals were estimated from the unthresholded recurrence plot, calculated with a properly processed ECG to remove variability related to external sources (noise, respiratory motion, T wave overlap). Simple features were considered from the autocorre-lation that attempts to describe the atrial activity in terms of range of recurrence and periodicity. Linear classification using support vector machines and logistic regression both allowed good classification performance (max accuracy 0.8 for both). Feature selection showed that right and left AFL have significantly different cycle lengths (right vs. left: 230.63 ms vs. 206.50 ms, p < 0.01).","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"21 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":"78999826","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/CinC49843.2019.9005719
MariNieves Pardo-Rodrı́guez, E. Bojorges-Valdez, O. Yáñez-Suárez
This study aimed to find whether there is a causal relationship between band power time series (BPts) extracted from EEG and heart rate variability (HRV). Such relationships were explored during spontaneous and a controlled breathing tasks. Data analyzed were recordings obtained from 14 healthy subjects using one ECG lead and 21 EEG channels. The RR intervals from the ECG were used to obtain the HRV signal, which was decomposed with Empirical Mode Decomposition into components of different spectral content known as intrinsic mode functions (IMFs). Granger causality tests were run for the BPts of alpha, beta and gamma frequency ranges of the EEG signal and the HRV signals IMFs. G-causality increased for three different conditions: slower IMFs (IMF4), BPts of higher frequency (gamma) band and during task realization. Meaning, gamma’s BPts G-caused HRV for a larger number of subjects and channels. Also there was a larger incidence on the number of channels that G-caused HRV during the controlled breathing task. The causal influence from the BPts of EEG signals to the HRV IMFs suggests there is an indirect or unobserved interaction between instantaneous changes on EEG band power and components of HRV which may explain changes in its dynamics.
{"title":"Causal Relationship Analysis of Heart Rate Variability and Band Power Time Series of Electroencephalographic Signals","authors":"MariNieves Pardo-Rodrı́guez, E. Bojorges-Valdez, O. Yáñez-Suárez","doi":"10.23919/CinC49843.2019.9005719","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005719","url":null,"abstract":"This study aimed to find whether there is a causal relationship between band power time series (BPts) extracted from EEG and heart rate variability (HRV). Such relationships were explored during spontaneous and a controlled breathing tasks. Data analyzed were recordings obtained from 14 healthy subjects using one ECG lead and 21 EEG channels. The RR intervals from the ECG were used to obtain the HRV signal, which was decomposed with Empirical Mode Decomposition into components of different spectral content known as intrinsic mode functions (IMFs). Granger causality tests were run for the BPts of alpha, beta and gamma frequency ranges of the EEG signal and the HRV signals IMFs. G-causality increased for three different conditions: slower IMFs (IMF4), BPts of higher frequency (gamma) band and during task realization. Meaning, gamma’s BPts G-caused HRV for a larger number of subjects and channels. Also there was a larger incidence on the number of channels that G-caused HRV during the controlled breathing task. The causal influence from the BPts of EEG signals to the HRV IMFs suggests there is an indirect or unobserved interaction between instantaneous changes on EEG band power and components of HRV which may explain changes in its dynamics.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"16 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":"80466413","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/CinC49843.2019.9005882
M. Calvo, V. Rolle, D. Romero, N. Béhar, P. Gomis, P. Mabo, Alfredo I. Hernández
Several autonomic markers were estimated overnight and during exercise and head-up tilt (HUT) testing for 44 BS patients, to design classifiers capable of distinguishing patients at different levels of risk. The classification performance of predictive models built from the optimization of a step-based machine-learning method were compared, so as to identify those autonomic protocols and markers best distinguishing between symptomatic and asymptomatic patients. Although exercise and HUT testing together led to better predictive results than when they were separately assessed, among all analyzed combinations, the night-based classifier presented the best performance (AUC = 95%), using the least amount of features. This optimal features subset was mostly composed of markers extracted between 4 a.m. - 5 a.m. Thus, results provide further evidence for the role of nighttime analysis, mainly during the last hours of sleep, for risk stratification in BS.
{"title":"Multivariate Classification of Brugada Syndrome Patients Based on the Autonomic Response During Sleep, Exercise and Head-up Tilt Testing","authors":"M. Calvo, V. Rolle, D. Romero, N. Béhar, P. Gomis, P. Mabo, Alfredo I. Hernández","doi":"10.23919/CinC49843.2019.9005882","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005882","url":null,"abstract":"Several autonomic markers were estimated overnight and during exercise and head-up tilt (HUT) testing for 44 BS patients, to design classifiers capable of distinguishing patients at different levels of risk. The classification performance of predictive models built from the optimization of a step-based machine-learning method were compared, so as to identify those autonomic protocols and markers best distinguishing between symptomatic and asymptomatic patients. Although exercise and HUT testing together led to better predictive results than when they were separately assessed, among all analyzed combinations, the night-based classifier presented the best performance (AUC = 95%), using the least amount of features. This optimal features subset was mostly composed of markers extracted between 4 a.m. - 5 a.m. Thus, results provide further evidence for the role of nighttime analysis, mainly during the last hours of sleep, for risk stratification in BS.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"24 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":"80918011","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/CinC49843.2019.9005738
M. Budanova, M. Chmelevsky, S. Zubarev, D. Potyagaylo, B. Rudic, E. Tueluemen, M. Borggrefe
Non-invasive electrocardiographic imaging (ECGI) shows high accuracy for topical diagnosis of focal arrhythmias. Activation maps obtained by ECGI allow for the analysis of excitation propagation during sinus rhythm with conduction disturbances. Nevertheless, noninvasive activation patterns have not been compared with the results of invasive mapping. In this article, we present the results of a qualitative comparison of non-invasive activation maps and CARTO LAT maps.
{"title":"Comparison of CARTO LAT Maps and Non-Invasive Activation Maps for Patients with Intraventricular Conduction Disturbance During Sinus Rhythm","authors":"M. Budanova, M. Chmelevsky, S. Zubarev, D. Potyagaylo, B. Rudic, E. Tueluemen, M. Borggrefe","doi":"10.23919/CinC49843.2019.9005738","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005738","url":null,"abstract":"Non-invasive electrocardiographic imaging (ECGI) shows high accuracy for topical diagnosis of focal arrhythmias. Activation maps obtained by ECGI allow for the analysis of excitation propagation during sinus rhythm with conduction disturbances. Nevertheless, noninvasive activation patterns have not been compared with the results of invasive mapping. In this article, we present the results of a qualitative comparison of non-invasive activation maps and CARTO LAT maps.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"277 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":"83061566","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：