Petr Andrla, F. Plesinger, J. Halámek, P. Leinveber, I. Viscor, P. Jurák
{"title":"A Method For Removing Pacing Artifacts From Ultra-High-Frequency Electrocardiograms","authors":"Petr Andrla, F. Plesinger, J. Halámek, P. Leinveber, I. Viscor, P. Jurák","doi":"10.22489/CinC.2018.106","DOIUrl":"https://doi.org/10.22489/CinC.2018.106","url":null,"abstract":"Cardiac resynchronization therapy (CRT) is an effective treatment for heart-failure patients with ventricular dyssynchrony. Analysis of ultra-high frequencies in ECG (UHFECG) has been shown to provide precise identification for the selection of CRT recipients, but the use of UHFECG for CRT optimization is limited due to the fact that UHFECG activity is buried under pacemaker stimuli. While removing the rising edge of a stimulus is quite straightforward, the localization and removal of the end of the post-stimulus recharge phase is more complicated due to its very low amplitude and interference with depolarization signals in QRS onset. 12-lead 5 kHz ECG during a 3–10 minute rest period was measured in 19 patients. We detected artifacts as 1.6-ms-long segments with high energy at frequencies of 1400–1900 Hz. We removed the area around the detected peaks in the time domain. Detection of artifacts, the stimulating pulse and the end of the recharge phase was evaluated against manually annotated marks with sensitivity and specificity of 0.98 and 0.97.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115274334","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}
{"title":"Evaluation of Multi-Lead ECG Markers to Track Changes in Dispersion of Ventricular Repolarization in the Intact Human Heart","authors":"M. Orini, N. Srinivasan, P. Taggart, P. Lambiase","doi":"10.22489/CinC.2018.345","DOIUrl":"https://doi.org/10.22489/CinC.2018.345","url":null,"abstract":"Dispersion of ventricular repolarization (DRT) is an important factor contributing to the vulnerability to life-threatening arrhythmias. An accurate non-invasive methodology for its estimation would contribute to improve risk-prediction. We assessed 3 multi-lead ECG markers to track changes in DRT using intra-cardiac data recorded in patients with structurally normal ventricles. Changes in DRT were measured with intra-cardiac unipolar electrograms (UEG) simultaneously recorded in the RV endocardium (RVendo), LV endocardium (LVendo) and LV epicardium (coronary sinus, LVepi) in 10 patients. Standard S1S2 restitution protocols were conducted by pacing from the RVendo (n = 8), LVendo (n = 10) and LVepi (n = 7). DRT was measured as latest minus earliest re-polarization time (RT). In the surface ECG, DRT was estimated from precordial and augmented limb leads as: (1) Interval between the earliest and the latest maximum up-slope of the T-wave (ΔTup); (2) Interval between median T-peak and median T-end (Tpe,med); (3) Interval between the earliest T-peak and latest T-end (Tpe,range). Intra-patient correlation with DRT changes was higher using ΔTup (0.79, 0.66 - 0.89) than Tpe,med (0.61, 0.14 - 0.76, $P$ = 0.001) or Tpe,med(0.71, 0.44 - 0.79, $P$ = 0.054).","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114364018","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}
A. Hunnik, S. Zeemering, P. Podziemski, Giulia Gatta, S. Verheule, U. Schotten
{"title":"Stationary and Recurrent Properties of Atrial Fibrillation Conduction Patterns in Goat","authors":"A. Hunnik, S. Zeemering, P. Podziemski, Giulia Gatta, S. Verheule, U. Schotten","doi":"10.22489/CinC.2018.291","DOIUrl":"https://doi.org/10.22489/CinC.2018.291","url":null,"abstract":"Introduction. Electrical mapping of the atria is used to assess the substrate of atrial fibrillation (AF). Targeted ablation of the AF substrate assumes spatiotemporal stationarity. In this study we analyzed long AF recordings of AF using high-density contact mapping. Methods. In 12 goats with stable AF 10 successive 60s files were recorded, within a single AF episode. AF cycle length, fractionation index (FI), lateral dissociation, conduction velocity, breakthroughs and preferentiality of conduction (Pref) were assessed to construct AF-property maps. The Pearson correlation coefficient (PCC) between AF-property maps of consecutive recordings was calculated. Recurrence plots and recurrence quantification analysis were used to identify recurrent patterns. Results Spatiotemporal stationarity for the 6 properties were high, PCC ranged from 0.66±0.11 for Pref to 0.98±0.01 for FI. The PCC is not affected by the time delay between files. Yet, highly dynamic patterns were found. Recurrence plots revealed few (1.6±0.7) recurrent patterns in individual animals. Conclusions AF properties were stationary in stable AF. This cannot be attributed to stable recurrent conduction patterns. during This suggests that spatial properties of the atrium determine AF properties.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114877524","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}
{"title":"ST Segment Change Classification Based on Multiple Feature Extraction Using ECG","authors":"Hongmei Wang, Wei Zhao, Yanwu Xu, Jing Hu, Cong Yan, Dongya Jia, Tianyuan You","doi":"10.22489/CinC.2018.253","DOIUrl":"https://doi.org/10.22489/CinC.2018.253","url":null,"abstract":"ST deviation detection using electrocardiogram (ECG) is of great significance for ischemia heart disease diagnosis. In this paper, we proposed an algorithm based on multiple feature extraction to classify the ST deviation beat by beat. First, the ST segment was located. Then, morphological and Poincaré features of ST segment were extracted and combined with global feature. Finally, random forest was adopted to classify the ST segment change into normal, elevated or depressed. The algorithm was evaluated on the European ST-T Database and the average sensitivity of normal, depressed and elevated ST segment was 85.2%, 86.9% and 88.8% respectively. The result shows that the developed algorithm is helpful in automatically detecting the ST segment elevation and depression, showing more details of the ischemic syndrome.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127158209","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}
Hamsa Naser, Dominic G. Whittaker, H. Shiels, M. Boyett, Henggui Zhang
{"title":"A Novel Model of Electrical Action Potentials of Teleost Fish Ventricular Myocytes","authors":"Hamsa Naser, Dominic G. Whittaker, H. Shiels, M. Boyett, Henggui Zhang","doi":"10.22489/CinC.2018.032","DOIUrl":"https://doi.org/10.22489/CinC.2018.032","url":null,"abstract":"Mathematical modelling, combined with experimental approaches, has become a powerful method for investigating the heart functions. So far, different models of cardiac electrical activities of variant species have been developed. However, models of fish cardiomycytes are less developed. Given the prominent problem of global warming, sea temperature changes will have a significant impact on the development of cardiac arrhythmias in the fish heart, leading to their sudden death, which may impose a heavy burden to the economy of the society. This study aimed to develop a biophysically detailed computer model for the teleost fish ventricular myocytes in warm acclimation (18 °C). A set of Hodgkin-Huxley (HH) formulations have been developed for the major ion currents that were based on experimental data from different teleost species. With a series of supra-threshold stimuli (amplitude of −41 pA/pF; duration of 10 ms and time interval (between two successive stimuli) of 1000 ms) the teleost fish model generates a successful sequence of action potentials (APs). The characteristics of the (APs) matched quantitatively the available experimental findings. In conclusion, a mathematical model for the electrical action potential of the teleost fish cardiac myocytes has been developed and validated.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126698545","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}
Jianwei Su, Sanchao Liu, Zehui Sun, Bailei Sun, Wenyu Ye, C. Rajagopalan, Xianliang He
{"title":"Real-time Fusion of ECG and SpO2 Signals to Reduce False Alarms","authors":"Jianwei Su, Sanchao Liu, Zehui Sun, Bailei Sun, Wenyu Ye, C. Rajagopalan, Xianliang He","doi":"10.22489/CinC.2018.163","DOIUrl":"https://doi.org/10.22489/CinC.2018.163","url":null,"abstract":"The aim of this study was the reduction of false arrhythmia alarms and improvement in the accuracy of calculated heart rates (HR) in real-time patient monitors by the fusion of information from ECG and SpO2 signals. These signals were analyzed independently to derive features for use in the fusion analysis. Information regarding the detection and classification of QRSs, signal quality index (SQI), HR and arrhythmia alarms were obtained from the ECG. Pulses, signal quality, pulse rate (PR) and hemodynamic parameters were obtained from the SpO2. Independent results from each signal were confirmed by fusing features from both. When an arrhythmia alarm was triggered, corresponding SpO2 features were checked to determine whether the alarm should be accepted or rejected HR and PR reliability was estimated using signal quality while QRSs and SpO2 pulses were matched to exclude spurious beats due to motion or other artifacts. Thus, calculated HR and PR were more accurate and false HRs from noisy ECG signals could be supplanted by the pulse rate if noise free. Adult, pediatric and neonate ECG signals were collected to make up training and test datasets. False alarm suppression was over 50% for all arrhythmia calls while it was over 60% for life threatening alarms. False HR/PR was reduced by 80%.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127270558","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}
{"title":"Pattern-Segmented Heart Rate Variability Analysis During Fetal Maturation","authors":"A. Schmidt, D. Hoyer, U. Schneider","doi":"10.22489/CinC.2018.008","DOIUrl":"https://doi.org/10.22489/CinC.2018.008","url":null,"abstract":"Background: Established fetal maturation diagnostics evaluates heart rate patterns (HRP) such as baseline, variability, decelerations (DC) and accelerations (AC). Fetal heart rate variability (fHRV) parameters provide valuable additional information. Their dependence on those patterns is crucial but not sufficiently explored. Objective of the present work is the comparison of the maturational age prediction using fHRV parameters with respect to those patterns. Methods: We analyzed 555 recordings, each one lasting 30 minutes, of normal fetuses, from 19 weeks of gestation (WGA) onward. We applied a pattern-segmented fHRV analysis of linear and nonlinear parameters under consideration of the fetal behavioral states to evaluate the WGA prediction accuracy, based on linear regression models that were tested using a repeated cross validation scheme. Results/Conclusion: fHRV parameters calculated under exclusion of DCs, show a significantly improved age dependency compared to the standard method, especially in the early weeks of the second half pregnancy. This aspect may improve the early sensitive identification of maturation disorders of the fetus.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123496762","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}
{"title":"Reconstruction of Patient-Specific Left Atrial Geometry from CMR Imaging","authors":"S. Teo, Xiaodan Zhao, R. Tan, L. Zhong, Yi Su","doi":"10.22489/CinC.2018.169","DOIUrl":"https://doi.org/10.22489/CinC.2018.169","url":null,"abstract":"Clinical quantification of left atrial (LA) volumes is currently performed using either the biplane area-length method or the method of discs (Simpson‘s method) on 2-D cardiac images or 3D echocardiography. However, these methods tend to underestimate LA volumes as compared to cardiovascular magnetic resonance (CMR) imaging. In this paper, we propose a geometry-based reconstruction algorithm for computing the LA volume automatically for the entire cardiac cycle by combining information from both the short- and long-axis from CMR imaging. The inputs to our reconstruction algorithm are as follows: (i) a set of segmented short-axis contours and (ii) a set of segmented long-axis contours from the standard 2-chamber and 4-chamber views. Our approach consists of a series of iterative steps where the most basal short-axis contour is projected in the atrial direction and subsequently morph to the patient-specific LA shape using the long-axis contours as guide. These series of morphing generate a left heart comprising both the LV and LA geometries with a planar basal surface. To reconstruct the LA cap, this planar basal surface is morphed into a hemisphere representing the closed surface of the LA using the long-axis contours as guide, thereby allowing us to reconstruct the closed LA shape and to calculate its volume.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123759621","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}
{"title":"Use of Approximation Entropy for Stratification of Risk in Patients With Chagas Disease","authors":"M. Vizcardo, A. Ravelo-García","doi":"10.22489/CinC.2018.234","DOIUrl":"https://doi.org/10.22489/CinC.2018.234","url":null,"abstract":"According to the World Health Organization, the number of people infected with Trypanosoma Cruzi is estimated between 6 and 7 million, the causative agent of Chagas disease, and in 550000 people exposed to the risk of affectation. The approximate entropy was used to quantify the regularity of the tachograms of patients with Chagas disease. The study population consisted of three groups of volunteers: 92 controls (C), 102 patients with positive serology without cardiac involvement diagnosed by conventional non-invasive methods (CH1) and 107 patients with positive serology and mild to moderate incipient heart failure (CH2). We analyzed RR segments of 5 minutes, 288 segments, corresponding to 24 hours per patient. We found significant differences between the Control and CH2 groups, which is used to stratify risk in the CH1 group.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121629832","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}
Naimahmed Nesaragi, Shubha Majumder, Ashish Sharma, K. Tavakolian, Shivnarayan Patidar
{"title":"Application of Recurrent Neural Network for the Prediction of Target Non-Apneic Arousal Regions in Physiological Signals","authors":"Naimahmed Nesaragi, Shubha Majumder, Ashish Sharma, K. Tavakolian, Shivnarayan Patidar","doi":"10.22489/CinC.2018.256","DOIUrl":"https://doi.org/10.22489/CinC.2018.256","url":null,"abstract":"This work presents a new method for detection of target non-apneic arousals by applying a recurrent neural network architecture on the various specified polysomno-graphic (PSG) signals. The proposed two stage architecture uses sequences of instantaneous frequencies and spectral entropies of the chosen PSG signals as feature vectors. At the first stage, these feature vectors are used to train several long-short term memory (LSTM) models. The LSTM networks can learn long-term relationships between time steps of time-frequency based sequences obtained out of physiological signals. As a second stage, some quadratic discriminant (QD) layers are modelled and appended to the trained LSTMs in groups. Subsequently, the outputs of all the QD layers are averaged for making final prediction. The models are trained using features obtained from one minute windows of the signals. However, the decision making on test signals involves inputs of one minute windows with half minute overlapping. When evaluated with 2018 PhysioNet/CinC Challenge dataset, the experimental outcomes demonstrate overall AUROC and AUPRC scores of 0.85±0.10 and 0.50±0.15 respectively for the training data. The generated test results indicate the AUROC and AUPRC scores of 0.624 and 0.10 respectively on a random subset of the test data.","PeriodicalId":215521,"journal":{"name":"2018 Computing in Cardiology Conference (CinC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124765223","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}