Ilaria Marcantoni, Raffaella Assogna, A. Sbrollini, M. Morettini, L. Burattini
{"title":"Cardiac Electrical Alternans in Pregnancy: an Observational Study","authors":"Ilaria Marcantoni, Raffaella Assogna, A. Sbrollini, M. Morettini, L. Burattini","doi":"10.23919/cinc53138.2021.9662936","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662936","url":null,"abstract":"In pregnancy, if the woman has a cardiovascular disease, her fetus has an increased risk of inherited cardiac genetic disorders. Aim of this study was to evaluate electrocardiographic alternans (ECGA, $mu V)$ of 23 pregnant women, comparing 12 mothers of fetuses with normal rhythm (Mum_NRF) and 11 mothers of arrhythmic fetuses (Mum_ArrF). ECGA is a noninvasive cardiac electrical risk marker able to reveal heart electrical instability. ECGA manifests in the ECG as P-wave alternans (PWA), QRS alternans (QRSA) and/or T-wave alternans (TWA). Analysis was performed by the enhanced adaptive matched filter method. ECGA distributions were expressed as: median (interquartile range). Comparisons were performed by the Wilcoxon rank-sum test. Although showing similar heart rate (Mum_NRF: 85 (19) bpm; Mum_ArrF: 90 (13) bpm), ECGA was higher in Mum_ArrF population than Mum_NRF one (PWA: 9 (7) $mu V vs. 14 (14) mu V;$ QRSA: 9 (10) $mu V vs$ . 17 (16) $mu V$, TWA: 12 (14) $mu Vvs. 28(17) mu V)$, but only TWA distributions were statistically different. Moreover, TWA was higher than in a female healthy population (on average $18mu V)$in 70% of Mum_ArrF, vs. 33% of Mum_NRF. Thus, higher TWA in our Mum_ArrF seems to reflect a more unstable heart electrical condition of arrhythmic fetuses' mothers than normal-rhythm fetuses' mothers.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"114 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":"116470855","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. Natarajan, G. Boverman, Yale Chang, Corneliu C Antonescu, Jonathan Rubin
{"title":"Convolution-Free Waveform Transformers for Multi-Lead ECG Classification","authors":"A. Natarajan, G. Boverman, Yale Chang, Corneliu C Antonescu, Jonathan Rubin","doi":"10.23919/cinc53138.2021.9662697","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662697","url":null,"abstract":"We present our entry to the 2021 PhysioNet/CinC challenge - a waveform transformer model to detect cardiac abnormalities from ECG recordings. We compare the performance of the waveform transformer model on different ECG-lead subsets using approximately 88,000 ECG recordings from six datasets. In the official rankings, team prna ranked between 9 and 15 on 12,6,4,3 and 2-lead sets respectively. Our waveform transformer model achieved scores of 0.49, 0.49, 0.46, 0.47 and 0.44 on different ECG-lead subsets, with an average score of 0.47 on the held-out test set. Our combined performance across all leads placed us at rank 11 out of 39 officially ranking teams.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"28 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":"114674005","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}
F. Perego, B. D. Maria, G. Cassetti, Monica Parati, V. Bari, B. Cairo, F. Gelpi, A. Porta, L. Vecchia
{"title":"Working in the Office and Smart Working Differently Impact on the Cardiac Autonomic Control","authors":"F. Perego, B. D. Maria, G. Cassetti, Monica Parati, V. Bari, B. Cairo, F. Gelpi, A. Porta, L. Vecchia","doi":"10.23919/cinc53138.2021.9662943","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662943","url":null,"abstract":"The COVID-19 pandemic significantly changed the working settings of millions of office employees. Recently, the study of the cardiac autonomic control profile (CACP) has been suggested as an early screening tool in occupational medicine. In this study we describe the CACP in relation to different working conditions. Seventeen healthy office active employees (age: $38pm 7 yrs, 9/8$ males/females) were studied, by means of electrocardiogram 24-hour Holter monitoring, while alternating working at home (SMART) and in the office (OFFICE), respectively. The beat-to-beat series of the time distance between two consecutive R-wave peaks was extracted during the 24 hours. Parametric power spectral analysis was iterated over the RR series during daytime (DAY) and nighttime (NIGHT). The degree of perceived stress, as measured via the visual analogue scale, was higher in OFFICE. During NIGHT the variance of the RR series was higher in SMART than in OFFICE situation. A similar tendency was observed for the absolute power of RR series in high frequency band. We conclude that the expected circadian rhythm of the vagal control is more evident in the SMART situation than in the OFFICE condition and the perceived stress is lower, with beneficial effects for the cardiovascular system and for the overall status of the entire organism.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"46 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":"114685928","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}
Mattias P. Karlsson, Mikael Wallman, S. R. Ulimoen, F. Sandberg
{"title":"Non-Invasive Characterization of Atrio-Ventricular Properties During Atrial Fibrillation","authors":"Mattias P. Karlsson, Mikael Wallman, S. R. Ulimoen, F. Sandberg","doi":"10.23919/cinc53138.2021.9662952","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662952","url":null,"abstract":"The atrio-ventricular (AV) node is the primary regulator of ventricular rhythm during atrial fibrillation (AF). Hence, ECG based characterization of AV node properties can be an important tool for monitoring and predicting the effect of rate control drugs. In this work we present a network model of the AV node, and an associated workflow for robust estimation of the model parameters from ECG. The model consists of interacting nodes with refractory periods and conduction delays determined by the stimulation history of each node. The nodes are organized in one fast pathway (FP) and one slow pathway (SP), interconnected at their last nodes. Model parameters are estimated using a genetic algorithm with a fitness function based on the Poincare plot of the RR interval series. The robustness of the parameter estimates was evaluated using simulated data based on ECG measurements. Results from this show that refractory period parameters $R_{min}^{SP}$ and $Delta R^{SP}$ can be estimated with an error $(meanpm std)$ of $10pm 22 ms and-12.6pm 26 ms$ respectively, and conduction delay parameters $D_{min,tot}^{SP}$ and $Delta D_{tot}^{SP}$ with an error of $7pm 35 ms$ and $4pm 36 ms$. Corresponding results for the fast pathway are $31.7pm 65 ms, -0.3pm 77 ms$, and 1 $7pm 29 ms,43pm 109 ms$. This suggest that AV node properties can be assessed from ECG during AF with enough precision and robustness for monitoring the effect of rate control drugs.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"27 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":"132137388","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":"An InceptionTime-Inspired Convolutional Neural Network to Detect Cardiac Abnormalities in Reduced-Lead ECG Data","authors":"Harry J. Crocker, Aaron Costall","doi":"10.23919/cinc53138.2021.9662678","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662678","url":null,"abstract":"Cardiovascular disease is the leading cause of death worldwide. The twelve-lead electrocardiogram (ECG) is a common tool for diagnosing cardiac abnormalities, but its interpretation requires a trained cardiologist. Thus there is growing interest in automated ECG diagnosis, especially using fewer leads. Hence the PhysioNet-CinC Challenge 2021: Will two (leads) do? The University of Bath team (UoB_HBC) developed InceptionTime-inspired deep convolutional neural networks, using parallel 1D convolutions of varying length, for twelve-, six-, four-, three-, and two-lead models. The twelve-lead model achieved a Challenge metric score of 0.35 on the test set, placing the University of Bath team 23rd out of 39 entries. Though the twelve-lead model performed best, three-lead performance was lower by only 0.25 %, suggesting potential for reliable reduced-lead diagnoses. Furthermore, the three-lead model performed consistently better than the six-lead, highlighting the importance of selection of type of lead, not just their number.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"50 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":"128221805","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":"Diagnosis of Cardiac Abnormalities Applying Scattering Transform and Fourier-Bessel Expansion on ECG Signals","authors":"N. Sawant, Shivnarayan Patidar","doi":"10.23919/cinc53138.2021.9662751","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662751","url":null,"abstract":"This work intends to devise an efficient feature extraction scheme for identifying common cardiac abnormalities using the Fourier-Bessel (FB) expansion of RR-intervals and time-frequency based features of Electrocardiogram (ECG) signals. The Bessel basis, when used for representing the RR-intervals, meaningfully enhances the pathologically induced low-frequency changes in terms of FB coefficients. To ensure the characterization of diverse pathological variability present in the ECG signals, time-frequency domain features are also extracted using scattering transform. The multi-label classification of the ECG signals, for five different lead combinations as mentioned in the Phys-ioNet/CinC Challenge 2021, is performed using Gated recurrent unit into specified twenty-six categories. We have participated in this Challenge as team “Medics”. Our code failed to run on the validation set during the official phase of the Challenge, hence our entry was not officially ranked in the Challenge. The experimental outcomes, for five-fold cross validation using 2021 PhysioNet/CinC Challenge dataset, demonstrates the mean Challenge scoring metric on the twelve-lead, six-lead, four-lead, three-lead, and two-lead combinations as 0.40, 0.43, 0.43, 0.44, and 0.45 respectively. According to the results, the proposed method justifies the use of the FB and scattering transform together for the detection and identification of common cardiac problems using ECG signals.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"7 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":"128232979","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. Porta, F. Gelpi, V. Bari, B. Cairo, B. D. Maria, A. Takahashi, A. Catai
{"title":"The Magnitude of the Postural Challenge Impacts on the Exponential Decay of the Baroreflex Impulse Response","authors":"A. Porta, F. Gelpi, V. Bari, B. Cairo, B. D. Maria, A. Takahashi, A. Catai","doi":"10.23919/cinc53138.2021.9662815","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662815","url":null,"abstract":"We hypothesize that a postural challenge can affect the bandwidth of the cardiac baroreflex. The study estimated the impulse response function (IRF) of cardiac baroreflex via a model-based approach applied to spontaneous fluctuations of heart period (HP) and systolic arterial pressure (SAP). The exponential decay constant of the IRF was taken as an estimate of the bandwidth of the HP-SAP relationship: the higher the exponential decay constant, the wider the bandwidth. The IRF of the HP-SAP link was estimated in 17 healthy humans (age: 21–36 yrs, median $=29yrs;8$ males) during graded head-up tilt with tilt table inclination at 0, 15, 30, 45, 60, 75 and 90 degrees. Each tilt session was preceded by a supine resting period and followed by a recovery. A bivariate autoregressive model with exogenous input was utilized to describe the dependence of HP variations on SAP changes. The exponential decay constant was calculated by fitting the IRF absolute value with a mono-exponential function. We found that the exponential decay constant gradually decreased with tilt table angles. This finding is compatible with a reduced bandwidth of the cardiac baroreflex, likely linked to the gradual vagal withdrawal associated with the magnitude of the challenge.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"43 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":"128686939","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}
Martin Baumgartner, M. Kropf, L. Haider, S. Veeranki, D. Hayn, G. Schreier
{"title":"ECG Classification Combining Conventional Signal Analysis, Random Forests and Neural Networks - a Stacked Learning Scheme","authors":"Martin Baumgartner, M. Kropf, L. Haider, S. Veeranki, D. Hayn, G. Schreier","doi":"10.23919/cinc53138.2021.9662777","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662777","url":null,"abstract":"This year's Physionet Challenge focused on the question how many leads are required to develop a high-quality ECG classification algorithm. We (team name: easyG) propose a stacked learning scheme combining conventional signal analysis, random forests and neural networks. Highly specialized regression random forest models were trained with classical ECG processing where features were derived for each channel of each signal. The outputs were then used in a neural network to achieve a 1D regression vector, which was used to optimize classification thresholds. We present offline validation results for each lead set and class-specific classification scores to allow for insights into the question how many leads are sufficient. Due to technical issues, we only achieved a score of -0.46 (all-lead) in the official leaderboard (rank 37). We have found that lead reduction leads to a minor loss in overall performance. However, variation in class-specific performance with lead reduction exists. Some classes were recognized better with more leads, but in rare cases, the opposite was true. The results suggest that the optimal number of used channels is depending on the setting and goals of the classification.","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":"134438260","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}
Aikaterini Vraka, V. Bertomeu-González, F. Hornero, F. Ravelli, R. Alcaraz, J. J. Rieta
{"title":"Linear and Nonlinear Correlations Between Surface and Invasive Atrial Activation Features in Catheter Ablation of Paroxysmal Atrial Fibrillation","authors":"Aikaterini Vraka, V. Bertomeu-González, F. Hornero, F. Ravelli, R. Alcaraz, J. J. Rieta","doi":"10.23919/cinc53138.2021.9662868","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662868","url":null,"abstract":"P-waves are vastly used to assess the outcome of catheter ablation (CA) of atrial fibrillation (AF). It remains unknown, however, if coronary sinus (CS), the key reference structure in CA procedures, follows similar patterns. This study's objective is to detect any correlations between the behavior of P-waves and CS local activation waves (LAWs) with regard to CA procedure. Duration, amplitude, area and slope rate were studied in P-waves and LAWs of five-minute recordings from 29 patients undergoing paroxysmal AF CA. Normalization (N) due to heart rate (HR) fluctuations was performed. Pearson's correlation (PC) between CA-induced variations $(Delta)$ of P-waves and LAWs was calculated. Linear correlations between each P-wave/LAW were studied with PC and linear regression with 10-fold cross-validation. Cross-quadratic sample entropy (CQSE) assessed nonlinear correlations. $PC(Delta: rho < 52.27%,p=0.015, P$-wave/LAW· $rho <$ 40.37%, $p=0.001)$ and linear regression analysis $(R^{2}- adj < 16.02%, p=0.015)$ showed low/mediocre linear correlations. CQSE ( 0.8 - 1.3) also suggested weak nonlinear relationships. P-waves and LAWs are poorly correlated and do not describe to the same degree the substrate modification after CA. It is possible that P-waves reflect the cumulative CA-induced modifications of various atrial sites, with CS being one of them but not the dominant.","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"9 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":"134088276","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 the ECGI Patchwork Method Using Experimental Data in Sinus Rhythm","authors":"Oumayma Bouhamama, L. Weynans, L. Bear","doi":"10.23919/cinc53138.2021.9662809","DOIUrl":"https://doi.org/10.23919/cinc53138.2021.9662809","url":null,"abstract":"Torso surface and ventricular epicardial potentials were recorded simultaneously in anesthetized, closed-chest pigs $(n=5)$ during sinus rhythm. Activation times were estimated from recorded torso potentials using three classical ECGI methods and a new method called the Patchwork Method (PM), which locally selects the optimal ECGI method and has demonstrated its efficiency with simulated data. The aim of this study was to evaluate the Patchwork method using experimental data in sinus rhythm. By comparing the classic ECGI reconstructions to recorded epicardial activation mapping, several inaccuracies in the ECGI maps are highlighted in this study. This involved inaccuracies in reconstructing activating maps, locating breakthrough sites and the production of artificial lines of block. However, the PM overcomes these restrictions, demonstrating its abilities to accurately reconstruct activation maps $(CC=0.90 [0.86;0.92]$ and $RE=0.20$ [0.19; 0.24]) and localize epicardial breakthrough sites $(LE=17.16 [8.87;22.14])$. Furthermore, it reduced the frequency of artificial lines of block (2 of 5 pig hearts).","PeriodicalId":126746,"journal":{"name":"2021 Computing in Cardiology (CinC)","volume":"31 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":"132757233","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}