{"title":"An Algorithm for Early Detection of Sepsis Using Traditional Statistical Regression Modeling","authors":"Roshan Pawar, J. Bone, J. Ansermino, M. Görges","doi":"10.23919/CinC49843.2019.9005699","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005699","url":null,"abstract":"Sepsis is the final common pathway for many infections, whereby the body’s immune response leads to organ failure, and eventually death. It is associated with high mortality rates and, if survived, significant morbidity. Early detection is imperative to improve outcomes. Yet, there is also a need to avoid a high false alarm rate. The aim of this study was to develop and evaluate a simple algorithm for early sepsis detection.Significant missing data were encountered in the dataset, which were forward-filled or substituted with population means. Clinically relevant variable combinations were added along with transformation features including dichotomization, z-scores, first derivative, and changes from baseline. A logistic regression model was used to identify candidate features and build the overall risk score function for prediction.The final candidate score had areas under the receiver operating characteristic curve of 0.747, 0.760, and 0.783 for the three test data sets. It had accuracies of 0.795, 0.889, 0.815, respectively, and an overall utility score for the full test set of 0.249 using a cutoff of 0.024.Evaluation indicated significant potential for further optimization, including reduction of false-positive predictions. Adding features capturing change over time is expected to provide scope for further investigation.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"1 1","pages":"Page 1-Page 4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89796323","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":"Sleep Stage Influence on the Autonomic Modulation of Sleep Apnea Syndrome","authors":"M. Calvo, R. Jané","doi":"10.23919/CinC49843.2019.9005885","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005885","url":null,"abstract":"Hypoxia induced by obstructive sleep apnea (OSA) leads to the deregulation of the autonomic nervous system (ANS), resulting in an abnormally increased sympathetic activity. Since ANS modulation varies throughout the night, notably for each sleep stage, the hypno-gram and heart rate signals of 81 OSA patients were collected during a polysomnography. They were classified as mild-moderate (n=44) or severe (n=37) based on their apnea-hypopnea index (AHI). Spectral heart rate variability (HRV) series were extracted by a time-frequency approach. These series were then averaged for each sleep stage, in order to compare the sympathetic modulation of mild-moderate and severe patients at the following phases: rapid eye movement (REM), S1, S2 and SWS (slow wave sleep). According to normalized power at the low-frequency band (LFnu) values, severe OSA seems to be associated with an increased sympathetic modulation at non-REM sleep. Moreover, a decreased autonomic variability throughout the night may be related to a reduced adaptability of the cardiovascular system, characterizing a more advanced stage of the disease. These results provide further evidence for the role of autonomic alterations induced by hypoxia, suggesting the use of HRV analysis, together with AHI, for the study of OSA severity.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"24 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82561798","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}
D. P. D. Silva, W. Watanabe, W. S. Lopes, Henrique Rodrigues, R. R. Silva, J. Salinet, M. Bissaco, D. G. Goroso
{"title":"Monitoring Remote of Biomedical Signal","authors":"D. P. D. Silva, W. Watanabe, W. S. Lopes, Henrique Rodrigues, R. R. Silva, J. Salinet, M. Bissaco, D. G. Goroso","doi":"10.23919/CinC49843.2019.9005724","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005724","url":null,"abstract":"The remote monitoring of the biomedical signal is an important tool for assessing the quality of life, control and prevention of diseases. In this research, we developed and validated a remote monitoring system for prevention and health promotion. The system architecture is composed of 3 main modules: a) interface for recording food intake and monitoring physical activity and heart rate frequency by a mobile application; b) interface for insert anthropometric assessment data of patient; c) web interface where all data is remotely shown through reports with information that can assist in preventive health actions. The study involved 70 children aged between 8 and 12 years. They were monitored for 4 months by the app installed in the children's own smartphones. Significant differences were observed in the frequency domain and nonlinear heart rate variability variables between each anthropometric group. Moreover, within the same group, there were also differences between night-morning and afternoon/evening time. Being the biggest variation in the frequency domain parameters during afternoon/evening time for the obese group.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"22 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82652085","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":"Aortic Pressure Waveforms Reconstruction Using Simplified Kalman Filter","authors":"Wenyan Liu, Zongpeng Li, Yang Yao, Shuran Zhou, Yuelan Zhang, Lisheng Xu","doi":"10.23919/CinC49843.2019.9005554","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005554","url":null,"abstract":"Aortic pressure (Pa) waveforms are important for diagnosis of cardiovascular disease. However, the direct measurement of Pa is invasive and expensive. In the paper, a new simplified Kalman filter (SKF) algorithm for blind system identification was employed for the reconstruction of Pa waveforms using two peripheral artery pressure waveforms. The data of Pa waveforms are collected from 24 human subjects. Simultaneously, brachial artery and femoral artery pressure waveforms data are generated from the simulation of a known two-channel finite impulse response system. In order to study the performance of the proposed SKF algorithm, different amounts of signal-to-noise ratio of the output signal were used in the experiment. Experimental results demonstrated that the proposed SKF algorithm had advantages in comparison with the canonical correlation analysis (CCA) algorithm. It is notable that the proposed SKF algorithm works much more noise-robust than the CCA algorithm in a wide range of SNR.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"61 4 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":"90104140","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":"Isosbestic Point in Optical Mapping; Theoretical and Experimental Determination With Di-4-ANBDQPQ Transmembrane Voltage Sensitive Dye","authors":"I. Uzelac, C. Crowley, F. Fenton","doi":"10.23919/CinC49843.2019.9005532","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005532","url":null,"abstract":"Optical mapping methods utilize fluorescence dyes to measure dynamic response of cardiac tissue such as changes in transmembrane potential (Vm). For the commonly used Vm sensitive dyes, a dye absorption and emission spectra shift as Vm changes. Signals relevant to Vm are calculated as a relative fluorescence change with respect to the fluorescence baseline. The amplitude of the change depends on the long-pass (LP) filter cut-on wavelength, placed on the sensor side, and the excitation wavelength. An excitation wavelength near the absorption peak, termed the isosbestic point, results in minimal absorption coefficient change as absorption spectra shifts. Consequentially the fluorescence intensity virtually does not change, when fluorescence across the entire emission spectra is measured, irrelevant of Vm changes. In this study we experimentally determined the isosbestic point for a near infrared dye Di-4-ANBDQPQ. We then present a theoretical study examining the dye linear or non-linear response as the fractional fluorescence change of Vm change, due to emission spectra shift and amplitude change, over a range of excitation wavelengths and LP filters. Linear \"optical\" response is important to quantify certain aspects of cardiac dynamics such as the action potential (AP) shape and duration, especially when studying drug effects and dynamical substrates for arrhythmia development.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"13 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":"75057821","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}
Alfonso Aranda, Joël M. H. Karel, P. Bonizzi, R. Peeters
{"title":"Acute MI Detection Derived From ECG Parameters Distribution","authors":"Alfonso Aranda, Joël M. H. Karel, P. Bonizzi, R. Peeters","doi":"10.23919/CinC49843.2019.9005742","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005742","url":null,"abstract":"Several studies in the past have evaluated the use of different ECG-based features to diagnose acute myocardial infarction (AMI). This was generally done by looking at how well a feature reflects differences between baseline (no AMI) and AMI situations. This approach tends to overlook the progress of AMI and to underestimate false positives when implemented into a continuous monitoring setting and therefore appears inadequate for it. This has hindered the adoption of those methods in the clinical practice. In this research, we present a novel set of parameters for the dynamic assessment of AMI condition. Those parameters are obtained by analyzing the changes over time in the distribution properties of ECG-based features.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"22 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":"79256532","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}
C. Varon, Dries Hendrikx, J. Bolea, P. Laguna, R. Bailón
{"title":"Quantification of Linear and Nonlinear Cardiorespiratory Interactions Under Autonomic Nervous System Blockade","authors":"C. Varon, Dries Hendrikx, J. Bolea, P. Laguna, R. Bailón","doi":"10.23919/CinC49843.2019.9005628","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005628","url":null,"abstract":"This paper proposes a methodology to extract both linear and nonlinear respiratory influences from the heart rate variability (HRV), by decomposing the HRV into a respiratory and a residual component. This methodology is based on least-squares support vector machines (LS-SVM) formulated for nonlinear function estimation. From this decomposition, a better estimation of the respiratory sinus arrhythmia (RSA) and the sympathovagal balance (SB) can be achieved. These estimates are first analyzed during autonomic blockade and an orthostatic maneuver, and then compared against the classical HRV and a model that considers only linear interactions. Results are evaluated using surrogate data analysis and they indicate that the classical HRV and the linear model underestimate the cardiorespiratory interactions. Moreover, the linear and nonlinear interactions appear to be mediated by different control mechanisms. These findings will allow to better assess the ANS and to improve the understanding of the interactions within the cardiorespiratory system.","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":"78997870","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}
Sophia Houriez--Gombaud-Saintonge, A. Pascaner, G. Soulat, U. Gencer, T. Dietenbeck, D. Craiem, E. Bollache, Y. Chenoune, É. Mousseaux, N. Kachenoura
{"title":"Characterization of Blood Flow Changes in Normal and Pathological Aortic Dilation from 4D Flow Magnetic Resonance Imaging","authors":"Sophia Houriez--Gombaud-Saintonge, A. Pascaner, G. Soulat, U. Gencer, T. Dietenbeck, D. Craiem, E. Bollache, Y. Chenoune, É. Mousseaux, N. Kachenoura","doi":"10.23919/CinC49843.2019.9005740","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005740","url":null,"abstract":"Aim: Maximal diameter (Dmax), which is commonly used to diagnose thoracic aortic aneurysm (TAA) was previously shown to be normal in 20-30% of patients who ultimately develop dissection. Besides, inner aortic flow is associated with its wall dynamics. Thus, our aim was to quantify aortic flow changes using 4D flow MRI in the setting of ascending aorta (AA) dilation.Methods: We studied 20 patients with TAA and tricuspid aortic valve (TAA) and 56 healthy controls (30 subjects, 36±9y ≤50 years named YC, 26 subjects, 65±9y >50 years named OC). All underwent 4D flow MRI. After aortic segmentation, regional volume of backward flow (VBF) was extracted in addition to in-cross-section velocity standard deviation (SD) as well as maximal velocity jet angle (Angle) and eccentricity (Ecc). Receiver operating characteristic (ROC) analysis was performed to assess ability of flow indices to characterize dilation.Results: While AA Dmax changed by 1.4 folds between TAA and OC, VBF changed by 6.5 folds, and Ecc, Angle and SD changed by 1.3 to 1.9 folds between the two groups. Moreover VBF varied consistently with age and was able to detect AA dilation with an accuracy of 0.98.Conclusion: 4D flow MRI indices of local aortic flow disorganization, specifically backward flow, were able to accurately characterize dilation.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"75 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80794178","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}
R. Molero, A. Climent, I. Hernández-Romero, A. Liberos, F. Fernández‐Avilés, F. Atienza, M. Guillem, M. Rodrigo
{"title":"Effects of Geometry in Atrial Fibrillation Markers Obtained With Electrocardiographic Imaging","authors":"R. Molero, A. Climent, I. Hernández-Romero, A. Liberos, F. Fernández‐Avilés, F. Atienza, M. Guillem, M. Rodrigo","doi":"10.23919/CinC49843.2019.9005905","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005905","url":null,"abstract":"Electrocardiographic imaging (ECGI) can characterise cardiac pathologies such as atrial fibrillation (AF) through specific markers based on frequency or phase analysis. In this study, the effect of the geometry of patients’ torso and atria in the ECGI resolution is studied.A realistic 3D atrial geometry was located on 30 patient torsos and ECGI signals were calculated for 30 different AF simulations in each torso. Dominant frequency (DF) and reentrant activity analysis were calculated for each scenario. Anatomical and geometrical measurements of each torso (30-80% of variability between patients) and atria were calculated and compared with the errors in the ECGI estimation versus the departing EGM maps.Results show evidences that big chest dimensions worsen the non-invasive calculation of AF markers (p<0.05). Also, higher number of visible electrodes from each atrial region improves ECGI characterization measured as lower DF deviations (0.64±0.26 Hz vs 0.72±0.27 Hz, p<0.05) and higher reentrant activity coincidence (10.1±12.2% vs 3.4±3.4%, p<0.05).Torso and atrial geometry affect the quality of the non-invasive reconstruction of AF markers such as DF or reentrant activity. Knowing the geometrical parameters that worsen non-invasive AF maps may help to measure each detected AF driver reliability.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"56 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80867241","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":"New Mathematical Models for the Mouse Atrial Fast Sodium Channel","authors":"Shanzhuo Zhang, Wei Wang, Kuanquan Wang, Henggui Zhang","doi":"10.23919/CinC49843.2019.9005857","DOIUrl":"https://doi.org/10.23919/CinC49843.2019.9005857","url":null,"abstract":"The fast sodium channel (FSC) is one of the most important channels in the cardiomyocytes. It leads the activation of the cardiac action potentials and its dysfunction may leads to many severe pathologies. However, the currently widely used FSC model is not developed for mouse, and relatively outdated compared with the emerging experimental data on mouse atria, making the model less reliable in investigating the mechanisms underlying atrial arrhythmias. In this work, we intend to develop a new model for the mouse atrial FSC which can reproduce the newly published experimental data. The kinetics of and the current generated by our new model were thoroughly validated. We investigated the response of the new model to infra- or supra-threshold stimuli and found that it needs a smaller stimulus to be activated and has a higher driving ability compared with the old model. The current amplitude of the new model also shows a smoother stimulus-dependent curve than the old model. This model will be a more suitable tool in the research of atrial arrhythmias.","PeriodicalId":6697,"journal":{"name":"2019 Computing in Cardiology (CinC)","volume":"4 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":"80193611","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}