Pub Date : 2007-09-01DOI: 10.1109/CIC.2007.4745529
A. Jalali, A. Ghaffari, M. Ghasemi, H. Sadabadi, P. Ghorbanian, H. Golbayani
An approach to classify disorders in autonomic control of cardiovascular system is proposed in this paper. The target of this study is to highlight main features of malfunctions in cardiovascular system due to autonomic disorder. Collecting the data from the physionet archive, we divide patients into two groups of normal and abnormal, based on having autonomic disorder in their cardiovascular system or not. Systolic blood pressure (SBP) and heart rate (HR) time series are evaluated for each patient. We then plot the diagram of SBP against HR for all patients in a single figure. Fuzzy c-means clustering (FCM) method is also applied to cluster data into two groups. A neural network is then implemented to classify and to distinguish the two groups. The network is trained with data of a normal patient and is tested with data of other normal and abnormal patients. Result show that selected features can clearly detect disorders in autonomic system.
{"title":"Disorder classification in the regulatory mechanism of the cardiovascular system","authors":"A. Jalali, A. Ghaffari, M. Ghasemi, H. Sadabadi, P. Ghorbanian, H. Golbayani","doi":"10.1109/CIC.2007.4745529","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745529","url":null,"abstract":"An approach to classify disorders in autonomic control of cardiovascular system is proposed in this paper. The target of this study is to highlight main features of malfunctions in cardiovascular system due to autonomic disorder. Collecting the data from the physionet archive, we divide patients into two groups of normal and abnormal, based on having autonomic disorder in their cardiovascular system or not. Systolic blood pressure (SBP) and heart rate (HR) time series are evaluated for each patient. We then plot the diagram of SBP against HR for all patients in a single figure. Fuzzy c-means clustering (FCM) method is also applied to cluster data into two groups. A neural network is then implemented to classify and to distinguish the two groups. The network is trained with data of a normal patient and is tested with data of other normal and abnormal patients. Result show that selected features can clearly detect disorders in autonomic system.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126572653","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745414
P. Stein, R. Cohen, N. Devlin, E.M. Lundequam, P. Domitrovich, J. Gottdiener, S. Redline
To characterize changes in nighttime cyclic variation in HR (CVHR) with advancing age in older adults, CVHR was quantified for N=56 adults with 2 Holter recordings 5 yrs apart (CHS1 and CHS 2) in the cardiovascular health study (CHS) and 2 overnight polysomnograms 5 yrs apart in the sleep heart health study (SHHS1 and SHHS2) using MatLab. Baseline age was 71plusmn3 yrs. The number of CVHR events was also normalized to time in bed (CVHR index). CVHR index did not change across recordings, but males had higher values (p=0.009). Mean HR increase during CVHR was similar in the first 3 recording but declined on the last (p<0.02). CVHR duration increased, but CHS1 vs. CHS2 and SHHS1 vs. SHHS2 were NS (rest, p<0.007). We conclude that CVHR is frequent at night in older adults, but results suggest an age-related trend towards decreased magnitude and longer durations of HR arousals, possibly due to the aging of the autonomic nervous system.
为了描述老年人夜间HR (CVHR)周期变化随年龄增长的变化，我们对56名成年人的CVHR进行了量化，其中包括心血管健康研究(CHS)中间隔5年的2次动态心电图(CHS1和CHS 2)和睡眠心脏健康研究(SHHS1和SHHS2)中间隔5年的2次夜间多路睡眠图(MatLab)。基线年龄71岁+ 3岁。CVHR事件的数量也被归一化到床上时间(CVHR指数)。CVHR指数在不同的记录中没有变化，但男性的值更高(p=0.009)。CVHR期间的平均HR增加在前3次记录中相似，但在最后一次记录中下降(p<0.02)。CVHR持续时间增加，但CHS1 vs CHS2、SHHS1 vs SHHS2为NS(其余，p<0.007)。我们的结论是，CVHR在老年人中经常发生在夜间，但结果表明，与年龄相关的趋势是HR唤醒的强度降低和持续时间延长，可能是由于自主神经系统的衰老。
{"title":"Cyclic variation in heart rate during sleep in four recordings of up to 13 years in elderly adults","authors":"P. Stein, R. Cohen, N. Devlin, E.M. Lundequam, P. Domitrovich, J. Gottdiener, S. Redline","doi":"10.1109/CIC.2007.4745414","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745414","url":null,"abstract":"To characterize changes in nighttime cyclic variation in HR (CVHR) with advancing age in older adults, CVHR was quantified for N=56 adults with 2 Holter recordings 5 yrs apart (CHS1 and CHS 2) in the cardiovascular health study (CHS) and 2 overnight polysomnograms 5 yrs apart in the sleep heart health study (SHHS1 and SHHS2) using MatLab. Baseline age was 71plusmn3 yrs. The number of CVHR events was also normalized to time in bed (CVHR index). CVHR index did not change across recordings, but males had higher values (p=0.009). Mean HR increase during CVHR was similar in the first 3 recording but declined on the last (p<0.02). CVHR duration increased, but CHS1 vs. CHS2 and SHHS1 vs. SHHS2 were NS (rest, p<0.007). We conclude that CVHR is frequent at night in older adults, but results suggest an age-related trend towards decreased magnitude and longer durations of HR arousals, possibly due to the aging of the autonomic nervous system.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127839392","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745407
V. Monasterio, J.P. Martinez
Several methods have been proposed to automatically detect and estimate T-wave alternans (TWA) in the ECG, all of them operating on a single-lead basis. In this study a multilead detection scheme is proposed. It combines principal component analysis with the Laplacian likelihood ratio method to improve the detection results. A simulation is carried out to evaluate the effect of different types of simulated and physiological noise, and to assess the performance of this detection scheme. According to simulation results, the proposed multilead approach can detect alternans with a SNR 30 dB lower than the single-lead approach, showing a remarkable improvement of the sensitivity to low-level alternans.
{"title":"A multilead approach to T-wave alternans detection combining principal component analysis and the Laplacian likelihood ratio method","authors":"V. Monasterio, J.P. Martinez","doi":"10.1109/CIC.2007.4745407","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745407","url":null,"abstract":"Several methods have been proposed to automatically detect and estimate T-wave alternans (TWA) in the ECG, all of them operating on a single-lead basis. In this study a multilead detection scheme is proposed. It combines principal component analysis with the Laplacian likelihood ratio method to improve the detection results. A simulation is carried out to evaluate the effect of different types of simulated and physiological noise, and to assess the performance of this detection scheme. According to simulation results, the proposed multilead approach can detect alternans with a SNR 30 dB lower than the single-lead approach, showing a remarkable improvement of the sensitivity to low-level alternans.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127623722","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745499
S. Sayeram, D. Lalush
The purpose of this study is to evaluate 4D reconstruction methods for the processing of gated cardiac single photon emission computed tomography (SPECT) images from obese patients. Clinical gated SPECT projection data were reconstructed using the ordered-sub sets expectation- maximization (OS-EM) and the 4D reseated block- iterative maximum a posteriori (RBI-MAP) reconstruction algorithms. The data were used to derive a relative distribution of quantitative tetrofosmin uptake ratios for the various organs. Using anthropometric data, body sizes were determined for a standard obese male and female NURBS-based cardiac torso (NCAT) phantom. Tetrofosmin uptake ratios were modeled in the obese phantoms and projection data were generated. Poisson noise was simulated, and the noisy data were reconstructed with OS-EM and 4D RBI-MAP. The projected and reconstructed data from the obese phantoms make for a realistic model of tetrofosmin uptake distribution. Qualitatively, 4D processing methods substantially improve visualization of cardiac motion in these very noisy images. We conclude that the tetrofosmin patient models provide a realistic, controllable test vehicle on which to evaluate 4D processing methods for gated cardiac SPECT. 4D processing methods improve the quality of gated SPECT images in obese patients, providing a usable representation of cardiac motion in these difficult-to-image patients.
{"title":"Performance evaluation of 4D reconstruction methods for gated cardiac single photon emission computed tomography in obese patients","authors":"S. Sayeram, D. Lalush","doi":"10.1109/CIC.2007.4745499","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745499","url":null,"abstract":"The purpose of this study is to evaluate 4D reconstruction methods for the processing of gated cardiac single photon emission computed tomography (SPECT) images from obese patients. Clinical gated SPECT projection data were reconstructed using the ordered-sub sets expectation- maximization (OS-EM) and the 4D reseated block- iterative maximum a posteriori (RBI-MAP) reconstruction algorithms. The data were used to derive a relative distribution of quantitative tetrofosmin uptake ratios for the various organs. Using anthropometric data, body sizes were determined for a standard obese male and female NURBS-based cardiac torso (NCAT) phantom. Tetrofosmin uptake ratios were modeled in the obese phantoms and projection data were generated. Poisson noise was simulated, and the noisy data were reconstructed with OS-EM and 4D RBI-MAP. The projected and reconstructed data from the obese phantoms make for a realistic model of tetrofosmin uptake distribution. Qualitatively, 4D processing methods substantially improve visualization of cardiac motion in these very noisy images. We conclude that the tetrofosmin patient models provide a realistic, controllable test vehicle on which to evaluate 4D processing methods for gated cardiac SPECT. 4D processing methods improve the quality of gated SPECT images in obese patients, providing a usable representation of cardiac motion in these difficult-to-image patients.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132490026","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745478
M. Svendsen, T. Oostendorp, E. Berbari
Auto-regressive modeling procedures (AR) have been used to quantify low magnitude components of abnormal activation within the QRS complex, called abnormal intra-QRS potentials (AIQPs). Research is still needed to identify the range in which the AR model can detect AIQP sources in different locations in the heart. A ventricular source model and forward model of electrocardiography called ECGSIM was used to test the ability of the AR model in detecting delays at various locations in the ventricles. A high resolution ECGSIM heart model was created to provide greater temporal and spatial control of the AIQP sources. The overall optimal model orders in this study were at an intermediate range seen previously in the literature. The ability of the AR model to detect the AIQP sources was dependent on the resolution of the heart model and the size and location of the AIQP sources.
{"title":"Evaluation of auto-regressive modeling procedures for the detection of abnormal intra-QRS potentials using a boundary element electrocardiogram model","authors":"M. Svendsen, T. Oostendorp, E. Berbari","doi":"10.1109/CIC.2007.4745478","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745478","url":null,"abstract":"Auto-regressive modeling procedures (AR) have been used to quantify low magnitude components of abnormal activation within the QRS complex, called abnormal intra-QRS potentials (AIQPs). Research is still needed to identify the range in which the AR model can detect AIQP sources in different locations in the heart. A ventricular source model and forward model of electrocardiography called ECGSIM was used to test the ability of the AR model in detecting delays at various locations in the ventricles. A high resolution ECGSIM heart model was created to provide greater temporal and spatial control of the AIQP sources. The overall optimal model orders in this study were at an intermediate range seen previously in the literature. The ability of the AR model to detect the AIQP sources was dependent on the resolution of the heart model and the size and location of the AIQP sources.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132695029","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745588
E. Pueyo, E. Laciar, E. Anzuola, P. Laguna, R. Jané
In this study the slopes of the QRS complex are evaluated for determination of the degree of myocardial damage in chronic chagasic patients. Previous studies have demonstrated the ability of the slope indices to reflect alterations in the conduction velocity of the cardiac impulse. Results obtained in the present study show that chronic chagasic patients have significantly flatter QRS slopes as compared to healthy subjects. Not only that but the extent of slope lessening turns out to be proportional to the degree of myocardial damage caused by the disease. Additionally, when incorporating the slope indices into a classification analysis together with other indices indicative of the presence of ventricular late potentials obtained from high resolution electrocardiography, results show that the percentages of correct classification increase up to 62.5%, which means eight points above the percentages obtained prior to incorporation of the slope indices. It can be concluded that QRS slopes have great potential for assessing the degree of severity associated with Chagaspsila disease.
{"title":"Assessment of myocardial damage in chronic chagasic patients using QRS slopes","authors":"E. Pueyo, E. Laciar, E. Anzuola, P. Laguna, R. Jané","doi":"10.1109/CIC.2007.4745588","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745588","url":null,"abstract":"In this study the slopes of the QRS complex are evaluated for determination of the degree of myocardial damage in chronic chagasic patients. Previous studies have demonstrated the ability of the slope indices to reflect alterations in the conduction velocity of the cardiac impulse. Results obtained in the present study show that chronic chagasic patients have significantly flatter QRS slopes as compared to healthy subjects. Not only that but the extent of slope lessening turns out to be proportional to the degree of myocardial damage caused by the disease. Additionally, when incorporating the slope indices into a classification analysis together with other indices indicative of the presence of ventricular late potentials obtained from high resolution electrocardiography, results show that the percentages of correct classification increase up to 62.5%, which means eight points above the percentages obtained prior to incorporation of the slope indices. It can be concluded that QRS slopes have great potential for assessing the degree of severity associated with Chagaspsila disease.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132910858","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745449
D. Farina, O. Dossel
A model-based approach to noninvasively determine the location and size of the infarction scar is proposed, that in addition helps to estimate the risk of arrhythmias. The approach is based on the optimization of an electrophysiological heart model with an introduced infarction scar to fit the multichannel ECG measured on the surface of the patient's thorax. This model delivers the distributions of transmembrane voltages (TMV) within the ventricles during a single heart cycle. The forward problem of electrocardiography is solved in order to obtain the simulated ECG of the patient. This ECG is compared with the measured one, the difference is used as the criterion for optimization of model parameters, which include the site and size of infarction scar.
{"title":"Model-based approach to the localization of infarction","authors":"D. Farina, O. Dossel","doi":"10.1109/CIC.2007.4745449","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745449","url":null,"abstract":"A model-based approach to noninvasively determine the location and size of the infarction scar is proposed, that in addition helps to estimate the risk of arrhythmias. The approach is based on the optimization of an electrophysiological heart model with an introduced infarction scar to fit the multichannel ECG measured on the surface of the patient's thorax. This model delivers the distributions of transmembrane voltages (TMV) within the ventricles during a single heart cycle. The forward problem of electrocardiography is solved in order to obtain the simulated ECG of the patient. This ECG is compared with the measured one, the difference is used as the criterion for optimization of model parameters, which include the site and size of infarction scar.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131663243","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745531
R. Alcaraz, J. J. Rieta
Recently, it has been suggested that many episodes of atrial fibrillation (AF) may be partially organized at the onset. Moreover, several clinical studies have demonstrated that an AF organization increase occurs prior to its spontaneous termination (paroxysmal AF), which could be used to predict the paroxysmal AF termination. However, although severals AF organization estimators based on invasive and non-invasive analysis have been proposed, the time course of organization in the first and last minutes of AF has not been quantified yet. Thereby, the aim of this work was to study the organization variations within the first and last minutes of paroxysmal AF episodes from surface ECG recordings making use of sample entropy. An organization decrease in the first minutes after AF onset and an increase within the last minute before spontaneous AF termination were obtained, these results were coincident with the conclusions presented in previous clinical works. Thus, it can be concluded that paroxysmal AF organization variations can be assessed from surface recordings without the need of invasive measurements.
{"title":"Organization deterioration assessment from the surface ECG in the onset and termination of paroxysmal atrial fibrillation","authors":"R. Alcaraz, J. J. Rieta","doi":"10.1109/CIC.2007.4745531","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745531","url":null,"abstract":"Recently, it has been suggested that many episodes of atrial fibrillation (AF) may be partially organized at the onset. Moreover, several clinical studies have demonstrated that an AF organization increase occurs prior to its spontaneous termination (paroxysmal AF), which could be used to predict the paroxysmal AF termination. However, although severals AF organization estimators based on invasive and non-invasive analysis have been proposed, the time course of organization in the first and last minutes of AF has not been quantified yet. Thereby, the aim of this work was to study the organization variations within the first and last minutes of paroxysmal AF episodes from surface ECG recordings making use of sample entropy. An organization decrease in the first minutes after AF onset and an increase within the last minute before spontaneous AF termination were obtained, these results were coincident with the conclusions presented in previous clinical works. Thus, it can be concluded that paroxysmal AF organization variations can be assessed from surface recordings without the need of invasive measurements.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131671797","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745435
I. Legarreta, S. Bauer, R. W. dos Santos, H. Koch, M. Bar
Time-resolved surface activation time maps recorded from isolated rabbit hearts were analyzed in order to compare them with analogue maps generated by a computer model. Recordings were obtained under normal conditions as well as after the administration of ajmaline. In parallel, the measured quantities were simulated in a realistic computer model of the rabbit heart. The effect of ajmaline was reproduced by reducing the conductivity of sodium channels GNa in the model. It was observed that addition of a given amount of ajmaline leads to an increase of the QRS time of up to 33% and a decrease of typical velocities by 20-40% with respect to the normal conditions. The velocity speeds obtained display large variations. A velocity decrease of about 20% was reproduced in the computer model by a reduction of the parameter GNa by 60%. Such a change in the model induces a corresponding QRS time by 20%.
{"title":"Spatial properties and effects of ajmaline for epicardial propagation on isolated rabbit hearts: Measurements and a computer study","authors":"I. Legarreta, S. Bauer, R. W. dos Santos, H. Koch, M. Bar","doi":"10.1109/CIC.2007.4745435","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745435","url":null,"abstract":"Time-resolved surface activation time maps recorded from isolated rabbit hearts were analyzed in order to compare them with analogue maps generated by a computer model. Recordings were obtained under normal conditions as well as after the administration of ajmaline. In parallel, the measured quantities were simulated in a realistic computer model of the rabbit heart. The effect of ajmaline was reproduced by reducing the conductivity of sodium channels GNa in the model. It was observed that addition of a given amount of ajmaline leads to an increase of the QRS time of up to 33% and a decrease of typical velocities by 20-40% with respect to the normal conditions. The velocity speeds obtained display large variations. A velocity decrease of about 20% was reproduced in the computer model by a reduction of the parameter GNa by 60%. Such a change in the model induces a corresponding QRS time by 20%.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"312 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122967529","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 : 2007-09-01DOI: 10.1109/CIC.2007.4745609
T.G. Zimmerman, T. Syeda-Mahmood
A statistical means to automatically detect heart disease from twelve channel ECG waveforms is reported. Patient ECG records from the PTB Diagnostic ECG Database are assigned to one or more of 18 heart disease groups. A single heart beat cycle near the beginning of the record is used to measure eight temporal intervals (e.g. QT, ST, PR, QS) for each of the twelve channels, resulting in 96 parameters for each patient record. The average and standard deviation of the 96 parameters for 63 non-disease patients are used as a control reference. The number of parameters that exceed two times the standard deviation of the control reference is used as a disease indicator. Using ten or more out-of-bound parameters as the disease criteria, 72% of disease patient records are correctly identified while 8% of control patient records are falsely identified as having a heart disease.
{"title":"Automatic detection of heart disease from twelve channel electrocardiogram waveforms","authors":"T.G. Zimmerman, T. Syeda-Mahmood","doi":"10.1109/CIC.2007.4745609","DOIUrl":"https://doi.org/10.1109/CIC.2007.4745609","url":null,"abstract":"A statistical means to automatically detect heart disease from twelve channel ECG waveforms is reported. Patient ECG records from the PTB Diagnostic ECG Database are assigned to one or more of 18 heart disease groups. A single heart beat cycle near the beginning of the record is used to measure eight temporal intervals (e.g. QT, ST, PR, QS) for each of the twelve channels, resulting in 96 parameters for each patient record. The average and standard deviation of the 96 parameters for 63 non-disease patients are used as a control reference. The number of parameters that exceed two times the standard deviation of the control reference is used as a disease indicator. Using ten or more out-of-bound parameters as the disease criteria, 72% of disease patient records are correctly identified while 8% of control patient records are falsely identified as having a heart disease.","PeriodicalId":406683,"journal":{"name":"2007 Computers in Cardiology","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121424203","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：