Pub Date : 2002-12-01DOI: 10.1109/CIC.2002.1166869
B. Hoffmeister, J. Sexton, B.S. Sheals, A. de Jongh, R. Malkin
Medical equipment can unintentionally allow the flow of small amounts of AC current through the patient causing hemodynamic collapse without fibrillation. This study examines the mechanical response of the left ventricle during AC induced hemodynamic collapse. Six dogs received 5 seconds of AC current stimulation ranging from 4-160 Hz and 10-1000 /spl mu/A to the right ventricle. A quadripolar catheter was placed in the apex of the left ventricle to measure left ventricular volume. Short-axis ultrasound images were recorded to measure left ventricular cross sectional area and wall thickness. Our results showed that the mean volume of the left ventricle during collapse was significantly smaller (p < 0.05) than the mean volume preceding collapse. Cross sectional area also decreased significantly and wall thickness increased. This suggests that the heart assumes a contracted, systole-like state during collapse.
{"title":"Mechanical response of the left ventricle during AC induced hemodynamic collapse","authors":"B. Hoffmeister, J. Sexton, B.S. Sheals, A. de Jongh, R. Malkin","doi":"10.1109/CIC.2002.1166869","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166869","url":null,"abstract":"Medical equipment can unintentionally allow the flow of small amounts of AC current through the patient causing hemodynamic collapse without fibrillation. This study examines the mechanical response of the left ventricle during AC induced hemodynamic collapse. Six dogs received 5 seconds of AC current stimulation ranging from 4-160 Hz and 10-1000 /spl mu/A to the right ventricle. A quadripolar catheter was placed in the apex of the left ventricle to measure left ventricular volume. Short-axis ultrasound images were recorded to measure left ventricular cross sectional area and wall thickness. Our results showed that the mean volume of the left ventricle during collapse was significantly smaller (p < 0.05) than the mean volume preceding collapse. Cross sectional area also decreased significantly and wall thickness increased. This suggests that the heart assumes a contracted, systole-like state during collapse.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"1 1","pages":"701-703"},"PeriodicalIF":0.0,"publicationDate":"2002-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166869","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62182613","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 : 2002-12-01DOI: 10.1109/CIC.2002.1166841
J. Couderc, A. Elder, C. Cox, W. Zareba, G. Oberdorster
A radio-telemetry technique used to record electrophysiological signals in animals is broadly used in experimental studies. Using implantable probes, this technique can record electrocardiographic (ECG) signals without disturbing animal activities. In this study, we investigated the stability of heart rate variability (HRV) parameters computed from radio-telemetry ECG recordings in unrestrained rats. The experiment involved 4 normal rats in which ECGs were recorded during baseline conditions with and without drug-induced autonomic blockade. The study revealed that the stability of HRV estimators for both time and frequency domain analysis in unrestrained rats was highly dependent on the average heart rate (related to physical rats activity) as well as the length of the ECG recording.
{"title":"Limitations of power-spectrum and time-domain analysis of heart rate variability in short-term ECG recorded using telemetry in unrestrained rats","authors":"J. Couderc, A. Elder, C. Cox, W. Zareba, G. Oberdorster","doi":"10.1109/CIC.2002.1166841","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166841","url":null,"abstract":"A radio-telemetry technique used to record electrophysiological signals in animals is broadly used in experimental studies. Using implantable probes, this technique can record electrocardiographic (ECG) signals without disturbing animal activities. In this study, we investigated the stability of heart rate variability (HRV) parameters computed from radio-telemetry ECG recordings in unrestrained rats. The experiment involved 4 normal rats in which ECGs were recorded during baseline conditions with and without drug-induced autonomic blockade. The study revealed that the stability of HRV estimators for both time and frequency domain analysis in unrestrained rats was highly dependent on the average heart rate (related to physical rats activity) as well as the length of the ECG recording.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"1 1","pages":"589-592"},"PeriodicalIF":0.0,"publicationDate":"2002-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166841","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62181816","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 : 2002-12-01DOI: 10.1109/CIC.2002.1166872
M. Firstenberg, G. Armstrong, N. Greenberg, M.J. Garcia, J.D. Thomas
Peak instantaneous power is a prognostic index of LV function but is difficult to measure. It is relatively load independent when corrected by preload (EDV/sup 2/). Easier to acquire power estimates have been proposed ncluding mean and simplified power. These require only echo Doppler flow and cuff pressures, but their relationship to invasively derived results has not been studied. Using a well-validated numerical model of the cardiovascular system, different estimates of power were compared for varying preload, afterload, and contractility. All power results were divided by EDV/sup 2/. Estimates of power correlate with peak power over a wide range of physiology. Corrected power estimates were independent of preload and afterload, but predictably increased with contractility. Different estimates of preload corrected power can be derived from non-invasively obtained variables and correlate with corrected peak instantaneous power.
{"title":"Different estimates of cardiac power: relationship to altered loading conditions","authors":"M. Firstenberg, G. Armstrong, N. Greenberg, M.J. Garcia, J.D. Thomas","doi":"10.1109/CIC.2002.1166872","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166872","url":null,"abstract":"Peak instantaneous power is a prognostic index of LV function but is difficult to measure. It is relatively load independent when corrected by preload (EDV/sup 2/). Easier to acquire power estimates have been proposed ncluding mean and simplified power. These require only echo Doppler flow and cuff pressures, but their relationship to invasively derived results has not been studied. Using a well-validated numerical model of the cardiovascular system, different estimates of power were compared for varying preload, afterload, and contractility. All power results were divided by EDV/sup 2/. Estimates of power correlate with peak power over a wide range of physiology. Corrected power estimates were independent of preload and afterload, but predictably increased with contractility. Different estimates of preload corrected power can be derived from non-invasively obtained variables and correlate with corrected peak instantaneous power.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"1 1","pages":"713-716"},"PeriodicalIF":0.0,"publicationDate":"2002-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166872","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62182669","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 : 2002-09-22DOI: 10.1109/CIC.2002.1166723
G. Moody
Cardiac inter-beat (RR) interval time series contain fluctuations at time scales ranging from a few seconds to many hours. Realistic models of these series are potentially useful to researchers, not only as sources of surrogate data with known properties for evaluating novel analytic methods, but also as sources of insight into the diverse mechanisms underlying heart rate variability. PhysioNet and Computers in Cardiology have sponsored an open on-line competition aimed at stimulating the creation and exchange of high-quality models of RR interval variability, the third in an annual series of challenges for the research community. Participants first created software that was used to generate 24-hour synthetic time series, then attempted to identify the synthetic series within an unlabeled data set that included roughly equal amounts of real and synthetic data. All of the software models and the data used in the challenge are available at http://www.physionet.org/challenge/2002/.
心脏搏动间隔时间序列包含从几秒到数小时不等的时间尺度波动。这些系列的现实模型对研究人员可能有用，不仅作为评估新分析方法的已知属性的替代数据的来源，而且作为洞察心率变异性的各种机制的来源。PhysioNet和Computers in Cardiology赞助了一项开放的在线竞赛，旨在促进RR间隔变异性高质量模型的创建和交流，这是研究界年度系列挑战中的第三项。参与者首先创建了用于生成24小时合成时间序列的软件，然后试图在包含大致相等数量的真实数据和合成数据的未标记数据集中识别合成序列。挑战中使用的所有软件模型和数据都可以在http://www.physionet.org/challenge/2002/上获得。
{"title":"RR interval time series modeling: the PhysioNet/Computers in Cardiology Challenge 2002","authors":"G. Moody","doi":"10.1109/CIC.2002.1166723","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166723","url":null,"abstract":"Cardiac inter-beat (RR) interval time series contain fluctuations at time scales ranging from a few seconds to many hours. Realistic models of these series are potentially useful to researchers, not only as sources of surrogate data with known properties for evaluating novel analytic methods, but also as sources of insight into the diverse mechanisms underlying heart rate variability. PhysioNet and Computers in Cardiology have sponsored an open on-line competition aimed at stimulating the creation and exchange of high-quality models of RR interval variability, the third in an annual series of challenges for the research community. Participants first created software that was used to generate 24-hour synthetic time series, then attempted to identify the synthetic series within an unlabeled data set that included roughly equal amounts of real and synthetic data. All of the software models and the data used in the challenge are available at http://www.physionet.org/challenge/2002/.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"1 1","pages":"125-128"},"PeriodicalIF":0.0,"publicationDate":"2002-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166723","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62180052","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 : 2002-09-22DOI: 10.1109/CIC.2002.1166715
A. Hemdndez, G. Carrault, F. Mora
This work presents current progress of a new system for cardiac beat interpretation, combining model-based reasoning and evolutionary computing. As a difference from other model-based systems, the proposed approach directly integrates ECG signals with a cardiac model. Model-based reasoning is formalized as the minimization of an error function defined between the observation and the model's output. This paper presents a new adaptation process permitting the reproduction of a sequence of cardiac beats and the generation of beat interpretations by means of ladder diagrams. Results show the application of the proposed approach to two pathological rhythms from the MIT-BIH arrhythmia database. Although some limitations persist, preliminary results are encouraging and show the potentiality of this approach to exploit anatomic and physiological knowledge in order to explain underlying conduction disorders.
{"title":"Model-based interpretation of cardiac beats by evolutionary algorithms","authors":"A. Hemdndez, G. Carrault, F. Mora","doi":"10.1109/CIC.2002.1166715","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166715","url":null,"abstract":"This work presents current progress of a new system for cardiac beat interpretation, combining model-based reasoning and evolutionary computing. As a difference from other model-based systems, the proposed approach directly integrates ECG signals with a cardiac model. Model-based reasoning is formalized as the minimization of an error function defined between the observation and the model's output. This paper presents a new adaptation process permitting the reproduction of a sequence of cardiac beats and the generation of beat interpretations by means of ladder diagrams. Results show the application of the proposed approach to two pathological rhythms from the MIT-BIH arrhythmia database. Although some limitations persist, preliminary results are encouraging and show the potentiality of this approach to exploit anatomic and physiological knowledge in order to explain underlying conduction disorders.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"1 1","pages":"93-96"},"PeriodicalIF":0.0,"publicationDate":"2002-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166715","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62180240","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 : 2002-09-22DOI: 10.1109/CIC.2002.1166746
Brian Hickey, Conor Heneghan
We present a technique for screening for imminent onset of paroxysmal atrial fibrillation (PAF) through automated assessment of 30-minute segments of electrocardiogram (ECG), which do not contain any episodes of atrial fibrillation. Algorithmic development was carried out using a training database of 75 half-hour records drawn from two subject groups. Subjects in the first group provided segments with PAF in the five minutes after the 30-minute recording; the second group do not have PAF (control subjects or subjects with non-PAF cardiac pathology). To differentiate between pre-PAF segments and non-PAF segments a linear discriminant classifier was developed, using the number of Atrial Premature Contractions (APCs) and two spectral measures as features. An independent test set of 72 recordings (28 pre-PAF and 44 non-PAF) was then classified, with an accuracy of 75% (sensitivity 79%, specificity 72%). When tested against a second database of subjects with no known cardiac pathology, the specificity rose to 95%.
{"title":"Screening for paroxysmal atrial fibrillation using atrial premature contractions and spectral measures","authors":"Brian Hickey, Conor Heneghan","doi":"10.1109/CIC.2002.1166746","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166746","url":null,"abstract":"We present a technique for screening for imminent onset of paroxysmal atrial fibrillation (PAF) through automated assessment of 30-minute segments of electrocardiogram (ECG), which do not contain any episodes of atrial fibrillation. Algorithmic development was carried out using a training database of 75 half-hour records drawn from two subject groups. Subjects in the first group provided segments with PAF in the five minutes after the 30-minute recording; the second group do not have PAF (control subjects or subjects with non-PAF cardiac pathology). To differentiate between pre-PAF segments and non-PAF segments a linear discriminant classifier was developed, using the number of Atrial Premature Contractions (APCs) and two spectral measures as features. An independent test set of 72 recordings (28 pre-PAF and 44 non-PAF) was then classified, with an accuracy of 75% (sensitivity 79%, specificity 72%). When tested against a second database of subjects with no known cardiac pathology, the specificity rose to 95%.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"1 1","pages":"217-220"},"PeriodicalIF":0.0,"publicationDate":"2002-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166746","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62180338","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 : 2002-09-22DOI: 10.1109/CIC.2002.1166762
N. Bruining, B. Hendriks, L. Boelhouwer, S. de Winter, M. Patijn, R. Hamers, N. van der Putten, J. Roelandt
Telemedicine (more specific TeleCardiology), including teleteaching and teleguidance, is a rapidly growing area in cardiology. The availability of hand-held network ready ultrasound equipment is one of the accelerators for furthers developments. A pilot project for both teleteaching and -guiding was started in our institution. For teleteaching the requirements were not too strict, e.g. no real-time interaction with the remote site necessary and some loss in image quality was allowed. For teleguidance however, near real-time transmission of images with no loss in diagnostic quality was demanded For both teleprojects solutions were found and/or developed with complete satisfactory to the clinical demands.
{"title":"Teleteaching and teleguiding using an intranetwork: A feasibility study","authors":"N. Bruining, B. Hendriks, L. Boelhouwer, S. de Winter, M. Patijn, R. Hamers, N. van der Putten, J. Roelandt","doi":"10.1109/CIC.2002.1166762","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166762","url":null,"abstract":"Telemedicine (more specific TeleCardiology), including teleteaching and teleguidance, is a rapidly growing area in cardiology. The availability of hand-held network ready ultrasound equipment is one of the accelerators for furthers developments. A pilot project for both teleteaching and -guiding was started in our institution. For teleteaching the requirements were not too strict, e.g. no real-time interaction with the remote site necessary and some loss in image quality was allowed. For teleguidance however, near real-time transmission of images with no loss in diagnostic quality was demanded For both teleprojects solutions were found and/or developed with complete satisfactory to the clinical demands.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"122 1","pages":"277-280"},"PeriodicalIF":0.0,"publicationDate":"2002-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166762","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62180365","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 : 2002-09-22DOI: 10.1109/CIC.2002.1166753
C. Vásquez, R. A. Siddiqui, A. Moreno, E. Berbari
Biophysical mechanisms behind the fractionated character of cardiac electrograms from infarct border zones have not been clearly identified. The working hypothesis of this study is that fibroblasts in the scar tissue are electrically coupled to myocytes via gap junctions, acting as RC connections between healthy cardiac cells. This study examined the physical characteristics of cultured fibroblasts and calculated an average surface area of 74.4 E-5 cm/sup 2/. Using reported gap junction conductance for myocyte-fibroblast-myocyte triplets, typical myoplasmic resistivity, and specific capacitance yields a total RC time constant in the range of 35-40 ms. This would cause major delays in propagation between two healthy myocytes conjoined by a fibroblast, and could explain phenomena such as micro-reentry and the fractionated electrogram.
从梗死边界区分离心脏电图特征背后的生物物理机制尚未明确确定。本研究的工作假设是疤痕组织中的成纤维细胞通过间隙连接与肌细胞电偶联，作为健康心脏细胞之间的RC连接。本研究检测了培养成纤维细胞的物理特性，计算出平均表面积为74.4 e - 5cm /sup 2/。利用已报道的肌细胞-成纤维细胞-肌细胞三联体的间隙结电导、典型肌浆电阻率和比电容可得出总RC时间常数在35-40 ms范围内。这将导致由成纤维细胞连接的两个健康肌细胞之间繁殖的严重延迟，并且可以解释诸如微再入和分次电图等现象。
{"title":"A fibroblast-myocyte model which accounts for slow conduction and fractionated electrograms in infarct border zones","authors":"C. Vásquez, R. A. Siddiqui, A. Moreno, E. Berbari","doi":"10.1109/CIC.2002.1166753","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166753","url":null,"abstract":"Biophysical mechanisms behind the fractionated character of cardiac electrograms from infarct border zones have not been clearly identified. The working hypothesis of this study is that fibroblasts in the scar tissue are electrically coupled to myocytes via gap junctions, acting as RC connections between healthy cardiac cells. This study examined the physical characteristics of cultured fibroblasts and calculated an average surface area of 74.4 E-5 cm/sup 2/. Using reported gap junction conductance for myocyte-fibroblast-myocyte triplets, typical myoplasmic resistivity, and specific capacitance yields a total RC time constant in the range of 35-40 ms. This would cause major delays in propagation between two healthy myocytes conjoined by a fibroblast, and could explain phenomena such as micro-reentry and the fractionated electrogram.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"55 1","pages":"245-248"},"PeriodicalIF":0.0,"publicationDate":"2002-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166753","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62180612","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 : 2002-09-22DOI: 10.1109/CIC.2002.1166789
M.A. Morales, S. Dalmiani, C. Carpeggiani, A. Macerata, S. Ghione
In an outpatient clinic, a huge amount of information, administrative, clinical and instrumental, has to be handled every day for patient care. A computerized method has been developed in our Institute that is able to track the patient from administrative admission up to discharge. For the purpose of obtaining electronic medical records in the patient who undergoes clinical and instrumental examinations, even on the same day, each clinical laboratory is provided by networked computers and results from instrumental data can be obtained on-line. The system is based on a relational database with clinical and administrative information and is integrated with a large hospital information system where the system covers the role of a functional island. Use of Java language, with its multiplatform capabilities, allows extensive installation in the clinical environment and full integration with other subsystems. A protected Web front-end allows remote consultation of data. For follow up purposes, all the data collected from 1999 to the present day during hospital admission of in- or out-patients can be collected, retrieved and updated. At present 4600 cardiological outpatients have been treated by this system with substantial clinical achievements, time saving, and better follow up organization.
{"title":"Electronic medical records in a cardiological outpatient clinic","authors":"M.A. Morales, S. Dalmiani, C. Carpeggiani, A. Macerata, S. Ghione","doi":"10.1109/CIC.2002.1166789","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166789","url":null,"abstract":"In an outpatient clinic, a huge amount of information, administrative, clinical and instrumental, has to be handled every day for patient care. A computerized method has been developed in our Institute that is able to track the patient from administrative admission up to discharge. For the purpose of obtaining electronic medical records in the patient who undergoes clinical and instrumental examinations, even on the same day, each clinical laboratory is provided by networked computers and results from instrumental data can be obtained on-line. The system is based on a relational database with clinical and administrative information and is integrated with a large hospital information system where the system covers the role of a functional island. Use of Java language, with its multiplatform capabilities, allows extensive installation in the clinical environment and full integration with other subsystems. A protected Web front-end allows remote consultation of data. For follow up purposes, all the data collected from 1999 to the present day during hospital admission of in- or out-patients can be collected, retrieved and updated. At present 4600 cardiological outpatients have been treated by this system with substantial clinical achievements, time saving, and better follow up organization.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"1 1","pages":"381-384"},"PeriodicalIF":0.0,"publicationDate":"2002-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166789","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62180980","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 : 2002-09-22DOI: 10.1109/CIC.2002.1166814
K. Lynn, H. Chiang
We develop a hybrid two-stage approach for paroxysmal atrial fibrillation (PAF) prognosis based on features extracted from short-term heart rate variability (HRV) sequences. At the first stage, a data-mining-based approach is used to identify crucial medical-oriented features that can distinguish PAF HRV sequences from non-PAF HRV ones. However, PAF patients can experience PAF without exhibiting the medical-oriented features. To detect this type of patients, at the second stage, we employ a machine-learning-based approach to select certain nonlinear features that can classify HRV sequences into classes of PAF or non-PAF The developed approach was trained on the PAF Prediction Challenge Database and was tested on the dataset consisting of minute HRV episodes extracted from MIT-BIH Atrial Fibrillation Database and the MIT-BIH Normal Sinus Rhythm Database. It was obtained from the numerical evaluation that the developed approach achieved about 85% of accuracy in short-term prognosis of PAF by using the first stage approach alone and around 90% of accuracy with the combination of both stages. Furthermore, the developed medical-oriented features can be clinically valuable to the cardiologists for providing insights to the initiation of PAF.
{"title":"A hybrid two-stage approach for paroxysmal atrial fibrillation prognosis problem","authors":"K. Lynn, H. Chiang","doi":"10.1109/CIC.2002.1166814","DOIUrl":"https://doi.org/10.1109/CIC.2002.1166814","url":null,"abstract":"We develop a hybrid two-stage approach for paroxysmal atrial fibrillation (PAF) prognosis based on features extracted from short-term heart rate variability (HRV) sequences. At the first stage, a data-mining-based approach is used to identify crucial medical-oriented features that can distinguish PAF HRV sequences from non-PAF HRV ones. However, PAF patients can experience PAF without exhibiting the medical-oriented features. To detect this type of patients, at the second stage, we employ a machine-learning-based approach to select certain nonlinear features that can classify HRV sequences into classes of PAF or non-PAF The developed approach was trained on the PAF Prediction Challenge Database and was tested on the dataset consisting of minute HRV episodes extracted from MIT-BIH Atrial Fibrillation Database and the MIT-BIH Normal Sinus Rhythm Database. It was obtained from the numerical evaluation that the developed approach achieved about 85% of accuracy in short-term prognosis of PAF by using the first stage approach alone and around 90% of accuracy with the combination of both stages. Furthermore, the developed medical-oriented features can be clinically valuable to the cardiologists for providing insights to the initiation of PAF.","PeriodicalId":80984,"journal":{"name":"Computers in cardiology","volume":"1 1","pages":"481-484"},"PeriodicalIF":0.0,"publicationDate":"2002-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CIC.2002.1166814","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62181365","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：