151
|
Ensemble Deep Learning for Biomedical Time Series Classification. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2016; 2016:6212684. [PMID: 27725828 PMCID: PMC5048093 DOI: 10.1155/2016/6212684] [Citation(s) in RCA: 30] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/12/2016] [Revised: 04/10/2016] [Accepted: 05/04/2016] [Indexed: 11/23/2022]
Abstract
Ensemble learning has been proved to improve the generalization ability effectively in both theory and practice. In this paper, we briefly outline the current status of research on it first. Then, a new deep neural network-based ensemble method that integrates filtering views, local views, distorted views, explicit training, implicit training, subview prediction, and Simple Average is proposed for biomedical time series classification. Finally, we validate its effectiveness on the Chinese Cardiovascular Disease Database containing a large number of electrocardiogram recordings. The experimental results show that the proposed method has certain advantages compared to some well-known ensemble methods, such as Bagging and AdaBoost.
Collapse
|
152
|
Park J, Kang M, Hur J, Kang K. Recommendations for antiarrhythmic drugs based on latent semantic analysis with fc-means clustering. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2016; 2016:4423-4426. [PMID: 28269259 DOI: 10.1109/embc.2016.7591708] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
In this paper, we propose a novel model for the appropriate recommendation of antiarrhythmic drugs by introducing a fusion of a latent semantic analysis and k-means clustering. Our model not only captures the latent factors between the types of arrhythmia and patients but also has the ability to search a group of patients with similar arrhythmias. The performance studies conducted against the MIT-BIH arrhythmia database show that clinicians accepted 66.67% of the drugs recommended from our model with a balanced f-score of 38.08%. Comparative study with previous approach also confirms the effectiveness of our model.
Collapse
|
153
|
Rahhal MA, Bazi Y, AlHichri H, Alajlan N, Melgani F, Yager R. Deep learning approach for active classification of electrocardiogram signals. Inf Sci (N Y) 2016. [DOI: 10.1016/j.ins.2016.01.082] [Citation(s) in RCA: 378] [Impact Index Per Article: 47.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
154
|
Luz EJDS, Schwartz WR, Cámara-Chávez G, Menotti D. ECG-based heartbeat classification for arrhythmia detection: A survey. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2016; 127:144-64. [PMID: 26775139 DOI: 10.1016/j.cmpb.2015.12.008] [Citation(s) in RCA: 256] [Impact Index Per Article: 32.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/27/2015] [Revised: 11/08/2015] [Accepted: 12/17/2015] [Indexed: 05/20/2023]
Abstract
An electrocardiogram (ECG) measures the electric activity of the heart and has been widely used for detecting heart diseases due to its simplicity and non-invasive nature. By analyzing the electrical signal of each heartbeat, i.e., the combination of action impulse waveforms produced by different specialized cardiac tissues found in the heart, it is possible to detect some of its abnormalities. In the last decades, several works were developed to produce automatic ECG-based heartbeat classification methods. In this work, we survey the current state-of-the-art methods of ECG-based automated abnormalities heartbeat classification by presenting the ECG signal preprocessing, the heartbeat segmentation techniques, the feature description methods and the learning algorithms used. In addition, we describe some of the databases used for evaluation of methods indicated by a well-known standard developed by the Association for the Advancement of Medical Instrumentation (AAMI) and described in ANSI/AAMI EC57:1998/(R)2008 (ANSI/AAMI, 2008). Finally, we discuss limitations and drawbacks of the methods in the literature presenting concluding remarks and future challenges, and also we propose an evaluation process workflow to guide authors in future works.
Collapse
Affiliation(s)
| | - William Robson Schwartz
- Universidade Federal de Minas Gerais, Computer Science Department, Belo Horizonte, MG, Brazil.
| | | | - David Menotti
- Universidade Federal de Ouro Preto, Computing Department, Ouro Preto, MG, Brazil; Universidade Federal do Paraná, Department of Informatics, Curitiba, PR, Brazil.
| |
Collapse
|
155
|
Li P, Wang Y, He J, Wang L, Tian Y, Zhou TS, Li T, Li JS. High-Performance Personalized Heartbeat Classification Model for Long-Term ECG Signal. IEEE Trans Biomed Eng 2016; 64:78-86. [PMID: 27046844 DOI: 10.1109/tbme.2016.2539421] [Citation(s) in RCA: 29] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Long-term electrocardiogram (ECG) has become one of the important diagnostic assist methods in clinical cardiovascular domain. Long-term ECG is primarily used for the detection of various cardiovascular diseases that are caused by various cardiac arrhythmia such as myocardial infarction, cardiomyopathy, and myocarditis. In the past few years, the development of an automatic heartbeat classification method has been a challenge. With the accumulation of medical data, personalized heartbeat classification of a patient has become possible. For the long-term data accumulation method, such as the holter, it is difficult to obtain the analysis results in a short time using the original method of serial design. The pressure to develop a personalized automatic classification model is high. To solve these challenges, this paper implemented a parallel general regression neural network (GRNN) to classify the heartbeat, and achieved a 95% accuracy according to the Association for the Advancement of Medical Instrumentation. We designed an online learning program to form a personalized classification model for patients. The achieved accuracy of the model is 88% compared to the specific ECG data of the patients. The efficiency of the parallel GRNN with GTX780Ti can improve by 450 times.
Collapse
|
156
|
Ghorbani Afkhami R, Azarnia G, Tinati MA. Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signals. Pattern Recognit Lett 2016. [DOI: 10.1016/j.patrec.2015.11.018] [Citation(s) in RCA: 121] [Impact Index Per Article: 15.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
157
|
Park J, Kang K. HeartSearcher: finds patients with similar arrhythmias based on heartbeat classification. IET Syst Biol 2015; 9:303-308. [PMID: 26577165 PMCID: PMC8687414 DOI: 10.1049/iet-syb.2015.0011] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2015] [Revised: 08/11/2015] [Accepted: 08/27/2015] [Indexed: 11/29/2023] Open
Abstract
Long-term electrocardiogram data can be acquired by linking a Holter monitor to a mobile phone. However, most systems of this variety are simply designed to detect arrhythmia through heartbeat classification, and do not provide any additional support for clinical decisions. HeartSearcher identifies patients with similar arrhythmias from heartbeat classifications, by summarising each patient's typical heartbeat pattern in the form of a regular expression, and then ranking patients according to the similarities of their patterns. Results obtained using electrocardiogram data from the MIT-BIH arrhythmia database show that this abstraction reduces the volume of heartbeat classifications by 98% on average, offering great potential to support clinical decisions.
Collapse
Affiliation(s)
- Juyoung Park
- Department of Computer Science and Engineering, Hanyang University, Ansan, Republic of Korea
| | - Kyungtae Kang
- Department of Computer Science and Engineering, Hanyang University, Ansan, Republic of Korea.
| |
Collapse
|
158
|
Krasteva V, Jekova I, Leber R, Schmid R, Abächerli R. Superiority of Classification Tree versus Cluster, Fuzzy and Discriminant Models in a Heartbeat Classification System. PLoS One 2015; 10:e0140123. [PMID: 26461492 PMCID: PMC4604143 DOI: 10.1371/journal.pone.0140123] [Citation(s) in RCA: 25] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2015] [Accepted: 09/22/2015] [Indexed: 11/18/2022] Open
Abstract
This study presents a 2-stage heartbeat classifier of supraventricular (SVB) and ventricular (VB) beats. Stage 1 makes computationally-efficient classification of SVB-beats, using simple correlation threshold criterion for finding close match with a predominant normal (reference) beat template. The non-matched beats are next subjected to measurement of 20 basic features, tracking the beat and reference template morphology and RR-variability for subsequent refined classification in SVB or VB-class by Stage 2. Four linear classifiers are compared: cluster, fuzzy, linear discriminant analysis (LDA) and classification tree (CT), all subjected to iterative training for selection of the optimal feature space among extended 210-sized set, embodying interactive second-order effects between 20 independent features. The optimization process minimizes at equal weight the false positives in SVB-class and false negatives in VB-class. The training with European ST-T, AHA, MIT-BIH Supraventricular Arrhythmia databases found the best performance settings of all classification models: Cluster (30 features), Fuzzy (72 features), LDA (142 coefficients), CT (221 decision nodes) with top-3 best scored features: normalized current RR-interval, higher/lower frequency content ratio, beat-to-template correlation. Unbiased test-validation with MIT-BIH Arrhythmia database rates the classifiers in descending order of their specificity for SVB-class: CT (99.9%), LDA (99.6%), Cluster (99.5%), Fuzzy (99.4%); sensitivity for ventricular ectopic beats as part from VB-class (commonly reported in published beat-classification studies): CT (96.7%), Fuzzy (94.4%), LDA (94.2%), Cluster (92.4%); positive predictivity: CT (99.2%), Cluster (93.6%), LDA (93.0%), Fuzzy (92.4%). CT has superior accuracy by 0.3-6.8% points, with the advantage for easy model complexity configuration by pruning the tree consisted of easy interpretable 'if-then' rules.
Collapse
Affiliation(s)
- Vessela Krasteva
- Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria
| | - Irena Jekova
- Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria
| | - Remo Leber
- Biomed Research and Signal Processing, Schiller AG, Baar, Switzerland
| | - Ramun Schmid
- Biomed Research and Signal Processing, Schiller AG, Baar, Switzerland
- Bern University of Applied Sciences, Medical Technology Center, Bern, Switzerland
| | - Roger Abächerli
- Biomed Research and Signal Processing, Schiller AG, Baar, Switzerland
- Bern University of Applied Sciences, Medical Technology Center, Bern, Switzerland
- University Hospital Basel, Cardiovascular Research Institute Basel, Bazel, Switzerland
| |
Collapse
|
159
|
Park J, Lee K, Kang K. Pit-a-Pat: A Smart Electrocardiogram System for Detecting Arrhythmia. Telemed J E Health 2015; 21:814-21. [DOI: 10.1089/tmj.2014.0187] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Affiliation(s)
- Juyoung Park
- Department of Computer Science & Engineering, Hanyang University, Ansan, Republic of Korea
| | - Kuyeon Lee
- Department of Computer Science & Engineering, Hanyang University, Ansan, Republic of Korea
| | - Kyungtae Kang
- Department of Computer Science & Engineering, Hanyang University, Ansan, Republic of Korea
| |
Collapse
|
160
|
Zandi AS, Boudreau P, Boivin DB, Dumont GA. Identification of scalp EEG circadian variation using a novel correlation sum measure. J Neural Eng 2015; 12:056004. [PMID: 26246488 DOI: 10.1088/1741-2560/12/5/056004] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
OBJECTIVE In this paper, we propose a novel method to determine the circadian variation of scalp electroencephalogram (EEG) in both individual and group levels using a correlation sum measure, quantifying self-similarity of the EEG relative energy across waking epochs. APPROACH We analysed EEG recordings from central-parietal and occipito-parietal montages in nine healthy subjects undergoing a 72 h ultradian sleep-wake cycle protocol. Each waking epoch (∼ 1 s) of every nap opportunity was decomposed using the wavelet packet transform, and the relative energy for that epoch was calculated in the desired frequency band using the corresponding wavelet coefficients. Then, the resulting set of energy values was resampled randomly to generate different subsets with equal number of elements. The correlation sum of each subset was then calculated over a range of distance thresholds, and the average over all subsets was computed. This average value was finally scaled for each nap opportunity and considered as a new circadian measure. MAIN RESULTS According to the evaluation results, a clear circadian rhythm was identified in some EEG frequency ranges, particularly in 4-8 Hz and 10-12 Hz. The correlation sum measure not only was able to disclose the circadian rhythm on the group data but also revealed significant circadian variations in most individual cases, as opposed to previous studies only reporting the circadian rhythms on a population of subjects. Compared to a naive measure based on the EEG absolute energy in the frequency band of interest, the proposed measure showed a clear superiority using both individual and group data. Results also suggested that the acrophase (i.e., the peak) of the circadian rhythm in 10-12 Hz occurs close to the core body temperature minimum. SIGNIFICANCE These results confirm the potential usefulness of the proposed EEG-based measure as a non-invasive circadian marker.
Collapse
Affiliation(s)
- Ali Shahidi Zandi
- Centre for Study and Treatment of Circadian Rhythms, Douglas Mental Health University Institute, McGill University, Montreal, QC, H4H 1R3, Canada
| | | | | | | |
Collapse
|
161
|
Balouchestani M, Raahemifar K, Krishnan S. A high reliability detection algorithm for wireless ECG systems based on compressed sensing theory. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2015; 2013:4722-5. [PMID: 24110789 DOI: 10.1109/embc.2013.6610602] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
Wireless Body Area Networks (WBANs) consist of small intelligent biomedical wireless sensors attached on or implanted in the body to collect vital biomedical data from the human body providing Continuous Health Monitoring Systems (CHMS). The WBANs promise to be a key element in wireless electrocardiogram (ECG) systems for next-generation. ECG signals are widely used in health care systems as a noninvasive technique for diagnosis of heart conditions. However, the use of conventional ECG system is restricted by patient's mobility, transmission capacity, and physical size. Aforementioned highlights the need and advantage of wireless ECG systems with low sampling-rate and low power consumption. With this in mind, Compressed Sensing (CS) procedure as a new sampling approach and the collaboration from Shannon Energy Transformation (SET) and Peak Finding Schemes (PFS) is used to provide a robust low-complexity detection algorithm in gateways and access points in the hospitals and medical centers with high probability and enough accuracy. Advanced wireless ECG systems based on our approach will be able to deliver healthcare not only to patients in hospitals and medical centers; but also at their homes and workplaces thus offering cost saving, and improving the quality of life. Our simulation results show an increment of 0.1 % for sensitivity as well as 1.5% for the prediction level and detection accuracy.
Collapse
|
162
|
Merino M, Gómez IM, Molina AJ. Envelopment filter and K-means for the detection of QRS waveforms in electrocardiogram. Med Eng Phys 2015; 37:605-9. [DOI: 10.1016/j.medengphy.2015.03.019] [Citation(s) in RCA: 40] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2014] [Revised: 01/14/2015] [Accepted: 03/23/2015] [Indexed: 11/30/2022]
|
163
|
Rahhal MMA, Bazi Y, Alajlan N, Malek S, Al-Hichri H, Melgani F, Zuair MAA. Classification of AAMI heartbeat classes with an interactive ELM ensemble learning approach. Biomed Signal Process Control 2015. [DOI: 10.1016/j.bspc.2015.03.010] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
164
|
de Chazal P. An adapting system for heartbeat classification minimising user input. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2015; 2014:82-5. [PMID: 25569902 DOI: 10.1109/embc.2014.6943534] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
An adaptive system for the processing of the electrocardiogram (ECG) for the classification of heartbeats into beat classes that seeks to minimize the required input from the user is presented. A first set of beat annotations is produced by the system by processing an incoming recording with a global-classifier. The beat annotations are then ranked by a confidence measure calculated from the posterior probabilities estimates associated with each beat classification. An expert then validates and if necessary corrects a fraction of the least confident beats of the recording. The system then adapts by first training a local-classifier using the newly annotated beats and combines this with the global-classifier to produce an adapted classification system. The adapted system is then used to update beat annotations. Our results show that we can achieve a significant boost in classification performance of the system by using a small number of beats for adaptation.
Collapse
|
165
|
|
166
|
Park J, Kang K. Intelligent classification of heartbeats for automated real-time ECG monitoring. Telemed J E Health 2014; 20:1069-77. [PMID: 25010717 PMCID: PMC4270110 DOI: 10.1089/tmj.2014.0033] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2014] [Revised: 04/01/2014] [Accepted: 04/10/2014] [Indexed: 11/13/2022] Open
Abstract
BACKGROUND The automatic interpretation of electrocardiography (ECG) data can provide continuous analysis of heart activity, allowing the effective use of wireless devices such as the Holter monitor. MATERIALS AND METHODS We propose an intelligent heartbeat monitoring system to detect the possibility of arrhythmia in real time. We detected heartbeats and extracted features such as the QRS complex and P wave from ECG signals using the Pan-Tompkins algorithm, and the heartbeats were then classified into 16 types using a decision tree. RESULTS We tested the sensitivity, specificity, and accuracy of our system against data from the MIT-BIH Arrhythmia Database. Our system achieved an average accuracy of 97% in heartbeat detection and an average heartbeat classification accuracy of above 96%, which is comparable with the best competing schemes. CONCLUSIONS This work provides a guide to the systematic design of an intelligent classification system for decision support in Holter ECG monitoring.
Collapse
Affiliation(s)
- Juyoung Park
- Department of Computer Science and Engineering, Hanyang University , Ansan, Republic of Korea
| | | |
Collapse
|
167
|
Park J, Kang K. PcHD: Personalized classification of heartbeat types using a decision tree. Comput Biol Med 2014; 54:79-88. [DOI: 10.1016/j.compbiomed.2014.08.013] [Citation(s) in RCA: 24] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2014] [Revised: 08/08/2014] [Accepted: 08/10/2014] [Indexed: 11/16/2022]
|
168
|
Zhang Z, Dong J, Luo X, Choi KS, Wu X. Heartbeat classification using disease-specific feature selection. Comput Biol Med 2014; 46:79-89. [DOI: 10.1016/j.compbiomed.2013.11.019] [Citation(s) in RCA: 214] [Impact Index Per Article: 21.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2013] [Revised: 11/20/2013] [Accepted: 11/23/2013] [Indexed: 11/28/2022]
|
169
|
Sansone M, Fusco R, Pepino A, Sansone C. Electrocardiogram pattern recognition and analysis based on artificial neural networks and support vector machines: a review. JOURNAL OF HEALTHCARE ENGINEERING 2014; 4:465-504. [PMID: 24287428 DOI: 10.1260/2040-2295.4.4.465] [Citation(s) in RCA: 53] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/03/2022]
Abstract
Computer systems for Electrocardiogram (ECG) analysis support the clinician in tedious tasks (e.g., Holter ECG monitored in Intensive Care Units) or in prompt detection of dangerous events (e.g., ventricular fibrillation). Together with clinical applications (arrhythmia detection and heart rate variability analysis), ECG is currently being investigated in biometrics (human identification), an emerging area receiving increasing attention. Methodologies for clinical applications can have both differences and similarities with respect to biometrics. This paper reviews methods of ECG processing from a pattern recognition perspective. In particular, we focus on features commonly used for heartbeat classification. Considering the vast literature in the field and the limited space of this review, we dedicated a detailed discussion only to a few classifiers (Artificial Neural Networks and Support Vector Machines) because of their popularity; however, other techniques such as Hidden Markov Models and Kalman Filtering will be also mentioned.
Collapse
Affiliation(s)
- Mario Sansone
- Department of Electrical Engineering and Information Technologies, University "Federico II" of Naples, Italy
| | | | | | | |
Collapse
|
170
|
de Chazal P. Detection of supraventricular and ventricular ectopic beats using a single lead ECG. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2013; 2013:45-48. [PMID: 24109620 DOI: 10.1109/embc.2013.6609433] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/02/2023]
Abstract
Two simple algorithms for supraventricular (SVEB) and ventricular ectopic beat (VEB) detection using the electrocardiogram (ECG) are presented. Both algorithms use time-domain features and a linear classifier. The first algorithm requires QRS detection only and the second algorithm requires P, QRS and T wave segmentation. Data was obtained from the 44 non-pacemaker recordings of the MIT-BIH arrhythmia database and contained approximately 100,000 beats. Performance assessment of the best system resulted in an accuracy of 94.4% when discriminating SVEB from non-SVEBs and 97.8% in discriminating VEB from non-VEBs.
Collapse
|