Detection of Life-Threatening Arrhythmias Using Feature Selection and Support Vector Machines

Alonso‐Atienza, Felipe; Morgado, Eduardo; Fernández-Martínez, Lorena T.; García‐Alberola, Arcadi; Rojo‐Álvarez, José Luis

doi:10.1109/tbme.2013.2290800

Cited by 187 publications

(101 citation statements)

References 30 publications

(52 reference statements)

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…The method proposed in this study was found to outperform the recent reported results in [26] as can be seen in Table 5. In [26], the authors had used 13 previously defined feature metrics and used support vector machine (SVM) classifier in contrast to the present study, where we have used 17 feature metrics and RF classifier.…”

Section: Discussionmentioning

confidence: 52%

“…Also we see that the best results are obtained for a window size of 8 s. The results are better than those obtained in [26]. A comparison has been shown in Table 5.…”

Section: Resultsmentioning

confidence: 64%

“…In addition, we used the balanced error rate (BER) [25] as the metric to compare our results with the previous results in [26].…”

Section: Resultsmentioning

confidence: 99%

“…In [26], the authors had used 13 previously defined feature metrics and used support vector machine (SVM) classifier in contrast to the present study, where we have used 17 feature metrics and RF classifier. The results also show that it is better to use overlapping segments to train the classifier as compared nonoverlapping segments which have been used in past studies.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Detection of Ventricular Fibrillation Using Random Forest Classifier

Verma¹,

Dong²

2016

JBiSE

View full text Add to dashboard Cite

Early warning and detection of ventricular fibrillation is crucial to the successful treatment of this life-threatening condition. In this paper, a ventricular fibrillation classification algorithm using a machine learning method, random forest, is proposed. A total of 17 previously defined ECG feature metrics were extracted from fixed length segments of the echocardiogram (ECG). Three annotated public domain ECG databases (Creighton University Ventricular Tachycardia database, MIT-BIH Arrhythmia Database and MIT-BIH Malignant Ventricular Arrhythmia Database) were used for evaluation of the proposed method. Window sizes 3 s, 5 s and 8 s for overlapping and non-overlapping segmentation methodologies were tested. An accuracy (Acc) of 97.17%, sensitivity (Se) of 95.17% and specificity (Sp) of 97.32% were obtained with 8 s window size for overlapping segments. The results were benchmarked against recent reported results and were found to outperform them with lower complexity.

show abstract

Section: Discussionmentioning

confidence: 52%

“…Also we see that the best results are obtained for a window size of 8 s. The results are better than those obtained in [26]. A comparison has been shown in Table 5.…”

Section: Resultsmentioning

confidence: 64%

“…In addition, we used the balanced error rate (BER) [25] as the metric to compare our results with the previous results in [26].…”

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Ventricular Fibrillation Using Random Forest Classifier

Verma¹,

Dong²

2016

JBiSE

View full text Add to dashboard Cite

show abstract

“…The Class 1 MITDB waveform database is considered gold standard in ECG analysis and is widely used, referenced and more importantly it is manually annotated by medics and is quite reliable as there is least noise in the dataset. [21] [22]. In order to classify arrhythmic beats, MITDB WFDB waveform records were used to prepare datasets to train classifiers.…”

Section: A Ecg Waveform Dataset Preparation and Analysismentioning

confidence: 99%

ECG classification and prognostic approach towards personalized healthcare

Walinjkar

Woods

2017

2017 International Conference on Social Media, Wearable and Web Analytics (Social Media)

View full text Add to dashboard Cite

Abstract-A very important aspect of personalized healthcare is to continuously monitor an individual's health using wearable biomedical devices and essentially to analyse and if possible to predict potential health hazards that may prove fatal if not treated in time. The prediction aspect embedded in the system helps in avoiding delays in providing timely medical treatment, even before an individual reaches a critical condition. Despite of the availability of modern wearable health monitoring devices, the real-time analyses and prediction component seems to be missing with these devices. The research work illustrated in this paper, at an outset, focussed on constantly monitoring an individual's ECG readings using a wearable 3-lead ECG kit and more importantly focussed on performing real-time analyses to detect arrhythmia to be able to identify and predict heart risk. Also, current research shows extensive use of heart rate variability (HRV) analysis and machine learning for arrhythmia classification, which however depends on the morphology of the ECG waveforms and the sensitivity of the ECG equipment. Since a wearable 3-lead ECG kit was used, the accuracy of classification had to be dealt with at the machine learning phase, so a unique feature extraction method was developed to increase the accuracy of classification. As a case study a very widely used Arrhythmia database (MIT-BIH, Physionet) was used to develop learning, classification and prediction models. Neuralnet fitting models on the extracted features showed mean-squared error of as low as 0.0085 and regression value as high as 0.99. Current experiments show 99.4% accuracy using k-NN Classification models and show values of Cross-Entropy Error of 7.6 and misclassification error value of 1.2 on test data using scaled conjugate gradient pattern matching algorithms. Software components were developed for wearable devices that took ECG readings from a 3-Lead ECG data acquisition kit in real time, de-noised, filtered and relayed the sample readings to the telehealth analytical server. The analytical server performed the classification and prediction tasks based on the trained classification models and could raise appropriate alarms if ECG abnormalities of V (Premature Ventricular Contraction: PVC), A (Atrial Premature Beat: APB), L (Left bundle branch block beat), R (Right bundle branch block beat) type annotations in MITDB were detected. The instruments were networked using IoT (Internet of Things) devices and abnormal ECG events related to arrhythmia, from analytical server could be logged using an FHIR web service implementation, according to a SNOMED coding system and could be accessed in Electronic Health Record by the concerned medic to take appropriate and timely decisions. The system focussed on 'preventive care rather than remedial cure' which has become a major focus of all the health care and cure institutions across the globe.

show abstract

Human machine interfacing technique for diagnosis of ventricular arrhythmia using supervisory machine learning algorithms

Karnan

Sivakumaran

Manivel³

2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary The state of art to integrate bio‐signals with computer based diagnosis is taking dominance. The man‐machine interface is useful for early and immediate clinical interpretation. The electrocardiogram (ECG) signal plays a vital role in revealing the possible data towards categorizing normal and abnormal cardiac functioning. The fatal conditions exhibited by ventricular arrhythmias (VA) pose a remarkable change in the feature set of the ECG signals. In this work, a novel approach to segregate the superior feature toward the ventricular arrhythmias are extracted using feature ranking score algorithm (FRSA). The FRSA collects feature vectors in three different domains and ranks it to find out the more prevalent feature for diagnosis of VA. The Support Vector Machine (SVM) classifier is administered by supervisory machine learning optimization algorithm Mean Grey Wolf Optimization (MGWO). The performance estimates of SVM‐MGWO is compared for classification of VA signals with other optimization also like SVM‐Particle Swarm Optimization (SVM‐PSO) and SVM‐Grey Wolf Optimization (SVM‐GWO). The non‐parametric and parametric analysis evidently shows the improved performance of feature parameter estimates for classification. The accuracy of classification for SVM‐MGWO attains 100% for finding test data with VA at a minimal convergence iteration while comparing it with the other mentioned supervisory algorithms. The standard deviation during parametric analysis is negligible, which reveals the fact that reductant feature extracted and utilized for testing of ECG data is minimal. The performance estimates attained by the proposed algorithm shows the selection of optimal feature for the findings of VA through ECG. The man‐machine interface aides in the early diagnosis of ventricular arrhythmias using non‐invasive diagnosing tool, the ECG.

show abstract

Detection of Life-Threatening Arrhythmias Using Feature Selection and Support Vector Machines

Cited by 187 publications

References 30 publications

Detection of Ventricular Fibrillation Using Random Forest Classifier

Detection of Ventricular Fibrillation Using Random Forest Classifier

ECG classification and prognostic approach towards personalized healthcare

Human machine interfacing technique for diagnosis of ventricular arrhythmia using supervisory machine learning algorithms

Contact Info

Product

Resources

About