Envelopment filter and K-means for the detection of QRS waveforms in electrocardiogram

Merino, Manuel; Gómez, I.; Molina, Alberto

doi:10.1016/j.medengphy.2015.03.019

Cited by 53 publications

(31 citation statements)

References 23 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[6] [7] Two or more cardiologists have independently annotated each record beat by beat by identifying abnormal beats in the waveform. Machine learning classification models have been successfully developed in the past with high degree of accuracy [9] [14]. The drawback however is that these models tend to accept test data in large samples and perform analysis on entire dataset in a single execution cycle and can't be used in real-time monitoring in order to generate alarms and alerts related to arrhythmia.…”

Section: A Ecg Overview and Mit-bih Arrhythmia Databasementioning

confidence: 99%

“…Pattern recognition using neural networks was also experimented with and Table 1 shows pattern recognition accuracy over several combinations of percentages of training-validation-test data showing no bias or overfit. Despite of the availability of accurate classification [9] algorithms, ECG equipment could not be used in the past for real time ECG classification due to nonreal time batch processing nature of the algorithms, where the analysis was done after data acquisition stage. Traditionally, ECG arrhythmia classification relied on HRV analysis which produced accurate results [15] [22] though it relied on accurate ECG equipment which was not portable or wearable.…”

Section: A Signal Processing Dataset Preparation and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Personalized wearable systems for real-time ECG classification and healthcare interoperability: Real-time ECG classification and FHIR interoperability

Walinjkar

Woods

2017

2017 Internet Technologies and Applications (ITA)

View full text Add to dashboard Cite

Abstract-Continuous monitoring of an individual's health using wearable biomedical devices is becoming a norm these days with a large number of wearable kits becoming easily available. Modern wearable health monitoring devices have become easily available in the consumer market, however, realtime analyses and prediction along with alerts and alarms about a health hazard are not adequately addressed in such devices. Taking ECG monitoring as a case study the research paper focusses on signal processing, arrhythmia detection and classification and at the same time focusses on updating the electronic health records database in realtime such that the concerned medical practitioners become aware of an emergent situation the patient being monitored might face. Also, heart rate variability (HRV) analysis is usually considered as a basis for arrhythmia classification which largely depends on the morphology of the ECG waveforms and the sensitivity of the biopotential measurements of the ECG kits, so it may not yield accurate results. Initially, the ECG readings from the 3-Lead ECG analog front-end were de-noised, zero-offset corrected, filtered using recursive least square adaptive filter and smoothed using Savitzky-Golay filter and subsequently passed to the data analysis component with a unique feature extraction method to increase the accuracy of classification. The machine learning models trained on MITDB arrhythmia database (MIT-BIH Physionet) showed more than 97% accuracy using kNN classifiers. Neuralnet fitting models showed mean-squared error of as low as 0.0085 and regression value as high as 0.99. ECG abnormalities based on annotations in MITDB could be classified and these ECG observations could be logged to a server implementation based on FHIR standards. The instruments were networked using IoT (Internet of Things) devices and ECG event observations were coded according to SNOMED coding system and could be accessed in Electronic Health Record by the concerned medic to take appropriate and timely decisions. The system emphasizes on 'preventive care rather than remedial cure' as the next generation personalized health-care monitoring devices become available.

show abstract

Section: A Ecg Overview and Mit-bih Arrhythmia Databasementioning

confidence: 99%

Section: A Signal Processing Dataset Preparation and Analysismentioning

confidence: 99%

Personalized wearable systems for real-time ECG classification and healthcare interoperability: Real-time ECG classification and FHIR interoperability

Walinjkar

Woods

2017

2017 Internet Technologies and Applications (ITA)

View full text Add to dashboard Cite

show abstract

“…ECG QRS detection is an important aspect in ECG analysis and techniques such as K-Means, PCA (Principal Component Analysis), K-Nearest Neighbours (K-NN) and Probabilistic Neural Network (PNN) have been successfully used recently yielding over 99% classification accuracy [11][12] [28]. The drawback however is that these models tend to accept test data in large samples and perform analysis on entire dataset in a single execution cycle instead of beatby-beat samples in real-time.…”

Section: B Mit-bih Arrhythmia Databasementioning

confidence: 99%

“…Along with regression based classification fitting and pattern recognition using neural networks was also experimented with and Table 2 and Figure 4 show pattern recognition accuracy over several combinations of percentages of training-validation-test data showing no bias or overfit. In currently available systems as mentioned in Background Literature and Problems section and despite of the availability of accurate classification [11] [12] [13] [47] algorithms these could not be put to practical and beneficial use to raise alarms due to size constraints of the accurate 12-lead ECG equipment and non-real time batch processing nature of the algorithms. Traditionally, ECG arrhythmia classification relied on QRS detection and HRV analysis which produced accurate results [10] [53].…”

Section: B Real-time Data Acquisition and Web-servicesmentioning

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

“…An electrocardiogram (ECG) is a recording of the electrical activity of the heart [1, 2] and a graphical representation of the signals obtained from electrodes placed on the skin near the heart [1, 3, 4]. The recent use of computers in conducting ECG analysis allows the patterns of the ECG signal, composed of multiple cycles that include numerous sample points, to be visualized [5].…”

Section: Introductionmentioning

confidence: 99%

R Peak Detection Method Using Wavelet Transform and Modified Shannon Energy Envelope

Park

Lee

Park

2017

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Rapid automatic detection of the fiducial points—namely, the P wave, QRS complex, and T wave—is necessary for early detection of cardiovascular diseases (CVDs). In this paper, we present an R peak detection method using the wavelet transform (WT) and a modified Shannon energy envelope (SEE) for rapid ECG analysis. The proposed WTSEE algorithm performs a wavelet transform to reduce the size and noise of ECG signals and creates SEE after first-order differentiation and amplitude normalization. Subsequently, the peak energy envelope (PEE) is extracted from the SEE. Then, R peaks are estimated from the PEE, and the estimated peaks are adjusted from the input ECG. Finally, the algorithm generates the final R features by validating R-R intervals and updating the extracted R peaks. The proposed R peak detection method was validated using 48 first-channel ECG records of the MIT-BIH arrhythmia database with a sensitivity of 99.93%, positive predictability of 99.91%, detection error rate of 0.16%, and accuracy of 99.84%. Considering the high detection accuracy and fast processing speed due to the wavelet transform applied before calculating SEE, the proposed method is highly effective for real-time applications in early detection of CVDs.

show abstract

Envelopment filter and K-means for the detection of QRS waveforms in electrocardiogram

Cited by 53 publications

References 23 publications

Personalized wearable systems for real-time ECG classification and healthcare interoperability: Real-time ECG classification and FHIR interoperability

Personalized wearable systems for real-time ECG classification and healthcare interoperability: Real-time ECG classification and FHIR interoperability

ECG classification and prognostic approach towards personalized healthcare

R Peak Detection Method Using Wavelet Transform and Modified Shannon Energy Envelope

Contact Info

Product

Resources

About