Beat Segmentation Research Articles

ECG classification via integration of adaptive beat segmentation and relative heart rate with deep learning networks

We propose a state-of-the-art deep learning approach for accurate electrocardiogram (ECG) signal analysis, addressing both waveform delineation and beat type classification tasks. For beat type classification, we integrated two novel schemes into the deep learning model, significantly enhancing its performance. The first scheme is an adaptive beat segmentation method that determines the optimal duration for each heartbeat based on RR-intervals, mitigating segmenting errors from conventional fixed-period segmentation. The second scheme incorporates relative heart rate information of the target beat compared to neighboring beats, improving the model’s ability to accurately detect premature atrial contractions (PACs) that are easily confused with normal beats due to similar morphology. Extensive evaluations on the PhysioNet QT Database, MIT-BIH Arrhythmia Database, and real-world wearable device data demonstrated the proposed approach’s superior capabilities over existing methods in both tasks. The proposed approach achieved sensitivities of 99.81% for normal beats, 99.08% for premature ventricular contractions, and 97.83% for PACs in beat type classification. For waveform delineation, we achieved F1-scores of 0.9842 for non-waveform, 0.9798 for P-waves, 0.9749 for QRS complexes, and 0.9848 for T-waves. It significantly outperforms existing methods in PAC detection while maintaining high performance across both tasks. The integration of aforementioned two schemes into the deep learning model improved the accuracy of normal sinus rhythms and arrhythmia detection.

Enhancing Inter-Patient Performance for Arrhythmia Classification with Adversarial Learning Using Beat-Score Maps

Research on computer-aided arrhythmia classification is actively conducted, but the limited generalization capacity constrains its applicability in practical clinical settings. One of the primary challenges in deploying such techniques in real-world scenarios is the inter-patient variability and the consequent performance degradation. In this study, we leverage our previous innovation, the n-beat-score map (n-BSM), to introduce an adversarial framework to mitigate the issue of poor performance in arrhythmia classification within the inter-patient paradigm. The n-BSM is a 2D representation of the ECG signal, capturing its constituent beat characteristics through beat-score vectors derived from a pre-trained beat classifier. We employ adversarial learning to eliminate patient-dependent features during the training of the beat classifier, thereby generating the patient-independent n-BSM (PI-BSM). This approach enables us to concentrate primarily on the learning characteristics associated with beat type rather than patient-specific features. Through a beat classifier pre-trained with adversarial learning, a series of beat-score vectors are generated for the beat segments that make up a given ECG signal. These vectors are then concatenated chronologically to form a PI-BSM. Utilizing PI-BSMs as the input, an arrhythmia classifier is trained to differentiate between distinct types of rhythms. This approach yields a 14.27% enhancement in the F1-score in the MIT-BIH arrhythmia database and a 4.97% improvement in cross-database evaluation using the Chapman–Shaoxing 12-lead ECG database.

Deep Learning System for Left Ventricular Assist Device Candidate Assessment from Electrocardiograms.

Left Ventricular Assist Devices (LVADs) are increasingly used as long-term implantation therapy for advanced heart failure patients, where candidacy assessment is crucial for successful treatment and recovery. A Deep Learning system based on Electrocardiogram (ECG) diagnoses criteria to stratify candidacy is proposed, implementing multi-model processing, interpretability, and uncertainty estimation. The approach includes beat segmentation for single-lead classification, 12-lead analysis, and semantic segmentation, achieving state-of-the-art results on the classification evaluation of each model, with multilabel average AUC results of 0.9924, 0.9468, and 0.9956, respectively, presenting a novel approach for LVAD candidacy assessment, serving as an aid for decision-making.

Electrocardiogram morphological arrhythmia classification using fuzzy entropy-based feature selection and optimal classifier

Electrocardiogram (ECG) signal analysis has become significant in recent years as cardiac arrhythmia shares a major portion of all mortality worldwide. To detect these arrhythmias, computer-assisted algorithms play a pivotal role as beat-by-beat monitoring of holter ECG signals is required. In this paper, a morphological arrhythmia classification algorithm has been proposed to classify seven different ECG beats, namely Normal Beat (N), Left Bundle Branch Block Beat (L), Right Bundle Branch Block Beat (R), Atrial Premature Contraction Beat (A), Premature Ventricular Contraction Beat (V), Fusion of Normal and Ventricle Beat (F) and Pace Beat (P). A novel feature set of 25 attributes has been extracted from each ECG beat and ranked using the Fuzzy Entropy-based feature selection (FEBFS) technique. In addition, two distinct classifiers, support vector machine with radial basis function as the kernel (SVM-RBF) and weighted K-nearest neighbor (WKNN), are used to categorize ECG beats, and their performances are also evaluated after adjusting vital parameters. The performance of classifiers is compared for four different ECG beat segmentation approaches and further analyzed using three similarity measurement techniques and two fuzzy entropy methods while feature selection. The classifier results are also cross-validated using a 10-fold cross-validation scheme, and the MIT-BIH Arrhythmia Database has been used to validate the proposed work. After selecting 21 highly ranked features, WKNN achieves the best results with the nearest neighbor value K = 3 and cityblock distance metrics, with Average Sensitivity (Sen) = 94.89%, Positive Predictivity (Ppre) = 97.13%, Specificity (Spe) = 99.72%, F1 Score = 95.95%, and Overall Accuracy (Acc) = 99.15%. The novelty of this work relies on formulating a unique feature set, including proposed symbolic features, followed by the FEBFS technique making this algorithm efficient and reliable for morphological arrhythmia classification. The above results demonstrate that the proposed algorithm performs better than many existing state-of-the-art works.

Improved delineation model of a standard 12-lead electrocardiogram based on a deep learning algorithm

BackgroundSignal delineation of a standard 12-lead electrocardiogram (ECG) is a decisive step for retrieving complete information and extracting signal characteristics for each lead in cardiology clinical practice. However, it is arduous to manually assess the leads, as a variety of signal morphological variations in each lead have potential defects in recording, noise, or irregular heart rhythm/beat.MethodA computer-aided deep-learning algorithm is considered a state-of-the-art delineation model to classify ECG waveform and boundary in terms of the P-wave, QRS-complex, and T-wave and indicated the satisfactory result. This study implemented convolution layers as a part of convolutional neural networks for automated feature extraction and bidirectional long short-term memory as a classifier. For beat segmentation, we have experimented beat-based and patient-based approach.ResultsThe empirical results using both beat segmentation approaches, with a total of 14,588 beats were showed that our proposed model performed excellently well. All performance metrics above 95% and 93%, for beat-based and patient-based segmentation, respectively.ConclusionsThis is a significant step towards the clinical pertinency of automated 12-lead ECG delineation using deep learning.

Domain and Patient Adversarial Multi-Task Learning for Arrhythmia Classification.

Manual screening of electrocardiograms (ECGs) for heart arrhythmias by clinicians is time-consuming and labor-intensive. A machine learning model for the automated diagnosis of heart arrhythmia from ECG signals can facilitate improved diagnosis, greater accessibility and earlier intervention for patients. The potential of such models is limited however by the small size of clinical datasets available for training. Methods that can be trained with multiple datasets to classify heart arrhythmia are needed to overcome this problem.In this paper, we propose using adversarial multi-task learning (AMTL) to extract domain and patient invariant features from two electrocardiogram databases. We further investigated the influence of beat segmentation location and beat normalization on domain invariance. Our proposed methods were tested on the MIT-BIH Arrhythmia and the St Petersburg INCART 12-lead Arrhythmia Databases. The domain adversarial models achieved a higher accuracy and average F1 score than their counterparts without domain adversarial learning. In particular, the patient and domain adversarial model improved the F1 scores on the two tested databases from 70% and 74% to 77% each.Clinical Relevance-This establishes that adversarial multitask learning with multiple datasets and multiple adversarial tasks can improve the F1 score of arrhythmia classification.

Subject-Independent per Beat PPG to Single-Lead ECG Mapping

In this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a single-lead electrocardiogram (single-lead ECG) signal. The main limiting factors represented in uncleaned data, subject dependency, and erroneous beat segmentation are regarded. The dataset is cleaned by a two-stage clustering approach. Rather than complete single–lead ECG signal reconstruction, a beat-based PPG-to-single-lead-ECG (PPG2ECG) conversion is introduced for providing a simple lightweight model that meets the computational capabilities of wearable devices. In addition, peak-to-peak segmentation is employed for alleviating errors in PPG onset detection. Furthermore, subject-dependent training is highlighted as a critical factor in training procedures because most existing work includes different beats/signals from the same subject’s record in both training and testing sets. So, we provide a completely subject-independent model where the testing subjects’ records are hidden in the training stage entirely, i.e., a subject record appears once either in the training or testing set, but testing beats/signals belong to records that never appear in the training set. The proposed deep learning model is designed for providing efficient feature extraction that attains high reconstruction quality over subject-independent scenarios. The achieved performance is about 0.92 for the correlation coefficient and 0.0086 for the mean square error for the dataset extracted/cleaned from the MIMIC II dataset.

Left ventricular hypertrophy detection using electrocardiographic signal

Left ventricular hypertrophy (LVH) indicates subclinical organ damage, associating with the incidence of cardiovascular diseases. From the medical perspective, electrocardiogram (ECG) is a low-cost, non-invasive, and easily reproducible tool that is often used as a preliminary diagnosis for the detection of heart disease. Nowadays, there are many criteria for assessing LVH by ECG. These criteria usually include that voltage combination of RS peaks in multi-lead ECG must be greater than one or more thresholds for diagnosis. We developed a system for detecting LVH using ECG signals by two steps: firstly, the R-peak and S-valley amplitudes of the 12-lead ECG were extracted to automatically obtain a total of 24 features and ECG beats of each case (LVH or non-LVH) were segmented; secondly, a back propagation neural network (BPN) was trained using a dataset with these features. Echocardiography (ECHO) was used as the gold standard for diagnosing LVH. The number of LVH cases (of a Taiwanese population) identified was 173. As each ECG sequence generally included 8 to 13 cycles (heartbeats) due to differences in heart rate, etc., we identified 1466 ECG cycles of LVH patients after beat segmentation. Results showed that our BPN model for detecting LVH reached the testing accuracy, precision, sensitivity, and specificity of 0.961, 0.958, 0.966 and 0.956, respectively. Detection performances of our BPN model, on the whole, outperform 7 methods using ECG criteria and many ECG-based artificial intelligence (AI) models reported previously for detecting LVH.

Intelligent Recognition Algorithm of Multiple Myocardial Infarction Based on Morphological Feature Extraction

Myocardial infarction is a type of heart disease marked by rapid progression and high mortality. In this paper, a novel intelligent recognition algorithm of multiple myocardial infarctions using a bidirectional long short-term memory (BiLSTM) neural network classification was proposed. This algorithm was based on morphological feature extraction, which can greatly improve the diagnostic efficiency of doctors for different kinds of myocardial infarction diseases. The algorithm includes noise reduction and beat segmentation of electrocardiogram (ECG) signals from the Physikalisch-Technische Bundesanstalt (PTB) database. According to the medical diagnosis guide, the distance feature of the whole waveform and the amplitude feature of the branch lead waveform are extracted. According to the extracted features, the long short-term memory network (LSTM) and the BiLSTM neural networks are built to classify and recognize heartbeats. The experimental results show that the accuracy of the morphological feature + BiLSTM algorithm in MI detection is 99.4%. At the same time, among the six common myocardial infarction diseases, the location and recognition rate of the culprit vessel is high. The sensitivity, specificity, PPV, NPV, and F1 score parameters all reach more than 98.4%, and the kappa coefficient also reaches 0.983, while the overall accuracy reaches 98.6%. The accuracy of this algorithm is improved by at least 1% compared with that of other existing algorithms. Thus, this study exhibits a very important clinical application value.

End-to-End Convolutional Neural Network Model to Detect and Localize Myocardial Infarction Using 12-Lead ECG Images without Preprocessing.

In recent years, many studies have proposed automatic detection and localization techniques for myocardial infarction (MI) using the 12-lead electrocardiogram (ECG). Most of them applied preprocessing to the ECG signals, e.g., noise removal, trend removal, beat segmentation, and feature selection, followed by model construction and classification based on machine-learning algorithms. The selection and implementation of preprocessing methods require specialized knowledge and experience to handle ECG data. In this paper, we propose an end-to-end convolutional neural network model that detects and localizes MI without such complicated multistep preprocessing. The proposed model executes comprehensive learning for the waveform features of unpreprocessed raw ECG images captured from 12-lead ECG signals. We evaluated the classification performance of the proposed model in two experimental settings: ten-fold cross-validation where ECG images were split randomly, and two-fold cross-validation where ECG images were split into one patient and the other patients. The experimental results demonstrate that the proposed model obtained MI detection accuracies of 99.82% and 93.93% and MI localization accuracies of 99.28% and 69.27% in the first and second settings, respectively. The performance of the proposed method is higher than or comparable to that of existing state-of-the-art methods. Thus, the proposed model is expected to be an effective MI diagnosis tool that can be used in intensive care units and as wearable technology.

Premature Beats Rejection Strategy on Paroxysmal Atrial Fibrillation Detection.

Paroxysmal atrial fibrillation (PAF) may related to the risk of thromboembolism and is the most common cardiac risk factor of cryptogenic stroke (CS). Due to its paroxysmal characteristics, it is usually diagnosed by continuous long-term ECG. Patients with paroxysmal atrial fibrillation usually have premature beats at the same time which is easy to be confused with the rhythm of atrial fibrillation. Therefore, in this article, we designed a screening algorithm for single premature beat, multi premature beats, bigeminy and trigeminy premature beats, according to their rhythm characteristics to reduce false detection caused by premature beats during the PAF detection process. The proposed elimination method was verified on ECG segments with different types of premature beats, and tested on long-term ECG data of PAF patients. ECG segments of different kinds of premature beats were selected from MIT Atrial Fibrillation database (MIT-AFDB), MIT-BIH Arrhythmia database (MIT-AR) and wearable ECG data from the China Physiological Signal Challenge 2021 (CPSC 2021). The proposed method can effectively eliminate single premature beat segments with 99.5% accuracy, and it also can eliminate more than 95% of ECG segments with other types of premature beats. We designed PAF-score as a new index to evaluate the accuracy of detection, and we also calculate the misjudged and missed segments to comprehensively evaluate the PAF detection algorithm. The proposed method get a PAF-score of 0.912 on MIT-AFDB. The proposed method also has the potential to implant low computing power wearable devices for real-time analysis.

Application-Specific Discriminant Analysis of Cardiac Anomalies Using Shift-Invariant Wavelet Transform

Automatic arrhythmia detection in electrocardiogram (ECG) using supervised learning has gained significant considerations in recent years. This paper projects the performance analysis of classifiers such as support vector machine (SVM), extreme learning machine (ELM), and k-nearest neighbor (KNN) with efficient time utilization showing multi-classification for specific medical application. The wavelet double decomposition is used to show the shift-invariant use of dual-tree complex wavelet transform for noise filtering and beat segmentation is done to extract 130 informative samples. Further, the linear discriminant analysis is applied to dimensionally reduce and elite the 12 most relevant features for classifying normal and four abnormal beats collected from MIT/BIH ECG database. The proposed executed system distinguishes SVM, ELM, and KNN with percentage accuracy of 99.8, 97, and 99.8 having classifier testing time as 0.0081s, 0.0031s, and 0.0234s, respectively. The simulated experimental outcomes in comparison with existing work yields adequate accuracy, and computational time.

ECG Beat Representation and Delineation by Means of Variable Projection.

The electrocardiogram (ECG) follows a characteristic shape, which has led to the development of several mathematical models for extracting clinically important information. Our main objective is to resolve limitations of previous approaches, that means to simultaneously cope with various noise sources, perform exact beat segmentation, and to retain diagnostically important morphological information. We therefore propose a model that is based on Hermite and sigmoid functions combined with piecewise polynomial interpolation for exact segmentation and low-dimensional representation of individual ECG beat segments. Hermite and sigmoidal functions enable reliable extraction of important ECG waveform information while the piecewise polynomial interpolation captures noisy signal features like the baseline wander (BLW). For that we use variable projection, which allows the separation of linear and nonlinear morphological variations of the according ECG waveforms. The resulting ECG model simultaneously performs BLW cancellation, beat segmentation, and low-dimensional waveform representation. We demonstrate its BLW denoising and segmentation performance in two experiments, using synthetic and real data. Compared to state-of-the-art algorithms, the experiments showed less diagnostic distortion in case of denoising and a more robust delineation for the P and T wave. This work suggests a novel concept for ECG beat representation, easily adaptable to other biomedical signals with similar shape characteristics, such as blood pressure and evoked potentials. Our method is able to capture linear and nonlinear wave shape changes. Therefore, it provides a novel methodology to understand the origin of morphological variations caused, for instance, by respiration, medication, and abnormalities.

Left ventricular hypertrophy detection system based on electrocardiogram signal

Abstract Background Left ventricular hypertrophy (LVH) is associated with increased risks of cardiovascular diseases. Electrocardiography (ECG) is generally used to screen LVH in general population and electrocardiographic LVH is further confirmed by transthoracic echocardiography (Echo). Purpose We aimed to establish an ECG LVH detection system that was validated by echo LVH. Methods We collected the data of ECGs and Echo from the previous database. The voltage of R- and S-amplitude in each ECG lead were measured twice by a study assistance blinded to the study design, (artificially measured). Another knowledge engineer analyzed row signals of ECG (the algorithm). We firstly check the correlation of R- and S-amplitude between the artificially measured and the algorythm. ECG LVH is defined by the voltage criteria and Echo LVH is defined by LV mass index >115 g/m2 in men and >95 g/m2 in women. Then we use decision tree, k-means, and back propagation neural network (BPNN) with or without heart beat segmentation to establish a rapid and accurate LVH detection system. The ratio of training set to test set was 7:3. Results The study consisted of a sample size of 953 individuals (90% male) with 173 Echo LVH. The R- and S-amplitude were highly correlated between artificially measured and the algorithm R- and S-amplitude regarding that the Pearson correlation coefficient were >0.9 in each lead (the highest r of 0.997 in RV5 and the lowest r of 0.904 in aVR). Without heart beat segmentation, the accuracy of decision tree, k-means, and BPNN to predict echo LVH were 0.74, 0.73 and 0.51, respectively. With heart beat segmentation, the signal of Echo LVH expanded to 1466, and the accuracy to predict ECG LVH were obviously improved (0.92 for decision tree, 0.96 for k-means, and 0.59 for BPNN). Conclusions Our study showed that machine-learning model by BPNN had the highest accuracy than decision trees and k-means based on ECG R- and S-amplitude signal analyses. Figure 1. Three layers of the decision tree Funding Acknowledgement Type of funding source: None

Stable Automatic Envelope Estimation for Noisy Doppler Ultrasound

Doppler ultrasound technology is widespread in clinical applications and is principally used for blood flow measurements in the heart, arteries, and veins. A commonly extracted parameter is the maximum velocity envelope. However, current methods of extracting it cannot produce stable envelopes in high noise conditions. This can limit clinical and research applications using the technology. In this article, a new method of automatic envelope estimation is presented. The method can handle challenging signals with high levels of noise and variable envelope shapes. Envelopes are extracted from a Doppler spectrogram image generated directly from the Doppler audio signal, making it less device-dependent than existing image-processing methods. The method's performance is assessed using simulated pulsatile flow, a flow phantom, and in vivo ascending aortic flow measurements and is compared with three state-of-the-art methods. The proposed method is the most accurate in noisy conditions, achieving, on average, for phantom data with signal-to-noise ratios (SNRs) below 10 dB, bias and standard deviation of 0.7% and 3.3% lower than the next-best performing method. In addition, a new method for beat segmentation is proposed. When combined, the two proposed methods exhibited the best performance using in vivo data, producing the least number of incorrectly segmented beats and 8.2% more correctly segmented beats than the next best performing method. The ability of the proposed methods to reliably extract timing indices for cardiac cycles across a range of signal quality is of particular significance for research and monitoring applications.

Detection of Premature Ventricular Complexes using Semisupervised Autoencoders and Random Forests.

In this paper, we propose a technique for detection of premature ventricular complexes (PVC) based on information obtained from single-lead electrocardiogram (ECG) signals. A combination of semisupervised autoencoders and Random Forests models are used for feature extraction and PVC detection. The ECG signal is first denoised using Stationary Wavelet Transforms and denoising convolutional autoencoders. Following this, PVC classification is performed. Individual ECG beat segments along with features derived from three consecutive beats are used to train a hybrid autoencoder network to learn class-specific beat encodings. These encodings, along with the beat-triplet features, are then input to a Random Forests classifier for final PVC classification. Results: The performance of our algorithm was evaluated on ECG records in the MIT-BIH Arrhythmia Database (MITDB) and the St. Petersburg INCART Database (INCARTDB). Our algorithm achieves a sensitivity of 92.67% and a PPV of 95.58% on the MITDB database. Similarly, a sensitivity of 88.08% and a PPV of 94.76% are achieved on the INCARTDB database.

Spatial-Temporal Signals and Clinical Indices in Electrocardiographic Imaging (I): Preprocessing and Bipolar Potentials.

During the last years, Electrocardiographic Imaging (ECGI) has emerged as a powerful and promising clinical tool to support cardiologists. Starting from a plurality of potential measurements on the torso, ECGI yields a noninvasive estimation of their causing potentials on the epicardium. This unprecedented amount of measured cardiac signals needs to be conditioned and adapted to current knowledge and methods in cardiac electrophysiology in order to maximize its support to the clinical practice. In this setting, many cardiac indices are defined in terms of the so-called bipolar electrograms, which correspond with differential potentials between two spatially close potential measurements. Our aim was to contribute to the usefulness of ECGI recordings in the current knowledge and methods of cardiac electrophysiology. For this purpose, we first analyzed the basic stages of conventional cardiac signal processing and scrutinized the implications of the spatial-temporal nature of signals in ECGI scenarios. Specifically, the stages of baseline wander removal, low-pass filtering, and beat segmentation and synchronization were considered. We also aimed to establish a mathematical operator to provide suitable bipolar electrograms from the ECGI-estimated epicardium potentials. Results were obtained on data from an infarction patient and from a healthy subject. First, the low-frequency and high-frequency noises are shown to be non-independently distributed in the ECGI-estimated recordings due to their spatial dimension. Second, bipolar electrograms are better estimated when using the criterion of the maximum-amplitude difference between spatial neighbors, but also a temporal delay in discrete time of about 40 samples has to be included to obtain the usual morphology in clinical bipolar electrograms from catheters. We conclude that spatial-temporal digital signal processing and bipolar electrograms can pave the way towards the usefulness of ECGI recordings in the cardiological clinical practice. The companion paper is devoted to analyzing clinical indices obtained from ECGI epicardial electrograms measuring waveform variability and repolarization tissue properties.

A Generic and Robust System for Automated Detection of Different Classes of Arrhythmia

Cardiovascular Arrhythmias (irregular beat) are related to the sudden death, can be characterized into two kinds, life-threatening (dangerous) and non-life-threatening. In clinical research and diagnosis analysis electrocardiography (ECG) plays an important role. The Advancement of Medical Instrumentation (AAMI) suggests, all the heartbeat of MIT-BIH dataset into four classes, namely, normal or bundle branch block (N), supraventricular ectopic (S), ventricular ectopic (V) and fusion of ventricular and normal (F). The objective of this paper is the classification of arrhythmias on the ECG as per AAMI standards. First beat detection and then on a given window size beat segmentation is performed. Then, features computed from ECG signals are RR (separation between two successive heartbeat pulses), local binary pattern(LBP), morphological changes, wavelet, high order statistics, and several amplitude values; Pre-RR, Post-RR, Local RR and Global RR. The main reason is to computing many morphological features to comparison analysis with the model when trained and tested on single features vs combining all features together. Model gives highest performance which is 90.8% accuracy using LBP as single feature compared with other features. Combined all important features together and optimal features (total 104) are given as an input to Single SVM classifier as well as ensembles of SVM which maps the component feature vectors to the particular class name. Principal Component Analysis (PCA) technique is also applied to the model which reduces the total number of features from 104 to 30 features. The Single SVM system can accurately classify four beat types and has an overall classification rate of 94.05% without PCA and using PCA 92.84% while the Ensemble SVM classifies and with an accuracy of 92.96%

A NARX Model to Predict Myocardial Ischemic Beats from ECG Using Features Extracted by ICA and WPD

This paper presents a methodology for predicting Myocardial Ischemic Beats from ECG signal using a Nonlinear Autoregressive Neural Network with Exogenous inputs (NARX) model. This technique utilizes the features extracted by integrating independent component analysis (ICA) and Wavelet packet decomposition (WPD) on ECG for detecting Myocardial Ischemic beats. At first, the denoised ECG beat segments are projected on the bases to create the independent component (IC) vectors. Further, these IC vectors are disintegrated by WPD. The feature set for distinguishing ischemic beats is extracted by calculating entropy, mean and standard deviation from wavelet coefficients. These features are input to NARX model for uncovering ischemic beats from normal beats. Several architectures of NARX models were tested for predicting myocardial ischemic beats. The efficacy of NARX architectures are assessed by comparing MSE and correlation coefficient. The NARX model with 2 hidden neurons and 2 delay lines provided the best results with a MSE of 0.0002 and correlation coefficient 0.99, which implies that the NARX neural network has huge potential in the prognosis of Myocardial Ischemic Beats.

Photoplethysmogram Signal Quality Assessment Using Support Vector Machine and Multi-Feature Fusion

Background: Noise is unavoidable in the physiological signal measurement system. Poor quality signals can affect the results of analysis and disable the following clinical diagnosis. Thus, it is necessary to perform signal quality assessment before we interpreting the signal. Objective: In this work, we describe a method combing support vector machine (SVM) and multi-feature fusion for assessing the signal quality of pulsatile waveforms, concentrating on the photoplethysmogram (PPG). Methods: PPG signals from 53 healthy volunteers were recorded. Each had a 5 min length. Signal quality in each heart beat was manual annotated by clinical expert, and then the signal quality in 5 s episode was automatically calculated according to the results from each beat segments, resulting in a total of 13,294 5-s PPG segments. Then a SVM was trained to classify clean/noisy PPG recordings by inputting a set of twelve signal quality features. Further experiments were carried out to verify the proposed SVM based signal quality classifier method. Results: An average accuracy of 87.90%, a sensitivity of 88.10% and a specificity of 87.66% were found on the 10-fold cross validation. Conclusions: The signal quality of PPGs can be accurately classified by using the proposed method.