An Automated System for ECG Arrhythmia Detection Using Machine Learning Techniques

Development and validation of machine learning algorithms based on electrocardiograms for cardiovascular diagnoses at the population level

Artificial intelligence-enabled electrocardiogram (ECG) algorithms are gaining prominence for the early detection of cardiovascular (CV) conditions, including those not traditionally associated with conventional ECG measures or expert interpretation. This study develops and validates such models for simultaneous prediction of 15 different common CV diagnoses at the population level. We conducted a retrospective study that included 1,605,268 ECGs of 244,077 adult patients presenting to 84 emergency departments or hospitals, who underwent at least one 12-lead ECG from February 2007 to April 2020 in Alberta, Canada, and considered 15 CV diagnoses, as identified by International Classification of Diseases, 10th revision (ICD-10) codes: atrial fibrillation (AF), supraventricular tachycardia (SVT), ventricular tachycardia (VT), cardiac arrest (CA), atrioventricular block (AVB), unstable angina (UA), ST-elevation myocardial infarction (STEMI), non-STEMI (NSTEMI), pulmonary embolism (PE), hypertrophic cardiomyopathy (HCM), aortic stenosis (AS), mitral valve prolapse (MVP), mitral valve stenosis (MS), pulmonary hypertension (PHTN), and heart failure (HF). We employed ResNet-based deep learning (DL) using ECG tracings and extreme gradient boosting (XGB) using ECG measurements. When evaluated on the first ECGs per episode of 97,631 holdout patients, the DL models had an area under the receiver operating characteristic curve (AUROC) of <80% for 3 CV conditions (PTE, SVT, UA), 80-90% for 8 CV conditions (CA, NSTEMI, VT, MVP, PHTN, AS, AF, HF) and an AUROC > 90% for 4 diagnoses (AVB, HCM, MS, STEMI). DL models outperformed XGB models with about 5% higher AUROC on average. Overall, ECG-based prediction models demonstrated good-to-excellent prediction performance in diagnosing common CV conditions.

Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning Models

Gait analysis has been studied over the last few decades as the best way to objectively assess the technical outcome of a procedure designed to improve gait. The treating physician can understand the type of gait problem, gain insight into the etiology, and find the best treatment with gait analysis. The gait parameters are the kinematics, including the temporal and spatial parameters, and lack the activity information of skeletal muscles. Thus, the gait analysis measures not only the three-dimensional temporal and spatial graphs of kinematics but also the surface electromyograms (sEMGs) of the lower limbs. Now, the shoe-worn GaitUp Physilog® wearable inertial sensors can easily measure the gait parameters when subjects are walking on the general ground. However, it cannot measure muscle activity. The aim of this study is to measure the gait parameters using the sEMGs of the lower limbs. A self-made wireless device was used to measure the sEMGs from the vastus lateralis and gastrocnemius muscles of the left and right feet. Twenty young female subjects with a skeletal muscle index (SMI) below 5.7 kg/m2 were recruited for this study and examined by the InBody 270 instrument. Four parameters of sEMG were used to estimate 23 gait parameters. They were measured using the GaitUp Physilog® wearable inertial sensors with three machine learning models, including random forest (RF), decision tree (DT), and XGBoost. The results show that 14 gait parameters could be well-estimated, and their correlation coefficients are above 0.800. This study signifies a step towards a more comprehensive analysis of gait with only sEMGs.

Prediction of postoperative complications after oesophagectomy using machine-learning methods

BACKGROUND

Oesophagectomy is an operation with a high risk of postoperative complications. The aim of this single-centre retrospective study was to apply machine-learning methods to predict complications (Clavien-Dindo grade IIIa or higher) and specific adverse events.

METHODS

Patients with resectable adenocarcinoma or squamous cell carcinoma of the oesophagus and gastro-oesophageal junction who underwent Ivor Lewis oesophagectomy between 2016 and 2021 were included. The tested algorithms were logistic regression after recursive feature elimination, random forest, k-nearest neighbour, support vector machine, and neural network. The algorithms were also compared with a current risk score (the Cologne risk score).

RESULTS

457 patients had Clavien-Dindo grade IIIa or higher complications (52.9 per cent) versus 407 patients with Clavien-Dindo grade 0, I, or II complications (47.1 per cent). After 3-fold imputation and 3-fold cross-validation, the overall accuracies were: logistic regression after recursive feature elimination, 0.528; random forest, 0.535; k-nearest neighbour, 0.491; support vector machine, 0.511; neural network, 0.688; and Cologne risk score, 0.510. For medical complications, the results were: logistic regression after recursive feature elimination, 0.688; random forest, 0.664; k-nearest neighbour, 0.673; support vector machine, 0.681; neural network, 0.692; and Cologne risk score, 0.650. For surgical complications, the results were: logistic regression after recursive feature elimination, 0.621; random forest, 0.617; k-nearest neighbour, 0.620; support vector machine, 0.634; neural network, 0.667; and Cologne risk score, 0.624. The calculated area under the curve of the neural network was 0.672 for Clavien-Dindo grade IIIa or higher, 0.695 for medical complications, and 0.653 for surgical complications.

CONCLUSION

The neural network scored the highest accuracies compared with all of the other models for the prediction of postoperative complications after oesophagectomy.

DDM-HSA: Dual Deterministic Model-Based Heart Sound Analysis for Daily Life Monitoring

A sudden cardiac event in patients with heart disease can lead to a heart attack in extreme cases. Therefore, prompt interventions for the particular heart situation and periodic monitoring are critical. This study focuses on a heart sound analysis method that can be monitored daily using multimodal signals acquired with wearable devices. The dual deterministic model-based heart sound analysis is designed in a parallel structure that uses two bio-signals (PCG and PPG signals) related to the heartbeat, enabling more accurate heart sound identification. The experimental results show promising performance of the proposed Model III (DDM-HSA with window and envelope filter), which had the highest performance, and S1 and S2 showed average accuracy (unit: %) of 95.39 (±2.14) and 92.55 (±3.74), respectively. The findings of this study are anticipated to provide improved technology to detect heart sounds and analyze cardiac activities using only bio-signals that can be measured using wearable devices in a mobile environment.

An Automatic Premature Ventricular Contraction Recognition System Based on Imbalanced Dataset and Pre-Trained Residual Network Using Transfer Learning on ECG Signal

The development of automatic monitoring and diagnosis systems for cardiac patients over the internet has been facilitated by recent advancements in wearable sensor devices from electrocardiographs (ECGs), which need the use of patient-specific approaches. Premature ventricular contraction (PVC) is a common chronic cardiovascular disease that can cause conditions that are potentially fatal. Therefore, for the diagnosis of likely heart failure, precise PVC detection from ECGs is crucial. In the clinical settings, cardiologists typically employ long-term ECGs as a tool to identify PVCs, where a cardiologist must put in a lot of time and effort to appropriately assess the long-term ECGs which is time consuming and cumbersome. By addressing these issues, we have investigated a deep learning method with a pre-trained deep residual network, ResNet-18, to identify PVCs automatically using transfer learning mechanism. Herein, features are extracted by the inner layers of the network automatically compared to hand-crafted feature extraction methods. Transfer learning mechanism handles the difficulties of required large volume of training data for a deep model. The pre-trained model is evaluated on the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia and Institute of Cardiological Technics (INCART) datasets. First, we used the Pan-Tompkins algorithm to segment 44,103 normal and 6423 PVC beats, as well as 106,239 normal and 9987 PVC beats from the MIT-BIH Arrhythmia and IN-CART datasets, respectively. The pre-trained model employed the segmented beats as input after being converted into 2D (two-dimensional) images. The method is optimized with the using of weighted random samples, on-the-fly augmentation, Adam optimizer, and call back feature. The results from the proposed method demonstrate the satisfactory findings without the using of any complex pre-processing and feature extraction technique as well as design complexity of model. Using LOSOCV (leave one subject out cross-validation), the received accuracies on MIT-BIH and INCART are 99.93% and 99.77%, respectively, suppressing the state-of-the-art methods for PVC recognition on unseen data. This demonstrates the efficacy and generalizability of the proposed method on the imbalanced datasets. Due to the absence of device-specific (patient-specific) information at the evaluating stage on the target datasets in this study, the method might be used as a general approach to handle the situations in which ECG signals are obtained from different patients utilizing a variety of smart sensor devices.

A Robustness Evaluation of Machine Learning Algorithms for ECG Myocardial Infarction Detection

An automatic electrocardiogram (ECG) myocardial infarction detection system needs to satisfy several requirements to be efficient in real-world practice. These requirements, such as reliability, less complexity, and high performance in decision-making, remain very important in a realistic clinical environment. In this study, we investigated an automatic ECG myocardial infarction detection system and presented a new approach to evaluate its robustness and durability performance in classifying the myocardial infarction (with no feature extraction) under different noise types. We employed three well-known supervised machine learning models: support vector machine (SVM), k-nearest neighbors (KNN), and random forest (RF), and tested the performance and robustness of these techniques in classifying normal (NOR) and myocardial infarction (MI) using real ECG records from the PTB database after normalization and segmentation of the data, with a suggested inter-patient paradigm separation as well as noise from the MIT-BIH noise stress test database (NSTDB). Finally, we measured four metrics: accuracy, precision, recall, and F1-score. The simulation revealed that all of the models performed well, with values of over 0.50 at lower SNR levels, in terms of all the metrics investigated against different types of noise, indicating that they are encouraging and acceptable under extreme noise situations are are thus considered sustainable and robust models for specific forms of noise. All of the methods tested could be used as ECG myocardial infarction detection tools in real-world practice under challenging circumstances.

Lightweight Multireceptive Field CNN for 12-Lead ECG Signal Classification

The electrical activity produced during the heartbeat is measured and recorded by an ECG. Cardiologists can interpret the ECG machine’s signals and determine the heart’s health condition and related causes of ECG signal abnormalities. However, cardiologist shortage is a challenge in both developing and developed countries. Moreover, the experience of a cardiologist matters in the accurate interpretation of the ECG signal, as the interpretation of ECG is quite tricky even for experienced doctors. Therefore, developing computer-aided ECG interpretation is required for its wide-reaching effect. 12-lead ECG generates a 1D signal with 12 channels among the well-known time-series data. Classical machine learning can develop automatic detection, but deep learning is more effective in the classification task. 1D-CNN is being widely used for CVDS detection from ECG datasets. However, adopting a deep learning model designed for computer vision can be problematic because of its massive parameters and the need for many samples to train. In many detection tasks ranging from semantic segmentation of medical images to time-series data classification, multireceptive field CNN has improved performance. Notably, the nature of the ECG dataset made performance improvement possible by using a multireceptive field CNN (MRF-CNN). Using MRF-CNN, it is possible to design a model that considers semantic context information within ECG signals with different sizes. As a result, this study has designed a multireceptive field CNN architecture for ECG classification. The proposed multireceptive field CNN architecture can improve the performance of ECG signal classification. We have achieved a 0.72 $F_1$ score and 0.93 AUC for 5 superclasses, a 0.46 $F_1$ score and 0.92 AUC for 20 subclasses, and a 0.31 $F_1$ score and 0.92 AUC for all the diagnostic classes of the PTB-XL dataset.

Classification of multi-lead ECG with deep residual convolutional neural networks

OBJECTIVE

Automatic ECG interpretation based on deep learning methods is attracting increasing attention. In this study, we propose a novel method to accurately classify multi-lead ECGs using deep residual neural networks.

APPROACH

ECG recordings from seven different open databases were provided by PhysioNet/Computing in Cardiology Challenge 2021. All the ECGs were pre-processed to obtain the same sampling rate. The label inconsistency among the databases was corrected by adding or removing specific labels. A label mask was created to filter out potentially incorrectly labelled data. Five models based on deep residual convolutional neural networks were optimized using an asymmetric loss function to classify multi-lead ECGs.

MAIN RESULTS

The proposed method achieved an official challenge score of 0.54, 0.52, 0.50, 0.51, and 0.50 on twelve-lead, six-lead, four-lead, three-lead, and two-lead ECG test sets, respectively. These scores were ranked 5th, 3rd, 7th, 5th and 7th, respectively, in the challenge.

SIGNIFICANCE

The proposed method can correct the differential labeling tendency of databases from different sources and exhibits good generalization for classifying multi-lead ECGs in the hidden test set. The proposed models have the potential for clinical applications.

Automatic detection of arrhythmias from an ECG signal using an auto-encoder and SVM classifier

Millions of people around the world are affected by arrhythmias, which are abnormal activities of the functioning of the heart. Most arrhythmias are harmful to the heart and can suddenly become life-threatening. The electrocardiogram (ECG) is an important non-invasive tool in cardiology for the diagnosis of arrhythmias. This work proposes a computer-aided diagnosis (CAD) system to automatically classify different types of arrhythmias from ECG signals. First, the auto-encoder convolutional network (ACN) model is used, which is based on a one-dimensional convolutional neural network (1D-CNN) that automatically learns the best features from the raw ECG signals. After that, the support vector machine (SVM) classifier is applied to the features learned by the ACN model to improve the detection of arrhythmic beats. This classifier detects four different types of arrhythmias, namely the left bundle branch block (LBBB), right bundle branch block (RBBB), paced beat (PB), and premature ventricular contractions (PVC), along with the normal sinus rhythms (NSR). Among these arrhythmias, PVC is particularly a dangerous type of heartbeat in ECG signals. The performance of the model is measured in terms of accuracy, sensitivity, and precision using a tenfold cross-validation strategy on the MIT-BIH arrhythmia database. The obtained overall accuracy of the SVM classifier was 98.84%. The result of this model is portrayed as a better performance than in other literary works. Thus, this approach may also help in further clinical studies of cardiac cases.

Machine learning for optimized individual survival prediction in resectable upper gastrointestinal cancer

PURPOSE

Surgical oncologists are frequently confronted with the question of expected long-term prognosis. The aim of this study was to apply machine learning algorithms to optimize survival prediction after oncological resection of gastroesophageal cancers.

METHODS

Eligible patients underwent oncological resection of gastric or distal esophageal cancer between 2001 and 2020 at Heidelberg University Hospital, Department of General Surgery. Machine learning methods such as multi-task logistic regression and survival forests were compared with usual algorithms to establish an individual estimation.

RESULTS

The study included 117 variables with a total of 1360 patients. The overall missingness was 1.3%. Out of eight machine learning algorithms, the random survival forest (RSF) performed best with a concordance index of 0.736 and an integrated Brier score of 0.166. The RSF demonstrated a mean area under the curve (AUC) of 0.814 over a time period of 10 years after diagnosis. The most important long-term outcome predictor was lymph node ratio with a mean AUC of 0.730. A numeric risk score was calculated by the RSF for each patient and three risk groups were defined accordingly. Median survival time was 18.8 months in the high-risk group, 44.6 months in the medium-risk group and above 10 years in the low-risk group.

CONCLUSION

The results of this study suggest that RSF is most appropriate to accurately answer the question of long-term prognosis. Furthermore, we could establish a compact risk score model with 20 input parameters and thus provide a clinical tool to improve prediction of oncological outcome after upper gastrointestinal surgery.

Beam Offset Detection in Laser Stake Welding of Tee Joints Using Machine Learning and Spectrometer Measurements

Laser beam welding offers high productivity and relatively low heat input and is one key enabler for efficient manufacturing of sandwich constructions. However, the process is sensitive to how the laser beam is positioned with regards to the joint, and even a small deviation of the laser beam from the correct joint position (beam offset) can cause severe defects in the produced part. With tee joints, the joint is not visible from top side, therefore traditional seam tracking methods are not applicable since they rely on visual information of the joint. Hence, there is a need for a monitoring system that can give early detection of beam offsets and stop the process to avoid defects and reduce scrap. In this paper, a monitoring system using a spectrometer is suggested and the aim is to find correlations between the spectral emissions from the process and beam offsets. The spectrometer produces high dimensional data and it is not obvious how this is related to the beam offsets. A machine learning approach is therefore suggested to find these correlations. A multi-layer perceptron neural network (MLPNN), support vector machine (SVM), learning vector quantization (LVQ), logistic regression (LR), decision tree (DT) and random forest (RF) were evaluated as classifiers. Feature selection by using random forest and non-dominated sorting genetic algorithm II (NSGAII) was applied before feeding the data to the classifiers and the obtained results of the classifiers are compared subsequently. After testing different offsets, an accuracy of 94% was achieved for real-time detection of the laser beam deviations greater than 0.9 mm from the joint center-line.

A Novel Deep-Learning-Based Framework for the Classification of Cardiac Arrhythmia

Cardiovascular diseases (CVDs) are the primary cause of death. Every year, many people die due to heart attacks. The electrocardiogram (ECG) signal plays a vital role in diagnosing CVDs. ECG signals provide us with information about the heartbeat. ECGs can detect cardiac arrhythmia. In this article, a novel deep-learning-based approach is proposed to classify ECG signals as normal and into sixteen arrhythmia classes. The ECG signal is preprocessed and converted into a 2D signal using continuous wavelet transform (CWT). The time–frequency domain representation of the CWT is given to the deep convolutional neural network (D-CNN) with an attention block to extract the spatial features vector (SFV). The attention block is proposed to capture global features. For dimensionality reduction in SFV, a novel clump of features (CoF) framework is proposed. The k-fold cross-validation is applied to obtain the reduced feature vector (RFV), and the RFV is given to the classifier to classify the arrhythmia class. The proposed framework achieves 99.84% accuracy with 100% sensitivity and 99.6% specificity. The proposed algorithm outperforms the state-of-the-art accuracy, F1-score, and sensitivity techniques.

ECG Data Analysis with Denoising Approach and Customized CNNs

In the last decade, the proactive diagnosis of diseases with artificial intelligence and its aligned technologies has been an exciting and fruitful area. One of the areas in medical care where constant monitoring is required is cardiovascular diseases. Arrhythmia, one of the cardiovascular diseases, is generally diagnosed by doctors using Electrocardiography (ECG), which records the heart's rhythm and electrical activity. The use of neural networks has been extensively adopted to identify abnormalities in the last few years. It is found that the probability of detecting arrhythmia increases if the denoised signal is used rather than the raw input signal. This paper compares six filters implemented on ECG signals to improve classification accuracy. Custom convolutional neural networks (CCNNs) are designed to filter ECG data. Extensive experiments are drawn by considering the six ECG filters and the proposed custom CCNN models. Comparative analysis reveals that the proposed models outperform the competitive models in various performance metrics.

Inter-patient arrhythmia identification method with RR-intervals and convolutional neural networks

OBJECTIVE

The arrhythmia identification method based on the U-net has the potential for fast application. The RR-intervals have been proven to improve the performance of single-heartbeat identification methods. However, because both the heartbeats number and location in the input of the U-net are unfixed, the approach based on the U-net cannot use RR-intervals directly. To solve this problem, we proposed a novel method. The proposed method also can identify heartbeats of four classes, including Non-ectopic (N), Supraventricular ectopic beat (SVEB), Ventricular ectopic beat (VEB), and Fusion beat (F).

APPROACH

Our method consists of the pre-processing and the two-stage identification framework. In the pre-processing part, we filtered input signals with a band-pass filter and created the auxiliary waveforms by RR-intervals. In the first stage of the framework, we designed a network to handle input signals and auxiliary waveforms. We proposed a masking operation to separate the input signal into two signals according to the result of the network. The first signal contains heartbeats of SVEB and VEB. The second signal includes heartbeats of N and F. The second stage consists of two networks and can further identify the heartbeats of SVEB, VEB, N, and F from these two signals.

MAIN RESULT

We validated our method on the MIT-BIH arrhythmia database with the inter-patient model. For classes N, SVEB, VEB, and F, our approach achieved F1 scores of 98.26, 68.61, 95.99, and 47.75, respectively. Significant. Our method not only can effectively utilize RR intervals but also can identify multiple arrhythmias.