Search

There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed to train NNs, and many ECGs are currently only in paper format, which are not suitable for NN training. We developed a fully-automated online ECG digitisation tool to convert scanned paper ECGs into digital signals. Using automated horizontal and vertical anchor point detection, the algorithm automatically segments the ECG image into separate images for the 12 leads and a dynamical morphological algorithm is then applied to extract the signal of interest. We then validated the performance of the algorithm on 515 digital ECGs, of which 45 were printed, scanned and redigitised. The automated digitisation tool achieved 99.0% correlation between the digitised signals and the ground truth ECG (n = 515 standard 3-by-4 ECGs) after excluding ECGs with overlap of lead signals. Without exclusion, the performance of average correlation was from 90 to 97% across the leads on all 3-by-4 ECGs. There was a 97% correlation for 12-by-1 and 3-by-1 ECG formats after excluding ECGs with overlap of lead signals. Without exclusion, the average correlation of some leads in 12-by-1 ECGs was 60–70% and the average correlation of 3-by-1 ECGs achieved 80–90%. ECGs that were printed, scanned, and redigitised, our tool achieved 96% correlation with the original signals. We have developed and validated a fully-automated, user-friendly, online ECG digitisation tool. Unlike other available tools, this does not require any manual segmentation of ECG signals. Our tool can facilitate the rapid and automated digitisation of large repositories of paper ECGs to allow them to be used for deep learning projects. [ABSTRACT FROM AUTHOR]

Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.

The prevalence of cardiovascular disease (CVD) has surged in recent years, making it the foremost cause of mortality among humans. The Electrocardiogram (ECG), being one of the pivotal diagnostic tools for cardiovascular diseases, is increasingly gaining prominence in the field of machine learning. However, prevailing neural network models frequently disregard the spatial dimension features inherent in ECG signals. In this paper, we propose an ECG autoencoder network architecture incorporating low-rank attention (LRA-autoencoder). It is designed to capture potential spatial features of ECG signals by interpreting the signals from a spatial perspective and extracting correlations between different signal points. Additionally, the low-rank attention block (LRA-block) obtains spatial features of electrocardiogram signals through singular value decomposition, and then assigns these spatial features as weights to the electrocardiogram signals, thereby enhancing the differentiation of features among different categories. Finally, we utilize the ResNet-18 network classifier to assess the performance of the LRA-autoencoder on both the MIT-BIH Arrhythmia and PhysioNet Challenge 2017 datasets. The experimental results reveal that the proposed method demonstrates superior classification performance. The mean accuracy on the MIT-BIH Arrhythmia dataset is as high as 0.997, and the mean accuracy and F 1 -score on the PhysioNet Challenge 2017 dataset are 0.850 and 0.843. [ABSTRACT FROM AUTHOR]

This paper proposes a denoising method based on an adversarial deep learning approach for the post-processing of multi-channel fetal electrocardiogram (ECG) signals. As it's well known, noise leads to misinterpretations of fetal ECG signals and thus limits the use of fetal electrocardiography for healthcare applications. Therefore, denoising algorithms are essential for the exploitation of non-invasive fetal ECG. The proposed method is based on the combination of three end-to-end trained sub-networks to convert noisy fetal ECG signals into clean signals. The first two sub-networks are linked by skip connections and form a deep convolutional network that downsamples the noisy signals into a latent representation and subsequently upsamples this latent representation to recover clean signals. The third sub-network aims to boost the decoder sub-network to generate realistic clean signals. Experiments carried out on synthetic and real data showed that the proposed method improved by the signal-to-noise (SNR) of fetal ECG signals with input SNR ranging from - 30 to 0 dB by an average of 20 dB, and improve fetal signal quality by significantly increasing the number of true detected QRS complexes and halving QRS complex detection errors. [ABSTRACT FROM AUTHOR]

The pulse arrival time (PAT), the difference between the R-peak time of electrocardiogram (ECG) signal and the systolic peak of photoplethysmography (PPG) signal, is an indicator that enables noninvasive and continuous blood pressure estimation. However, it is difficult to accurately measure PAT from ECG and PPG signals because they have inconsistent shapes owing to patient-specific physical characteristics, pathological conditions, and movements. Accordingly, complex preprocessing is required to estimate blood pressure based on PAT. In this paper, as an alternative solution, we propose a noninvasive continuous algorithm using the difference between ECG and PPG as a new feature that can include PAT information. The proposed algorithm is a deep CNN–LSTM-based multitasking machine learning model that outputs simultaneous prediction results of systolic (SBP) and diastolic blood pressures (DBP). We used a total of 48 patients on the PhysioNet website by splitting them into 38 patients for training and 10 patients for testing. The prediction accuracies of SBP and DBP were 0.0 ± 1.6 mmHg and 0.2 ± 1.3 mmHg, respectively. Even though the proposed model was assessed with only 10 patients, this result was satisfied with three guidelines, which are the BHS, AAMI, and IEEE standards for blood pressure measurement devices. [ABSTRACT FROM AUTHOR]

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases ( n = 9854 ECGs) and achieved an F1 score of 95.43% in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations ( + 24 % compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy. [ABSTRACT FROM AUTHOR]

Pretest probability (PTP) for assessing obstructive coronary artery disease (ObCAD) was updated to reduce overestimation. However, standard laboratory findings and electrocardiogram (ECG) raw data as first-line tests have not been evaluated for integration into the PTP estimation. Therefore, this study developed an ensemble model by adopting machine learning (ML) and deep learning (DL) algorithms with clinical, laboratory, and ECG data for the assessment of ObCAD. Data were extracted from the electronic medical records of patients with suspected ObCAD who underwent coronary angiography. With the ML algorithm, 27 clinical and laboratory data were included to identify ObCAD, whereas ECG waveform data were utilized with the DL algorithm. The ensemble method combined the clinical-laboratory and ECG models. We included 7907 patients between 2008 and 2020. The clinical and laboratory model showed an area under the curve (AUC) of 0.747; the ECG model had an AUC of 0.685. The ensemble model demonstrated the highest AUC of 0.767. The sensitivity, specificity, and F1 score of the ensemble model ObCAD were 0.761, 0.625, and 0.696, respectively. It demonstrated good performance and superior prediction over traditional PTP models. This may facilitate personalized decisions for ObCAD assessment and reduce PTP overestimation. [ABSTRACT FROM AUTHOR]

Arrhythmia detection from ECG is an important area of computational ECG analysis. However, although a large number of public ECG recordings are available, most research uses only few datasets, making it difficult to estimate the generalizability of the plethora of ECG classification methods. Furthermore, there is a large variability in the evaluation procedures, as well as lack of insight into whether they could successfully perform in a real-world setup. To address these problems, we propose an open-source, flexible and configurable ECG classification codebase—ECGDL, as one of the first efforts that includes 9 arrhythmia datasets, covering a large number of both morphological and rhythmic arrhythmias, as well as 4 deep neural networks, 4 segmentation techniques and 4 evaluation schemes. We perform a comparative analysis along these framework components to provide a comprehensive perspective into arrhythmia classification, focusing on single-lead ECG as the most recent trend in wireless ECG monitoring. ECGDL unifies the class information representation in datasets by creating a label dictionary. Furthermore, it includes a set of the best-performing deep learning approaches with varying signal segmentation techniques and network architectures. A novel evaluation scheme, inter-patient cross-validation, has also been proposed to perform fair evaluation and comparison of results. [ABSTRACT FROM AUTHOR]

In the pregnant mother and her fetus, chronic prenatal stress results in entrainment of the fetal heartbeat by the maternal heartbeat, quantified by the fetal stress index (FSI). Deep learning (DL) is capable of pattern detection in complex medical data with high accuracy in noisy real-life environments, but little is known about DL's utility in non-invasive biometric monitoring during pregnancy. A recently established self-supervised learning (SSL) approach to DL provides emotional recognition from electrocardiogram (ECG). We hypothesized that SSL will identify chronically stressed mother-fetus dyads from the raw maternal abdominal electrocardiograms (aECG), containing fetal and maternal ECG. Chronically stressed mothers and controls matched at enrolment at 32 weeks of gestation were studied. We validated the chronic stress exposure by psychological inventory, maternal hair cortisol and FSI. We tested two variants of SSL architecture, one trained on the generic ECG features for emotional recognition obtained from public datasets and another transfer-learned on a subset of our data. Our DL models accurately detect the chronic stress exposure group (AUROC = 0.982 ± 0.002), the individual psychological stress score (R2 = 0.943 ± 0.009) and FSI at 34 weeks of gestation (R2 = 0.946 ± 0.013), as well as the maternal hair cortisol at birth reflecting chronic stress exposure (0.931 ± 0.006). The best performance was achieved with the DL model trained on the public dataset and using maternal ECG alone. The present DL approach provides a novel source of physiological insights into complex multi-modal relationships between different regulatory systems exposed to chronic stress. The final DL model can be deployed in low-cost regular ECG biosensors as a simple, ubiquitous early stress detection and monitoring tool during pregnancy. This discovery should enable early behavioral interventions. [ABSTRACT FROM AUTHOR]

Atrial fibrillation (AF) is the most prevalent arrhythmia and is associated with increased morbidity and mortality. Its early detection is challenging because of the low detection yield of conventional methods. We aimed to develop a deep learning-based algorithm to identify AF during normal sinus rhythm (NSR) using 12-lead electrocardiogram (ECG) findings. We developed a new deep neural network to detect subtle differences in paroxysmal AF (PAF) during NSR using digital data from standard 12-lead ECGs. Raw digital data of 2,412 12-lead ECGs were analyzed. The artificial intelligence (AI) model showed that the optimal interval to detect subtle changes in PAF was within 0.24 s before the QRS complex in the 12-lead ECG. We allocated the enrolled ECGs to the training, internal validation, and testing datasets in a 7:1:2 ratio. Regarding AF identification, the AI-based algorithm showed the following values in the internal and external validation datasets: area under the receiver operating characteristic curve, 0.79 and 0.75; recall, 82% and 77%; specificity, 78% and 72%; F1 score, 75% and 74%; and overall accuracy, 72.8% and 71.2%, respectively. The deep learning-based algorithm using 12-lead ECG demonstrated high accuracy for detecting AF during NSR. [ABSTRACT FROM AUTHOR]

Cardiac accessory pathways (APs) in Wolff–Parkinson–White (WPW) syndrome are conventionally diagnosed with decision tree algorithms; however, there are problems with clinical usage. We assessed the efficacy of the artificial intelligence model using electrocardiography (ECG) and chest X-rays to identify the location of APs. We retrospectively used ECG and chest X-rays to analyse 206 patients with WPW syndrome. Each AP location was defined by an electrophysiological study and divided into four classifications. We developed a deep learning model to classify AP locations and compared the accuracy with that of conventional algorithms. Moreover, 1519 chest X-ray samples from other datasets were used for prior learning, and the combined chest X-ray image and ECG data were put into the previous model to evaluate whether the accuracy improved. The convolutional neural network (CNN) model using ECG data was significantly more accurate than the conventional tree algorithm. In the multimodal model, which implemented input from the combined ECG and chest X-ray data, the accuracy was significantly improved. Deep learning with a combination of ECG and chest X-ray data could effectively identify the AP location, which may be a novel deep learning model for a multimodal model. [ABSTRACT FROM AUTHOR]

Detection and delineation are key steps for retrieving and structuring information of the electrocardiogram (ECG), being thus crucial for numerous tasks in clinical practice. Digital signal processing (DSP) algorithms are often considered state-of-the-art for this purpose but require laborious rule readaptation for adapting to unseen morphologies. This work explores the adaptation of the the U-Net, a deep learning (DL) network employed for image segmentation, to electrocardiographic data. The model was trained using PhysioNet's QT database, a small dataset of 105 2-lead ambulatory recordings, while being independently tested for many architectural variations, comprising changes in the model's capacity (depth, width) and inference strategy (single- and multi-lead) in a fivefold cross-validation manner. This work features several regularization techniques to alleviate data scarcity, such as semi-supervised pre-training with low-quality data labels, performing ECG-based data augmentation and applying in-built model regularizers. The best performing configuration reached precisions of 90.12%, 99.14% and 98.25% and recalls of 98.73%, 99.94% and 99.88% for the P, QRS and T waves, respectively, on par with DSP-based approaches. Despite being a data-hungry technique trained on a small dataset, a U-Net based approach demonstrates to be a viable alternative for this task. [ABSTRACT FROM AUTHOR]

Standard 12-lead electrocardiography (ECG) is used as the primary clinical tool to diagnose changes in heart function. The value of automated 12-lead ECG diagnostic approaches lies in their ability to screen the general population and to provide a second opinion for doctors. Yet, the clinical utility of automated ECG interpretations remains limited. We introduce a two-way approach to an automated cardiac disease identification system using standard digital or image 12-lead ECG recordings. Two different network architectures, one trained using digital signals (CNN-dig) and one trained using images (CNN-ima), were generated. An open-source dataset of 41,830 classified standard ECG recordings from patients and volunteers was generated. CNN-ima was trained to identify atrial fibrillation (AF) using 12-lead ECG digital signals and images that were also transformed to mimic mobile device camera-acquired ECG plot snapshots. CNN-dig accurately (92.9–100%) identified every possible combination of the eight most-common cardiac conditions. Both CNN-dig and CNN-ima accurately (98%) detected AF from standard 12-lead ECG digital signals and images, respectively. Similar classification accuracy was achieved with images containing smartphone camera acquisition artifacts. Automated detection of cardiac conditions in standard digital or image 12-lead ECG signals is feasible and may improve current diagnostic methods. [ABSTRACT FROM AUTHOR]

Tracking the fluctuations in blood glucose levels is important for healthy subjects and crucial diabetic patients. Tight glucose monitoring reduces the risk of hypoglycemia, which can result in a series of complications, especially in diabetic patients, such as confusion, irritability, seizure and can even be fatal in specific conditions. Hypoglycemia affects the electrophysiology of the heart. However, due to strong inter-subject heterogeneity, previous studies based on a cohort of subjects failed to deploy electrocardiogram (ECG)-based hypoglycemic detection systems reliably. The current study used personalised medicine approach and Artificial Intelligence (AI) to automatically detect nocturnal hypoglycemia using a few heartbeats of raw ECG signal recorded with non-invasive, wearable devices, in healthy individuals, monitored 24 hours for 14 consecutive days. Additionally, we present a visualisation method enabling clinicians to visualise which part of the ECG signal (e.g., T-wave, ST-interval) is significantly associated with the hypoglycemic event in each subject, overcoming the intelligibility problem of deep-learning methods. These results advance the feasibility of a real-time, non-invasive hypoglycemia alarming system using short excerpts of ECG signal. [ABSTRACT FROM AUTHOR]