ECG Database Research Articles

Deep learning hybrid model ECG classification using AlexNet and parallel dual branch fusion network model.

Cardiovascular diseases are a cause of death making it crucial to accurately diagnose them. Electrocardiography plays a role in detecting heart issues such as heart attacks, bundle branch blocks and irregular heart rhythms. Manual analysis of ECGs is prone to mistakes and time consuming, underscoring the importance of automated methods. This study uses AI models like AlexNet and a dual branch model for categorizing ECG signals from the PTB Diagnostic ECG Database. AlexNet achieved a validation accuracy of 98.64% and a test set accuracy of 99% while the dual branch fusion network model achieved a test set accuracy of 99%. Data preprocessing involved standardizing, balancing and reshaping ECG signals. These models exhibited precision, sensitivity and specificity. In comparison to state of the arts' models such as Hybrid AlexNet SVM and DCNN LSTM our proposed models displayed performance. The high accuracy rates of 99% underscore their potential for ECG classification. These results validate the advantages of incorporating learning models into setups for automated ECG analysis providing adaptable solutions for various healthcare settings including rural areas.

Predicting Spontaneous Termination of Atrial Fibrillation Based on Analysis of Standard Electrocardiograms: ASystematic Review.

Forward prediction of atrial fibrillation (AF) termination is a challenging technical problem of increasing significance due to rising AF presentations to emergency departments worldwide. The ability to non-invasively predict which AF episodes will terminate has important implications in terms of clinical decision-making surrounding treatment and admission, with subsequent impacts on hospital capacity and the economic cost of AF hospitalizations. MEDLINE, EMCare, CINAHL, CENTRAL, and SCOPUS were searched on 29 July 2023 for articles where an attempt to predict AF termination was made using standard surface ECG recordings. The final review included 35 articles. Signal processing techniques fit into three broad categories including machine learning (n = 14), entropy analysis (n = 12), and time-frequency/frequency analysis (n = 9). Retrospectively processed ECG data was used in all studies with no prospective validation studies. Most studies (n = 33) utilized the same ECG database, which included recordings that either terminated within 1 min or continued for over 1 h. There was no significant difference in accuracy between groups (H(2) = 0.058, p-value = 0.971). Only one study assessed recordings earlier than several minutes preceding termination, achieving 92% accuracy using the central 10 s of paroxysmal episodes lasting up to 174. No studies attempted to forward predict AF termination in real-time, representing an opportunity for novel prospective validation studies. Multiple signal processing techniques have proven accurate in predicting AF termination utilizing ECG recordings sourced from a database retrospectively.

A deep learning modular ECG approach for cardiologist assisted adjudication of atrial fibrillation and atrial flutter episodes

BackgroundDetection of atrial tachyarrhythmias (ATA) on long-term ECG recordings is a pre-requisite to reduce ATA-related adverse events. However, the burden of editing massive ECG data is not sustainable. Deep Learning (DL) algorithms provide improved performances on resting ECG databases. However, results on long-term Holter recordings are scarce. ObjectiveWe aimed to build and evaluate a DL modular software using ECG features well known to cardiologists with a user interface that allows cardiologists to adjudicate the results and drive a second DL analysis. MethodsUsing a large (n=187 recordings, 249,419 one-minute samples), beat-to-beat annotated, two-lead Holter database, we built a DL algorithm with a modular structure mimicking expert physician ECG interpretation to classify atrial rhythms. The DL network includes 3 modules (cardiac rhythm regularity, electrical atrial waveform, and raw voltage by time data) followed by a decision network and a long-term weighting factor . The algorithm was validated on an external database. ResultsF1 scores of our classifier were 99% for ATA detection, 95% for Atrial fibrillation and 90% for Atrial flutter respectively. Using the external MIT-database, the classifier obtains F1-score of 97% for the NSR class and 96% for the ATA class. Residual errors could be corrected by manual deactivation of one module in 7/15 of the recordings with an accuracy < 90%. ConclusionA DL modular software using ECG features well known to cardiologists provided an excellent overall performance. Clinically significant residual errors were most often related to the classification of the atrial arrhythmia type (fibrillation vs. flutter). The modular structure of the algorithm helped to edit and correct the AI-based first-pass analysis and will provide a basis for explainability.

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.

Delineation of 12-Lead ECG Representative Beats Using Convolutional Encoder-Decoders with Residual and Recurrent Connections.

The aim of this study is to address the challenge of 12-lead ECG delineation by different encoder-decoder architectures of deep neural networks (DNNs). This study compares four concepts for encoder-decoders based on a fully convolutional architecture (CED-Net) and its modifications with a recurrent layer (CED-LSTM-Net), residual connections between symmetrical encoder and decoder feature maps (CED-U-Net), and sequential residual blocks (CED-Res-Net). All DNNs transform 12-lead representative beats to three diagnostic ECG intervals (P-wave, QRS-complex, QT-interval) used for the global delineation of the representative beat (P-onset, P-offset, QRS-onset, QRS-offset, T-offset). All DNNs were trained and optimized using the large PhysioNet ECG database (PTB-XL) under identical conditions, applying an advanced approach for machine-based supervised learning with a reference algorithm for ECG delineation (ETM, Schiller AG, Baar, Switzerland). The test results indicate that all DNN architectures are equally capable of reproducing the reference delineation algorithm's measurements in the diagnostic PTB database with an average P-wave detection accuracy (96.6%) and time and duration errors: mean values (-2.6 to 2.4 ms) and standard deviations (2.9 to 11.4 ms). The validation according to the standard-based evaluation practices of diagnostic electrocardiographs with the CSE database outlines a CED-Net model, which measures P-duration (2.6 ± 11.0 ms), PQ-interval (0.9 ± 5.8 ms), QRS-duration (-2.4 ± 5.4 ms), and QT-interval (-0.7 ± 10.3 ms), which meet all standard tolerances. Noise tests with high-frequency, low-frequency, and power-line frequency noise (50/60 Hz) confirm that CED-Net, CED-Res-Net, and CED-LSTM-Net are robust to all types of noise, mostly presenting a mean duration error < 2.5 ms when compared to measurements without noise. Reduced noise immunity is observed for the U-net architecture. Comparative analysis with other published studies scores this research within the lower range of time errors, highlighting its competitive performance.

The role of beat-by-beat cardiac features in machine learning classification of ischemic heart disease (IHD) in magnetocardiogram (MCG)

Cardiac electrical changes associated with ischemic heart disease (IHD) are subtle and could be detected even in rest condition in magnetocardiography (MCG) which measures weak cardiac magnetic fields. Cardiac features that are derived from MCG recorded from multiple locations on the chest of subjects and some conventional time domain indices are widely used in Machine learning (ML) classifiers to objectively distinguish IHD and control subjects. Most of the earlier studies have employed features that are derived from signal-averaged cardiac beats and have ignored inter-beat information. The present study demonstrates the utility of beat-by-beat features to be useful in classifying IHD subjects (n = 23) and healthy controls (n = 75) in 37-channel MCG data taken under rest condition of subjects. The study reveals the importance of three features (out of eight measured features) namely, the field map angle (FMA) computed from magnetic field map, beat-by-beat variations of alpha angle in the ST-T region and T wave magnitude variations in yielding a better classification accuracy (92.7 %) against that achieved by conventional features (81 %). Further, beat-by-beat features are also found to augment the accuracy in classifying myocardial infarction (MI) Versus control subjects in two public ECG databases (92 % from 88 % and 94 % from 77 %). These demonstrations summarily suggest the importance of beat-by-beat features in clinical diagnosis of ischemia.

Enhancing Fetal Electrocardiogram Signal Extraction Accuracy through a CycleGAN Utilizing Combined CNN-BiLSTM Architecture.

The fetal electrocardiogram (FECG) records changes in the graph of fetal cardiac action potential during conduction, reflecting the developmental status of the fetus in utero and its physiological cardiac activity. Morphological alterations in the FECG can indicate intrauterine hypoxia, fetal distress, and neonatal asphyxia early on, enhancing maternal and fetal safety through prompt clinical intervention, thereby reducing neonatal morbidity and mortality. To reconstruct FECG signals with clear morphological information, this paper proposes a novel deep learning model, CBLS-CycleGAN. The model's generator combines spatial features extracted by the CNN with temporal features extracted by the BiLSTM network, thus ensuring that the reconstructed signals possess combined features with spatial and temporal dependencies. The model's discriminator utilizes PatchGAN, employing small segments of the signal as discriminative inputs to concentrate the training process on capturing signal details. Evaluating the model using two real FECG signal databases, namely "Abdominal and Direct Fetal ECG Database" and "Fetal Electrocardiograms, Direct and Abdominal with Reference Heartbeat Annotations", resulted in a mean MSE and MAE of 0.019 and 0.006, respectively. It detects the FQRS compound wave with a sensitivity, positive predictive value, and F1 of 99.51%, 99.57%, and 99.54%, respectively. This paper's model effectively preserves the morphological information of FECG signals, capturing not only the FQRS compound wave but also the fetal P-wave, T-wave, P-R interval, and ST segment information, providing clinicians with crucial diagnostic insights and a scientific foundation for developing rational treatment protocols.

Power-MF: robust fetal QRS detection from non-invasive fetal electrocardiogram recordings

Objective. Perinatal asphyxia poses a significant risk to neonatal health, necessitating accurate fetal heart rate monitoring for effective detection and management. The current gold standard, cardiotocography, has inherent limitations, highlighting the need for alternative approaches. The emerging technology of non-invasive fetal electrocardiography shows promise as a new sensing technology for fetal cardiac activity, offering potential advancements in the detection and management of perinatal asphyxia. Although algorithms for fetal QRS detection have been developed in the past, only a few of them demonstrate accurate performance in the presence of noise and artifacts. Approach. In this work, we propose Power-MF, a new algorithm for fetal QRS detection combining power spectral density and matched filter techniques. We benchmark Power-MF against three open-source algorithms on two recently published datasets (Abdominal and Direct Fetal ECG Database: ADFECG, subsets B1 Pregnancy and B2 Labour; Non-invasive Multimodal Foetal ECG-Doppler Dataset for Antenatal Cardiology Research: NInFEA). Main results. Our results show that Power-MF outperforms state-of-the-art algorithms on ADFECG (B1 Pregnancy: 99.5% ± 0.5% F1-score, B2 Labour: 98.0% ± 3.0% F1-score) and on NInFEA in three of six electrode configurations by being more robust against noise. Significance. Through this work, we contribute to improving the accuracy and reliability of fetal cardiac monitoring, an essential step toward early detection of perinatal asphyxia with the long-term goal of reducing costs and making prenatal care more accessible.

Multipoint ECG Signal Extraction on Palms and Figures for Human Identification System

The ECG signal contain vital information for cardiac disease which is one of main cause of catastrophic mortality. In conventional technique, the signals are extracted through different points located on the limbs and surface of the chest. The biological impedance of human body eliminates any practical means of making fake copies of the relevant physiological traits. Moreover, this method needs the complex data acquisition system and apparatus as well as inconvenience way of acquisition of signal at the chest. Hence, there is a demand to find out the promising alternative technique to extract the ECG signals in more convenient way with high accuracy. In this paper, the real-time ECG monitor has been developed to extract the signals from the multipoint on the hands and fingers. Placement of the electrodes are done based on the acupressure point on palms and fingers. A total of 120 volunteers were investigated to develop the ECG database as the development dataset. This work uses the template matching algorithm and distance classification method to analyze and to find the best similarities between the developed dataset of ECG biometric signals to improve the identification rate. In order to lessen the noise that was recorded with the ECG signals, signal averaging was used to create ECG databases and templates. The recognition rate rose to 98% accuracy on the development dataset when the prescreening procedure was introduced to create a combined system model. ECG biometric model was created by combining the two models and using the development dataset's results. The algorithm was applied on the entire developed ECG dataset and 96% of accuracy rate was achieved in identification.

PCA-Based Preprocessing for Clustering-Based Fetal Heart Rate Extraction in Non-Invasive Fetal Electrocardiograms

Non-invasive fetal electrocardiography (NI-ECG) is based on the acquisition of signals from electrodes on the mother’s abdominal surface. This abdominal ECG (aECG) signal consists of the maternal ECG (mECG) along with the fetal ECG (fECG) and other noises and artifacts. These records allow the acquisition of valuable and reliable information that helps ensure fetal well-being during pregnancy. This paper proposes a procedure based on principal component analysis (PCA) to obtain a single-channel master abdominal ECG record that can be used as input to fetal heart rate extraction techniques. The new procedure requires three main processing stages: PCA-based analysis for fECG-component extraction, polarity test, and curve fitting. To show the advantages of the proposal, this PCA-based method has been used as the feeding stage to a previously developed clustering-based method for single-channel aECG fetal heart rate monitoring. The results obtained for a set of real abdominal ECG recordings from annotated public aECG databases, the Abdominal and Direct Fetal ECG Database and the Challenge 2013 Training Set A, show improved efficiency in fetal heart rate extraction and illustrate the benefits derived from the use of such a master abdominal ECG channel. This allows us to achieve proper fetal heart rate monitoring without the need for manual inspection and selection of channels to be processed, while also allowing us to analyze records that would have been discarded otherwise.

Application of Convolutional Neural Network for Decoding of 12-Lead Electrocardiogram from a Frequency-Modulated Audio Stream (Sonified ECG).

Research of novel biosignal modalities with application to remote patient monitoring is a subject of state-of-the-art developments. This study is focused on sonified ECG modality, which can be transmitted as an acoustic wave and received by GSM (Global System for Mobile Communications) microphones. Thus, the wireless connection between the patient module and the cloud server can be provided over an audio channel, such as a standard telephone call or audio message. Patients, especially the elderly or visually impaired, can benefit from ECG sonification because the wireless interface is readily available, facilitating the communication and transmission of secure ECG data from the patient monitoring device to the remote server. The aim of this study is to develop an AI-driven algorithm for 12-lead ECG sonification to support diagnostic reliability in the signal processing chain of the audio ECG stream. Our methods present the design of two algorithms: (1) a transformer (ECG-to-Audio) based on the frequency modulation (FM) of eight independent ECG leads in the very low frequency band (300-2700 Hz); and (2) a transformer (Audio-to-ECG) based on a four-layer 1D convolutional neural network (CNN) to decode the audio ECG stream (10 s @ 11 kHz) to the original eight-lead ECG (10 s @ 250 Hz). The CNN model is trained in unsupervised regression mode, searching for the minimum error between the transformed and original ECG signals. The results are reported using the PTB-XL 12-lead ECG database (21,837 recordings), split 50:50 for training and test. The quality of FM-modulated ECG audio is monitored by short-time Fourier transform, and examples are illustrated in this paper and supplementary audio files. The errors of the reconstructed ECG are estimated by a popular ECG diagnostic toolbox. They are substantially low in all ECG leads: amplitude error (quartile range RMSE = 3-7 μV, PRD = 2-5.2%), QRS detector (Se, PPV > 99.7%), P-QRS-T fiducial points' time deviation (<2 ms). Low errors generalized across diverse patients and arrhythmias are a testament to the efficacy of the developments. They support 12-lead ECG sonification as a wireless interface to provide reliable data for diagnostic measurements by automated tools or medical experts.

Analyzing ECG signals in professional football players using machine learning techniques

BackgroundFootball player's health is important, and preventing sudden cardiac arrest may be a critical issue. Professional football players have different ECG signals than the average population, yet there are considerable gaps in study whereas the general population has been extensively studied. Objectives(a) Generate a reference and innovative resting 12-lead ECG database from 54 UEFA PRO level male football players from La Liga. This is a novel approach to cope the ECG and possible arrythmias in athletes. (b) Manage each XML athlete ECG data and develop a free-use program to visualize, denoise and filter the signal with the capacity to automate the labelling of the waves and save the reports. (c) Study the ECG wave shape and generate models through ML to analyse its utility to automate basic diagnosis. MethodsThe dataset collection is based on a prospective observational cohort and includes 10 s, 12-lead ECGs and rhythm and condition labels for each athlete. Physiological sport arrhythmias, T-Wave shape and other findings were studied and labelled. ECG Visualizer was developed and used for 3 machine learning (ML) methods to automate sinus bradycardia arrhythmia diagnosis. ResultsA dataset with 163 ECGs in XML format was collected comprising the Pro Football 12-lead Resting Electrocardiogram Database (PF12RED). “ECG Visualizer” software was developed, and ML was shown to be useful in detecting sinus bradycardia. ConclusionsThe study demonstrates that AI and machine learning can detect simple arrhythmias with accuracy, also it provides a valuable dataset and a free software application.

Application of LightGBM hybrid model based on TPE algorithm optimization in sleep apnea detection.

Sleep apnoea syndrome (SAS) is a serious sleep disorder and early detection of sleep apnoea not only reduces treatment costs but also saves lives. Conventional polysomnography (PSG) is widely regarded as the gold standard diagnostic tool for sleep apnoea. However, this method is expensive, time-consuming and inherently disruptive to sleep. Recent studies have pointed out that ECG analysis is a simple and effective diagnostic method for sleep apnea, which can effectively provide physicians with an aid to diagnosis and reduce patients' suffering. To this end, in this paper proposes a LightGBM hybrid model based on ECG signals for efficient detection of sleep apnea. Firstly, the improved Isolated Forest algorithm is introduced to remove abnormal data and solve the data sample imbalance problem. Secondly, the parameters of LightGBM algorithm are optimised by the improved TPE (Tree-structured Parzen Estimator) algorithm to determine the best parameter configuration of the model. Finally, the fusion model TPE_OptGBM is used to detect sleep apnoea. In the experimental phase, we validated the model based on the sleep apnoea ECG database provided by Phillips-University of Marburg, Germany. The experimental results show that the model proposed in this paper achieves an accuracy of 95.08%, a precision of 94.80%, a recall of 97.51%, and an F1 value of 96.14%. All of these evaluation indicators are better than the current mainstream models, which is expected to assist the doctor's diagnostic process and provide a better medical experience for patients.

Robust algorithm for the detection and classification of QRS complexes with different morphologies using the continuous spline wavelet transform with automatic scale detection

This work presents an algorithm for the detection and classification of QRS complexes based on the continuous wavelet transform (CWT) with splines. This approach can evaluate the CWT at any integer scale and the analysis is not restricted to powers of two. The QRS detector comprises four stages: implementation of CWT with splines, detection of QRS complexes, searching for undetected QRS complexes, and correction of the R wave peak location in detected QRS complexes. After, the onsets and ends of the QRS complexes are detected. The algorithm was evaluated with synthetic ECG and with the manually annotated databases: MIT-BIH Arrhythmia, European ST-T, QT and PTB Diagnostic ECG. Evaluation results of the QRS detector were: MIT-BIH arrhythmia database (109,447 beats analyzed), sensitivity Se = 99.72% and positive predictivity P+ = 99.87%; European ST-T database (790522 beats analyzed), Se = 99.92% and P+ = 99.55% and QT database (86498 beats analyzed), Se = 99.97% and P+ = 99.99%. To evaluate the delineation algorithm of the QRS onset (Qi) and QRS end (J) with the QT and PTB Diagnostic ECG databases, the mean and standard deviations of the differences between the automatic and manual annotated location of these points were calculated. The standard deviations were close to the accepted tolerances for deviations determined by the CSE experts. The proposed algorithm is robust to noise, artifacts and baseline drifts, classifies QRS complexes, automatically selects the CWT scale according to the sampling frequency of the ECG record used, and adapts to changes in the heart rate, amplitude and morphology of QRS complexes.

A new method using deep transfer learning on ECG to predict the response to cardiac resynchronization therapy

Background: Cardiac resynchronization therapy (CRT) has emerged as an effective treatment for heart failure patients with electrical dyssynchrony. However, accurately predicting which patients will respond to CRT remains a challenge. This study explores the application of deep transfer learning techniques to train a predictive model for CRT response. Methods: In this study, the short-time Fourier transform (STFT) technique was employed to transform ECG signals into two-dimensional images. A transfer learning approach was then applied to the MIT-BIT ECG database to pre-train a convolutional neural network (CNN) model. The model was fine-tuned to extract relevant features from the ECG images and then tested on our dataset of CRT patients to predict their response. Results: Seventy-one CRT patients were enrolled in this study. The transfer learning model achieved an accuracy of 72% in distinguishing responders from non-responders in the local dataset. Furthermore, the model showed good sensitivity (0.78) and specificity (0.79) in identifying CRT responders. The performance of our model outperformed clinic guidelines and traditional machine learning approaches. Conclusion: The utilization of ECG images as input and leveraging the power of transfer learning allows for improved accuracy in identifying CRT responders. This approach offers potential for enhancing patient selection and improving the outcomes of CRT.

Binarized spiking neural network optimized with momentum search algorithm for fetal arrhythmia detection and classification from ECG signals

Diagnosing the fetal cardiac abnormalities by fetal electrocardiogram (FECG) is a difficult task, but it is essential to identify the fetus health condition. FECG monitoring is essential to provide accurate information on the state of the fetus. Severe fetal arrhythmia can cause heart failure or death. Therefore, it must be required to identify fetal arrhythmias early. The obtained ECG signals are very noisy and have artifacts from breathing and muscle contraction, which makes ECG extraction difficult. Misdiagnosis of fetal arrhythmias can lead to inappropriate treatment, which may result in further complications. If a defect has occurred in the heart of the fetus, it leads to death. To overcome these issues, Binarized spiking neural network optimized with Momentum search algorithm for Fetal Arrhythmia Detection and Classification from ECG signals is proposed in this manuscript for classifying the output as normal and arrhythmia. Initially, the input ECG signals are considered as Fetal ECG data base. The pre-processed ECG signals are extracted by Hexadecimal Local Adaptive Binary Pattern (HLABP). These extracting features are given to BSNN classifier for categorizing the output as normal and arrhythmia. Generally, BSNN does not adopt any optimization methods to determine the optimal parameters and to guarantee an exact classification. Hence, Momentum search algorithm (MSA) is employed to enhance the weight parameters of BSNN. The proposed technique is activated in python and utilizing some performance metrics, like sensitivity, precision, recall, f-measure, specificity, accuracy compared with existing approaches.

Wavelet transform and deep learning-based obstructive sleep apnea detection from single-lead ECG signals.

Sleep apnea is a common sleep disorder. Traditional testing and diagnosis heavily rely on the expertise of physicians, as well as analysis and statistical interpretation of extensive sleep testing data, resulting in time-consuming and labor-intensive processes. To address the problems of complex feature extraction, data imbalance, and low model capacity, we proposed an automatic sleep apnea classification model (CA-EfficientNet) based on the wavelet transform, a lightweight neural network, and a coordinated attention mechanism. The signal is converted into a time-frequency image by wavelet transform and put into the proposed model for classification. The effects of input time window, wavelet transform type and data balancing on the classification performance are considered, and a cost-sensitive algorithm is introduced to more accurately distinguish between normal and abnormal breathing events. PhysioNet apnea ECG database was used for training and evaluation. The 3-min Frequency B-Spline wavelets transform of ECG signal was carried out, and Dice Loss was used to train the classification model of sleep breathing. The classification accuracy was 93.44%, sensitivity was 88.9%, specificity was 96.2% and most indexes were better than other related work.

Neural network-derived electrocardiographic features have prognostic significance and important phenotypic and genotypic associations

Abstract Background Subtle, prognostically-meaningful ECG features may not be apparent to physicians. In the course of supervised machine learning (ML) training, many thousands of ECG features are identified. These are not limited to conventional ECG parameters and morphology. Purpose To investigate novel neural network (NN)-derived ECG features, that may have clinical, phenotypic and genotypic associations and prognostic significance. Methods We extracted 5120 NN-derived ECG features from an AI-ECG model trained for six simple diagnoses and applied unsupervised machine learning to identify three phenogroups. The derivation set, the Clinical Outcomes in Digital Electrocardiography (CODE) cohort (n = 1,558,421), is a database of ECGs recorded in primary care in Brazil. There were four external validation cohorts. A cohort of British civil servants (WH II, n = 5,066). A longitudinal study of volunteers in the UK (UK Biobank, n = 42,386). A longitudinal cohort of Brazilian public servants (ELSA-Brasil, n = 13,739). Lastly, a cohort of patients with chronic Chagas cardiomyopathy (SaMi-Trop, n = 1,631) . Results In the derivation cohort (CODE), the three phenogroups had significantly different mortality profiles (Figure 1). After adjusting for known covariates, phenogroup B had a 1.2-fold increase in long-term mortality compared to phenogroup A (HR 1.20, 95% CI 1.17-1.23, p &amp;lt; 0.0001). We externally validated our findings in four diverse cohorts. Phenogroup C was poorly represented in the volunteer cohorts and therefore was excluded from those analyses. We found phenogroup B had a significantly greater risk of mortality in all cohorts (Figure 1). We performed a phenome-wide association study (PheWAS) in the UK Biobank. We found ECG phenogroup significantly associated with cardiac and non-cardiac phenotypes, including cardiac chamber volumes and cardiac output (Figure 2A). A single-trait genome-wide association study (GWAS) was conducted. The GWAS yielded four loci (Figure 2B). SCN10A, SCN5A and CAV1 have well described roles in cardiac conduction and arrhythmia. ARHGAP24 has been previously associated with ECG parameters, however, our analysis has identified for the first time ARHGAP24 as a gene associated with a prognostically significant phenogroup. Mendelian randomisation demonstrated the higher risk ECG phenogroup was causally associated with higher odds of atrioventricular (AV) block but lower odds of atrial fibrillation and ischaemic heart disease. Conclusion NN-derived ECG features have important applications beyond the original model from which they are derived and may be transferable and applicable for risk prediction in a wide range of settings, in addition to mortality prediction. We have shown the significant potential of NN-derived ECG features, as a highly transferable and potentially universal risk marker, that may be applied to a wide range of clinical contexts.

Determinants and differences of delay in cardiac resynchronization therapy

Abstract Background Cardiac resynchronization therapy (CRT) is recommended for the treatment of heart failure (HF) patients with reduced ejection fraction and left bundle branch block (LBBB) but is still largely underused which may further deteriorate the HF condition. Studying the impact and factors related to delays in CRT with or without an Implantable cardioverter defibrillator (ICD) is fundamental to enhance CRT implementation in clinical practice. Methods We used a central ECG database together with National patient registries to identify LBBB patients with a QRS duration of more than 150 ms and estimated a class I indication for CRT based on a registered diagnosis of HF and ejection fraction &amp;lt; 35% (baseline date). We compared patient characteristics in those with CRT-D, CRT without defibrillator (CRT-P) and patients with an indication but without CRT. Factors associated with CRT-P or CRT-D were analyzed as well as factors related to delay in CRT utilization. Outcome parameters were HF hospitalization and combined total and CV mortality and the impact of the delay in CRT utilization on outcome was analysed. Results Of 5359 patients with LBBB and QRS &amp;gt; 150ms, 1268 (24%) developed a class I indication for CRT. Of these 31% received a CRT-P, 36% CRT-D and 33% were not implanted. Independent predictors for CRT-P were age &amp;gt; 75 years and for CRT-D ischemic heart failure aetiology, hypertension and male sex. Patients with CRT-D had similar HF hospitalization rate (hazard ratio (HR): 0.95, 95% (CI) 0.80-1.14) as patients with CRT-P. In contrast, patients indicated but not implanted with CRT had a significantly higher prevalence of HF hospitalization (HR: 1.65, CI 1.39-1.96). A delay in CRT use &amp;gt; 365 days (161 patients) from indication (baseline) was associated with increased risk of overall mortality and cardiovascular mortality compared to CRT implantation &amp;lt; 30 days from the indication (HR: 1.64, CI 1.05-2.55 and HR: 1.87, CI 1.10-3.18). Age &amp;gt; 75 years, male sex, paroxysmal atrial fibrillation, diabetes and ischemic heart disease were associated with significant delay in CRT use (&amp;gt;365 days). Conclusion In a large real-world setting, delay in CRT implantation was common and associated with increased mortality. The findings suggest a need for new methods to find and treat HF patients with an indication for CRT.

Abstract 16189: Using Vectorcardiography to Predict Prognosis in Patients With STEMI and Heart Failure

Introduction: There is an unmet need for a non-invasive and cost-effective surveillance tool for characterizing the severity and progression of heart failure (HF) to guide evidence-based therapies. We hypothesize that changes over time in unique parameters extracted using vectorcardiography (VKG) have the potential to predict clinical outcomes in patients with HF. The pathophysiology of HF involves abnormal remodeling and a loss of cardiomyocytes, which may alter the strength and direction of the net depolarization signal. These subtle changes can be elucidated using VKG and correlated with prognosis. We hypothesize a similar approach can be utilized for patients post-STEMI as the underlying pathophysiology - loss of myocardium - is comparable and could serve as an initial proof-of-concept. Methods: We identified 209 patients discharged from Michigan Medicine between 2016 and 2021 with a diagnosis of acute STEMI. For each patient, a single 12-lead EKG pre-STEMI and &gt;1-week post-STEMI were collected. A set of 60 VKG parameters were derived by analyzing features of the QRS complex. We used LASSO regression analysis incorporating clinical variables and VKG parameters to create a predictive model for the composite outcome of mortality or HF at 90 days post-STEMI. Model accuracy was determined by randomly partitioning the data into five folds and running the logistic regression model on all folds but one. Results: Comorbid diabetes (OR = 3.04, p = 0.06), QTc post-STEMI (OR = 2.44, p &lt;0.05), and P wave onset pre-STEMI (OR = 0.41, p &lt; 0.05) were consistently predictive. A logistic regression with just these variables has a raw accuracy of 80.3% and cross-fold validation accuracy of 79.4%. Future work aims to create one of the largest pre-/post-STEMI ECG databases, with over 1,200 patients, which will be used to corroborate the above results and serve as a tool for other investigators to explore. Conclusions: ECG changes before and after a STEMI event can be used to assess the risk of mortality or HF and help guide management. The composite outcome appears to be dominated by variables that are primarily associated with arrhythmogenic death. Future work will focus on pump failure alone and determine VKG parameter predictiveness in HF specifically.