Prediction of incident atrial fibrillation using deep learning, clinical models and polygenic scores.

BACKGROUND AND AIMS: Deep learning applied to electrocardiograms (ECG-AI) is an emerging approach for predicting atrial fibrillation or flutter (AF). This study introduces an ECG-AI model developed and tested at a tertiary cardiac centre, comparing its performance with clinical and AF polygenic scores (PGS). METHODS: ECG in sinus rhythm from the Montreal Heart Institute were analysed, excluding those from patients with preexisting AF. The primary outcome was incident AF at 5 years. An ECG-AI model was developed by splitting patients into non-overlapping datasets: 70% for training, 10% for validation, and 20% for testing. Performance of ECG-AI, clinical models and PGS was assessed in the test dataset. The ECG-AI model was externally validated in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) hospital dataset. RESULTS: A total of 669,782 ECGs from 145,323 patients were included. Mean age was 61±15 years, and 58% were male. The primary outcome was observed in 15% of patients and the ECG-AI model showed an area under the receiver operating characteristic curve (AUC) of 0.78. In time-to-event analysis including the first ECG, ECG-AI inference of high risk identified 26% of the population with a 4.3-fold increased risk of incident AF (95% confidence interval 4.02-4.57). In a subgroup analysis of 2,301 patients, ECG-AI outperformed CHARGE-AF (AUC=0.62) and PGS (AUC=0.59). Adding PGS and CHARGE-AF to ECG-AI improved goodness-of-fit (likelihood ratio test p<0.001), with minimal changes to the AUC (0.76-0.77). In the external validation cohort (mean age 59±18 years, 47% male, median follow-up 1.1 year) ECG-AI model performance= remained consistent (AUC=0.77). CONCLUSIONS: ECG-AI provides an accurate tool to predict new-onset AF in a tertiary cardiac centre, surpassing clinical and polygenic scores.

[Race against sudden death : the benefits of pre-participation cardiovascular screening]. / Course contre la mort subite : intérêt du dépistage cardiovasculaire avant une compétition sportive.

Sudden death (SD) in young, apparently healthy athletes under 35 is an underestimated public health problem in Belgium. This is dramatically illustrated by the case of a 28-year old ultra-trail runner who suffered cardiac arrest during training, revealing an unrecognized cardiomyopathy. This highlights the importance of pre-participation cardiovascular screening in identifying such hidden conditions. The variety of causes of SD, mainly of cardiac origin, underlines the complexity of screening and the need to tailor it to the specific risks of each individual. The central issue in screening is the relevance of the resting 12-lead electrocardiogram (ECG). While some countries have adopted it with positive results, others continue to debate its systematic inclusion. Sudden death affects not only professional athletes, but also amateurs, who are often less medically monitored. The aim of cardiovascular screening is twofold: to identify young people at risk, while not unnecessarily limiting access to sport for those with no cardiac pathology. The effectiveness of the ECG is well recognized, but the implementation of such systematic screening in Belgium must take into account certain practical aspects.

La mort subite (MS) chez les jeunes sportifs de moins de 35 ans, en bonne santé apparente, est une problématique de santé publique sous-estimée en Belgique. Cette réalité est dramatiquement illustrée par le cas d'un ultra-traileur de 28 ans, victime d'un arrêt cardiaque lors d'un entraînement, révélant une cardiomyopathie méconnue. Cela met en lumière l'importance d'un dépistage cardiovasculaire pré-participatif pour identifier de telles affections cachées. La variété des causes de MS, principalement d'origine cardiaque, souligne la complexité du dépistage et la nécessité de l'adapter en fonction des risques spécifiques à chaque individu. La question centrale du dépistage est la pertinence de l'électrocardiogramme (ECG) à 12 dérivations de repos. Tandis que certains pays l'ont adopté avec des résultats positifs, d'autres continuent de débattre sur son inclusion systématique. La MS n'affecte pas que les athlètes professionnels, mais aussi les amateurs, souvent moins suivis sur le plan médical. L'objectif du dépistage cardiovasculaire est double : identifier les jeunes à risque, tout en ne limitant pas inutilement l'accès au sport pour ceux dépourvus de pathologie cardiaque. L'efficacité de l'ECG est reconnue, mais la mise en œuvre d'un tel dépistage systématique en Belgique doit tenir compte de certains aspects pratiques.

Association between maternal hypothyroidism, baby birth weight, and adult cardiovascular disease risk: insights from ECG measurements.

OBJECTIVES: Thyroid hormone (TH) deficiency during pregnancy may affect cardiovascular function in offspring rats. This study aimed to evaluate the effect of TH deficiency during gestation, on the electrocardiogram indices of young and middle-aged offspring of male rats. METHODS: Eight female rats were equally divided into hypothyroid and control groups. The hypothyroid mothers received 0.025% 6-propyl-2-thiouracil (PTU) in drinking water throughout pregnancy, while control mothers consumed only tap water. Following birth, male rats from each group were observed for 4 months (young age) and 12 months (middle-aged). The group known as fetal hypothyroid (FH) consisted of rats born from hypothyroid mothers. The serum T4 and TSH concentrations from mothers and newborn male rats were assayed at the end of gestation. Lead II electrocardiogram (ECG) was recorded for 5 minutes using Power Lab, AD Instruments. RESULTS: There was a significant rise in the P wave voltage in young FH rats, whereas, it was decreased in middle-aged control and FH rats. The voltage of QRS decreased and its duration increased in the young and middle-aged FH rats compared to the corresponding control groups. Duration and voltage of the T wave were significantly altered in the young and middle-aged FH groups. PR and QT intervals significantly increased in the young and middle-aged FH groups compared to their controls. CONCLUSIONS: Maternal hypothyroidism affected the electrocardiogram indices of offspring rats, possibly signaling cardiovascular problems later in life.

Cardiovascular disease detection from cardiac arrhythmia ECG signals using artificial intelligence models with hyperparameters tuning methodologies.

Cardiovascular disease (CVD) is connected with irregular cardiac electrical activity, which can be seen in ECG alterations. Due to its convenience and non-invasive aspect, the ECG is routinely exploited to identify different arrhythmias and automatic ECG recognition is needed immediately. In this paper, enhancement for the detection of CVDs such as Ventricular Tachycardia (VT), Premature Ventricular Contraction (PVC) and ST Change (ST) arrhythmia using different dimensionality reduction techniques and multiple classifiers are presented. Three-dimensionality reduction methods, such as Local Linear Embedding (LLE), Diffusion Maps (DM), and Laplacian Eigen (LE), are employed. The dimensionally reduced ECG samples are further feature selected with Cuckoo Search (CS) and Harmonic Search Optimization (HSO) algorithms. A publicly available MIT-BIH (Physionet) - VT database, PVC database, ST Change database and NSR database were used in this work. The cardiac vascular disturbances are classified by using seven classifiers such as Gaussian Mixture Model (GMM), Expectation Maximization (EM), Non-linear Regression (NLR), Logistic Regression (LR), Bayesian Linear Discriminant Analysis (BDLC), Detrended Fluctuation Analysis (Detrended FA), and Firefly. For different classes, the average overall accuracy of the classification techniques is 55.65 % when without CS and HSO feature selection, 64.36 % when CS feature selection is used, and 75.39 % when HSO feature selection is used. Also, to improve the performance of classifiers, the hyperparameters of four classifiers (GMM, EM, BDLC and Firefly) are tuned with the Adam and Grid Search Optimization (GSO) approaches. The average accuracy of classification for the CS feature-based classifiers that used GSO and Adam hyperparameter tuning was 79.92 % and 85.78 %, respectively. The average accuracy of classification for the HSO feature-based classifiers that used GSO and Adam hyperparameter tuning was 86.87 % and 93.77 %, respectively. The performance of the classifier is analyzed based on the accuracy parameter for both with and without feature selection methods and with hyperparameter tuning techniques. In the case of ST vs. NSR, a higher accuracy of 98.92 % is achieved for the LLE dimensionality reduction with HSO feature selection for the GMM classifier with Adam's hyperparameter tuning approach. The GMM classifier with the Adam hyperparameter tuning approach with 98.92 % accuracy in detecting ST vs. NSR cardiac disease is outperforming all other classifiers and methodologies.

How to improve medical students' ECG interpretation skills ? Multicenter survey and results of a comparative study evaluating a new educational approach.

BACKGROUND: Learning to interpret electrocardiograms (ECGs) is a crucial objective in medical education. Despite its importance, errors in ECGs interpretation are common, and the optimal teaching methods have not yet been clearly established. OBJECTIVES: To evaluate students' confidence in ECGs analysis and their opinion on current teaching methods, and to assess the effectiveness of a new ECG educational approach. METHODS: First, we conducted a survey on ECG learning among fourth to sixth-year medical students. Second, a 5-week multicenter comparative study was conducted with fourth-year medical students during their cardiology internship. Two different teaching methods were used, assigned by center. The first group participated in 5-minutes workshops 4 times a week using a "reversed classroom" method, supervised by a cardiologist, where students took turns selecting, presenting and discussing ECGs. The control group attended a single 2-hour face-to-face ECG course. All participants completed a 30-minute ECGs analysis test at baseline and after 5 weeks. RESULTS: Out of 401 survey respondents, the confidence levels in ECG interpretation were 3/5 (IQR 2-3) for routine situations and 2/5 (IQR 1-3) for emergency situations. Satisfaction with ECG teaching was low (2/5, IQR 1-3) and 96.3% of respondents favored more extensive ECG training. In the comparative study, 52 students from 3 medical schools were enrolled (control group: n = 27; workshop group: n = 25). Both groups showed significant improvement in exam scores from baseline to 5-week (33/100 ± 12/100 to 44/100 ± 12/100, p < 0.0001 for the control group and 36/100 ± 13/100 to 62/100 ± 12/100, p < 0.0001 for the workshop group). The improvement was significantly greater in the workshop group compared to the control group (+ 26 ± 11 vs. + 11 ± 6, p < 0.001). CONCLUSIONS: Among French medical students who initially reported low confidence and insufficient skills in ECG interpretation, the workshop approach using a "reversed classroom" method was found to be more effective than conventional lecture-based teaching during cardiology internship.

Intracoronary ECG ST-Segment Shift Remission Time During Reactive Myocardial Hyperemia (Τ-icECG): A New Method to Assess Hemodynamic Coronary Stenosis Severity.

Background-Fractional flow reserve (FFR) measurements are recommended for assessing hemodynamic coronary stenosis severity. Intracoronary ECG (icECG) is easily obtainable and highly sensitive in detecting myocardial ischemia due to its close vicinity to the myocardium. We hypothesized that the remission time of myocardial ischemia on icECG after a controlled coronary occlusion accurately detects hemodynamically relevant coronary stenosis. Methods-This retrospective, observational study included patients with chronic coronary syndrome undergoing hemodynamic coronary stenosis assessment immediately following a strictly 1-minute proximal coronary artery balloon occlusion with simultaneous icECG recording. IcECG was used for a beat-to-beat analysis of the ST-segment shift during reactive hyperemia immediately following balloon deflation. The time from coronary balloon deflation until the ST-segment shift reached 37% of its maximum level, i.e., icECG ST-segment shift remission time(τ-icECG in seconds,s) was obtained by an automatic algorithm. τ-icECG was tested against the simultaneously obtained reactive hyperemia FFR at a threshold of 0.80 as reference parameter. Results-One hundred and thirty-nine icECGs from 120 patients (age 68±10 years) were analysed. Receiver operating characteristic (ROC) analysis of τ-icECG for the detection of hemodynamically relevant coronary stenosis at an FFR of ≤0.80 was performed. The area under the ROC curve was equal to 0.621(p=0.0363) at an optimal τ-icECG threshold of 8s(sensitivity 61%, specificity 67%). τ-icECG correlated inversely and linearly with FFR(p=0.0327). Conclusion-This first proof-of-concept study demonstrates that τ-icECG, a measure of icECG ST segment-shift remission after a 1-minute coronary artery balloon occlusion accurately detects hemodynamically relevant coronary artery stenosis according to FFR at a threshold of ≥8seconds.

LDCNN: A new arrhythmia detection technique with ECG signals using a linear deep convolutional neural network.

The electrocardiogram (ECG) is a fundamental and widely used tool for diagnosing cardiovascular diseases. It involves recording cardiac electrical signals using electrodes, which illustrate the functioning of cardiac muscles during contraction and relaxation phases. ECG is instrumental in identifying abnormal cardiac activity, heart attacks, and various cardiac conditions. Arrhythmia detection, a critical aspect of ECG analysis, entails accurately classifying heartbeats. However, ECG signal analysis demands a high level of expertise, introducing the possibility of human errors in interpretation. Hence, there is a clear need for robust automated detection techniques. Recently, numerous methods have emerged for arrhythmia detection from ECG signals. In our research, we developed a novel one-dimensional deep neural network technique called linear deep convolutional neural network (LDCNN) to identify arrhythmias from ECG signals. We compare our suggested method with several state-of-the-art algorithms for arrhythmia detection. We evaluate our methodology using benchmark datasets, including the PTB Diagnostic ECG and MIT-BIH Arrhythmia databases. Our proposed method achieves high accuracy rates of 99.24% on the PTB Diagnostic ECG dataset and 99.38% on the MIT-BIH Arrhythmia dataset.

[Early classification and recognition algorithm for sudden cardiac arrest based on limited electrocardiogram data trained with a two-stages convolutional neural network].

Sudden cardiac arrest (SCA) is a lethal cardiac arrhythmia that poses a serious threat to human life and health. However, clinical records of sudden cardiac death (SCD) electrocardiogram (ECG) data are extremely limited. This paper proposes an early prediction and classification algorithm for SCA based on deep transfer learning. With limited ECG data, it extracts heart rate variability features before the onset of SCA and utilizes a lightweight convolutional neural network model for pre-training and fine-tuning in two stages of deep transfer learning. This achieves early classification, recognition and prediction of high-risk ECG signals for SCA by neural network models. Based on 16 788 30-second heart rate feature segments from 20 SCA patients and 18 sinus rhythm patients in the international publicly available ECG database, the algorithm performance evaluation through ten-fold cross-validation shows that the average accuracy (Acc), sensitivity (Sen), and specificity (Spe) for predicting the onset of SCA in the 30 minutes prior to the event are 91.79%, 87.00%, and 96.63%, respectively. The average estimation accuracy for different patients reaches 96.58%. Compared to traditional machine learning algorithms reported in existing literatures, the method proposed in this paper helps address the requirement of large training datasets for deep learning models and enables early and accurate detection and identification of high-risk ECG signs before the onset of SCA.

Selection of number of clusters and warping penalty in clustering functional electrocardiogram.

Clustering functional data aims to identify unique functional patterns in the entire domain, but this can be challenging due to phase variability that distorts the observed patterns. Curve registration can be used to remove this variability, but determining the appropriate level of warping flexibility can be complicated. Curve registration also requires a target to which a functional object is aligned, typically the cross-sectional mean of functional objects within the same cluster. However, this mean is unknown prior to clustering. Furthermore, there is a trade-off between flexible warping and the number of resulting clusters. Removing more phase variability through curve registration can lead to fewer remaining variations in the functional data, resulting in a smaller number of clusters. Thus, the optimal number of clusters and warping flexibility cannot be uniquely identified. We propose to use external information to solve the identification issue. We define a cross validated Kullback-Leibler information criterion to select the number of clusters and the warping penalty. The criterion is derived from the predictive classification likelihood considering the joint distribution of both the functional data and external variable and penalizes the uncertainty in the cluster membership. We evaluate our method through simulation and apply it to electrocardiographic data collected in the Chronic Renal Insufficiency Cohort study. We identify two distinct clusters of electrocardiogram (ECG) profiles, with the second cluster exhibiting ST segment depression, an indication of cardiac ischemia, compared to the normal ECG profiles in the first cluster.

Left Ventricular Perforation Following Transcutaneous Pigtail Catheter Placement Mimicking Anterior Wall Myocardial Infarction: An Unusual Complication.

In modern medical practice, procedures that involve the use of catheters are common. These procedures can range from percutaneous coronary and peripheral vascular interventions to using catheters to drain fluid. However, complications associated with catheter usage can arise, and the most severe one is the puncture of a vital organ due to catheter misplacement. In this case, we present a rare complication related to the use of a pigtail catheter, which caused perforation of the left ventricular free wall. The patient presented with an electrocardiogram showing ST segment elevation in the anterior wall, indicative of a heart attack. The patient underwent coronary angiography, which showed that the coronary arteries were unblocked. However, during the procedure, the medical team suspected that the pigtail catheter was stuck in the left ventricle chamber, based on the use of fluoroscopy. This suspicion was later confirmed using computer tomography. To address the issue, the patient underwent an emergent cardiorrhaphy, which was performed immediately. Fortunately, the patient survived the complication.

Monitoring of myocardial injury by serial measurements of QRS area and T area: The MaastrICCht cohort.

BACKGROUND: Manually derived electrocardiographic (ECG) parameters were not associated with mortality in mechanically ventilated COVID-19 patients in earlier studies, while increased high-sensitivity cardiac troponin-T (hs-cTnT) and N-terminal pro-B-type natriuretic peptide (NT-proBNP) were. To provide evidence for vectorcardiography (VCG) measures as potential cardiac monitoring tool, we investigated VCG trajectories during critical illness. METHODS: All mechanically ventilated COVID-19 patients were included in the Maastricht Intensive Care Covid Cohort between March 2020 and October 2021. Serum hs-cTnT and NT-proBNP concentrations were measured daily. Conversion of daily 12-lead ECGs to VCGs by a MATLAB-based script provided QRS area, T area, maximal QRS amplitude, and QRS duration. Linear mixed-effect models investigated trajectories in serum and VCG markers over time between non-survivors and survivors, adjusted for confounders. RESULTS: In 322 patients, 5461 hs-cTnT, 5435 NT-proBNP concentrations and 3280 ECGs and VCGs were analyzed. Non-survivors had higher hs-cTnT concentrations at intubation and both hs-cTnT and NT-proBNP significantly increased compared with survivors. In non-survivors, the following VCG parameters decreased more when compared to survivors: QRS area (-0.27 (95% CI) (-0.37 to -0.16, p < .01) µVs per day), T area (-0.39 (-0.62 to -0.16, p < .01) µVs per day), and maximal QRS amplitude (-0.01 (-0.01 to -0.01, p < .01) mV per day). QRS duration did not differ. CONCLUSION: VCG-derived QRS area and T area decreased in non-survivors compared with survivors, suggesting that an increase in myocardial damage and tissue loss play a role in the course of critical illness and may drive mortality. These VCG markers may be used to monitor critically ill patients.

Conv-RGNN: An efficient Convolutional Residual Graph Neural Network for ECG classification.

BACKGROUND AND OBJECTIVE: Electrocardiogram (ECG) analysis is crucial in diagnosing cardiovascular diseases (CVDs). It is important to consider both temporal and spatial features in ECG analysis to improve automated CVDs diagnosis. Significant progress has been made in automated CVDs diagnosis based on ECG with the continuous development of deep learning. Current most researches often treat 12-lead ECG signals as synchronous sequences in Euclidean space, focusing primarily on extracting temporal features while overlooking the spatial relationships among the 12-lead. However, the spatial distribution of 12-lead ECG electrodes can be more naturally represented using non-Euclidean data structures, which makes the relationships among leads more consistent with their intrinsic characteristics. METHODS: This study proposes an innovative method, Convolutional Residual Graph Neural Network (Conv-RGNN), for ECG classification. The first step is to segment the 12-lead ECG into twelve single-lead ECG, which are then mapped to nodes in a graph that captures the relationships between the different leads through spatial connections, resulting in the 12-lead ECG graph. The graph is then used as input for Conv-RGNN. A convolutional neural network with a position attention mechanism is used to extract temporal sequence information and selectively integrate contextual information to enhance semantic features at different positions. The spatial features of the 12-lead ECG graph are extracted using the residual graph neural network. RESULTS: The experimental results indicate that Conv-RGNN is highly competitive in two multi-label datasets and one single-label dataset, demonstrating exceptional parameter efficiency, inference speed, model performance, and robustness. CONCLUSION: The Conv-RGNN proposed in this paper offer a promising and feasible approach for intelligent diagnosis in resource-constrained environments.

Exploring the Interplay between Extracellular pH and Dronedarone's Pharmacological Effects on Cardiac Function.

Dronedarone (DRN) is a clinically used drug to mitigate arrhythmias with multichannel block properties, including the sodium channel Nav1.5. Extracellular acidification is known to change the pharmacological properties of several antiarrhythmic drugs. Here, we explore how modification in extracellular pH (pHe) shapes the pharmacological profile of DRN upon Nav1.5 sodium current (INa) and in the ex vivo heart preparation. Embryonic human kidney cells (HEK293T/17) were used to transiently express the Nav1.5 α-subunit. Patch-Clamp technique was employed to study INa. Neurotoxin-II (ATX-II) was used to induce the late sodium current (INaLate). Additionally, ex vivo Wistar male rat preparations in the Langendorff system were utilized to study electrocardiogram (ECG) waves. DRN preferentially binds to the closed state inactivation mode of Nav1.5 at pHe 7.0. The recovery from INa inactivation was delayed in the presence of DRN in both pHe 7.0 and 7.4, and the use-dependent properties were distinct at pHe 7.0 and 7.4. However, the potency of DRN upon the peak INa, the voltage dependence for activation, and the steady-state inactivation curves were not altered in both pHe tested. Also, the pHe did not change the ability of DRN to block INaLate. Lastly, DRN in a concentration and pH dependent manner modulated the QRS complex, QT and RR interval in clinically relevant concentration. Thus, the pharmacological properties of DRN upon Nav1.5 and ex vivo heart preparation partially depend on the pHe. The pHe changed the biological effect of DRN in the heart electrical function in relevant clinical concentration.

Clinical usability of deep learning-based saliency maps for occlusion myocardial infarction identification from the prehospital 12-Lead electrocardiogram.

INTRODUCTION: Deep learning (DL) models offer improved performance in electrocardiogram (ECG)-based classification over rule-based methods. However, for widespread adoption by clinicians, explainability methods, like saliency maps, are essential. METHODS: On a subset of 100 ECGs from patients with chest pain, we generated saliency maps using a previously validated convolutional neural network for occlusion myocardial infarction (OMI) classification. Three clinicians reviewed ECG-saliency map dyads, first assessing the likelihood of OMI from standard ECGs and then evaluating clinical relevance and helpfulness of the saliency maps, as well as their confidence in the model's predictions. Questions were answered on a Likert scale ranging from +3 (most useful/relevant) to -3 (least useful/relevant). RESULTS: The adjudicated accuracy of the three clinicians matched the DL model when considering area under the receiver operating characteristics curve (AUC) and F1 score (AUC 0.855 vs. 0.872, F1 score = 0.789 vs. 0.747). On average, clinicians found saliency maps slightly clinically relevant (0.96 ± 0.92) and slightly helpful (0.66 ± 0.98) in identifying or ruling out OMI but had higher confidence in the model's predictions (1.71 ± 0.56). Clinicians noted that leads I and aVL were often emphasized, even when obvious ST changes were present in other leads. CONCLUSION: In this clinical usability study, clinicians deemed saliency maps somewhat helpful in enhancing explainability of DL-based ECG models. The spatial convolutional layers across the 12 leads in these models appear to contribute to the discrepancy between ECG segments considered most relevant by clinicians and segments that drove DL model predictions.

3DECG-Net: ECG fusion network for multi-label cardiac arrhythmia detection.

Cardiovascular diseases represent the leading global cause of death, typically diagnosed and addressed through electrocardiograms (ECG), which record the heart's electrical activity. In recent years, there has been a notable surge in ECG recordings, driven by the widespread use of wearable devices. However, the limited availability of medical experts to analyze these recordings underscores the necessity for automated ECG analysis using computer-aided methods. In this study, we introduced 3DECG-Net, a deep learning model designed to detect and classify seven distinct heart states through the analysis of data fusion from 12-lead ECG in a multi-label framework. Our model leverages a residual architecture with a multi-head attention mechanism, undergoing training within a five-fold cross-validation scheme. By transforming 12-lead ECG signals into 3D data with the help of Recurrent Plot technique, 3DECG-Net achieves a noteworthy micro F1-score of 80.3 %, surpassing the performance of other state-of-the-art deep learning models developed for this specific task. Also, we present an ECG preprocessing framework to generate compact, high-quality ECG signals for potential application in future studies within this domain. We conduct an explainable AI experiment using Local Interpretable Model-agnostic Explanations (LIME) to elucidate the significance of each lead in accurately diagnosing specific arrhythmias, ensuring the logical processing of ECG data by 3DECG-Net. The findings of this study suggest that the proposed model is trustworthy and has the potential to be used as an effective diagnostic toolset for identifying heart arrhythmias. Its effectiveness can improve the diagnostic process, facilitate early treatment, and enhance overall efficiency in medical settings.

How to perform an electrocardiogram in an awake pond slider turtle (Trachemys scripta): a comparative study of five noninvasive methodologies.

OBJECTIVE: To compare multiple noninvasive ECG methods in pond sliders based upon repeatability, ability to recognize standard waveforms, and measurability. METHODS: The study was performed from November 2023 through January 2024. Ten healthy adult pond turtles were enrolled in the study. ECG tracings were obtained using 4 previously reported and 1 novel ECG methodology, using adhesive patches applied to the prehumeral fossae and abdominal scutes. The 50 ECG tracings were blinded by method and turtle, randomized for evaluation by 4 observers, and assessed for quality on a scale from 0 to 3. RESULTS: Interobserver and intraobserver intraclass correlation coefficients for all tracings were 0.84 and 0.97, respectively, indicating an almost perfect agreement. The average score amongst the observers for each tracing was then averaged by method, ranging from 0.875 to 2.15. The novel method demonstrated a collective average of 2.15 and was the highest scoring method for 8 of 10 turtles. CONCLUSIONS: Electrocardiogram utilizing methods that apply adhesive patches to the prehumeral fossae and either the abdominal scutes of the plastron or prefemoral fossae in pond turtles can be performed to produce recognizable waveforms. CLINICAL RELEVANCE: Diagnostic tools, such as ECGs, are imperative to enhance veterinary care in nonconventional species, particularly with the rising trend of exotic pets worldwide.

HEART Score: Prospective Evaluation of Its Accuracy and Applicability.

Background: The History, Electrocardiogram, Age, Risk factors, and Troponin I (HEART) score is a simple method to risk stratify patients with chest pain according to the risk for incidence of major adverse cardiac events (MACEs). Materials and methods: A 202-patient prospective, single center study at Sri Siddhartha Medical College, Tumkur. Patients included were those who were presented to the emergency department (ED) due to non-traumatic chest pain, irrespective of age or any previous medical treatments, and were later referred to the cardiac care unit (CCU), cardiology department (CD). The end point of the study was the incidence of MACE. Results: There was a high occurrence of endpoint-myocardial infarction (MI) as MACE among patients with a high-risk HEART score (p < 0.001). About 52 patients (81.3%) who had MI had a high-risk score and 2 patients (3.1%) who had an endpoint of MI had a low-risk score. Sensitivity of HEART score to anticipate MACE was 91%, and the specificity was 80%. Conclusions: Our prospective study demonstrates the high sensitivity of the HEART score to effectively risk stratify patients and project the phenomenon of MACE. We support the use of the HEART score as a fast and accurate risk stratification tool in the ED. How to cite this article: Anwar I, Sony D. HEART Score: Prospective Evaluation of Its Accuracy and Applicability. Indian J Crit Care Med 2024;28(8):748-752.

Review on spiking neural network-based ECG classification methods for low-power environments.

This paper reviews arrhythmia classification studies using electrocardiogram (ECG) signals. Research on automatically diagnosing arrhythmia in daily life has been actively underway for early detection and treatment of heart disease. Development of automatic arrhythmia classification using ECG signal began based on handcrafted morphological feature extraction and machine learning-based classification methods. As deep neural networks (DNN) show excellent performance in the signal processing field, studies using various types of DNN are also being conducted in ECG classification. However, these DNN-based studies have extremely high computational complexity, making it challenging to perform real-time classification, and are unsuitable for low-power environments such as wearable devices due to high power consumption. Currently, research based on spiking neural network (SNN), which mimics the low-power operation of the human nervous system, is attracting attention as a method that can dramatically reduce complexity and power consumption. The classification accuracy of the SNN-based ECG classification studies is close to that of the DNN-based studies. When combined with neuromorphic hardware, it shows ultra-low-power performance, suggesting the possibility of use in lightweight devices. In this paper, the SNN-based ECG classification studies for low-power environments are mainly reviewed, and prior to this, conventional and DNN-based ECG classification studies are also reviewed. We hope that this review will be helpful to researchers and engineers interested in the field of ECG classification.

Assessing the Reliability of Machine Learning Explanations in ECG Analysis Through Feature Attribution.

Feature attribution methods stand as a popular approach for explaining the decisions made by convolutional neural networks. Given their nature as local explainability tools, these methods fall short in providing a systematic evaluation of their global meaningfulness. This limitation often gives rise to confirmation bias, where explanations are crafted after the fact. Consequently, we conducted a systematic investigation of feature attribution methods within the realm of electrocardiogram time series, focusing on R-peak, T-wave, and P-wave. Using a simulated dataset with modifications limited to the R-peak and T-wave, we evaluated the performance of various feature attribution techniques across two CNN architectures and explainability frameworks. Extending our analysis to real-world data revealed that, while feature attribution maps effectively highlight significant regions, their clarity is lacking, even under the simulated ideal conditions, resulting in blurry representations.

Benchmarking Approaches: Time Series Versus Feature-Based Machine Learning in ECG Analysis on the PTB-XL Dataset.

Extensive research has been conducted on time series and tabular data in the context of classification tasks, considering their distinct data domains. While feature extraction enables the transformation of series into tabular data, direct comparative comparisons between these data types remain scarce. Especially in the domain of medical data, such as electrocardiograms (ECGs), deep learning faces challenges due to its lack of easy and fast interpretability and explainability. However, these are crucial aspects for a wide and reliable adoption in the field. In our study, we assess the performance of XGBoost and InceptionTime on ECG features and time series data respectively. Our findings reveal that features extracted from ECG signals not only achieve competitive performance but also retain advantages during training and inference. These advantages encompass accuracy, resource efficiency, stability, and a high level of explainability.