DeepMiceTL: a deep transfer learning based prediction of mice cardiac conduction diseases using early electrocardiograms.

Cardiac conduction disease is a major cause of morbidity and mortality worldwide. There is considerable clinical significance and an emerging need of early detection of these diseases for preventive treatment success before more severe arrhythmias occur. However, developing such early screening tools is challenging due to the lack of early electrocardiograms (ECGs) before symptoms occur in patients. Mouse models are widely used in cardiac arrhythmia research. The goal of this paper is to develop deep learning models to predict cardiac conduction diseases in mice using their early ECGs. We hypothesize that mutant mice present subtle abnormalities in their early ECGs before severe arrhythmias present. These subtle patterns can be detected by deep learning though they are hard to be identified by human eyes. We propose a deep transfer learning model, DeepMiceTL, which leverages knowledge from human ECGs to learn mouse ECG patterns. We further apply the Bayesian optimization and $k$-fold cross validation methods to tune the hyperparameters of the DeepMiceTL. Our results show that DeepMiceTL achieves a promising performance (F1-score: 83.8%, accuracy: 84.8%) in predicting the occurrence of cardiac conduction diseases using early mouse ECGs. This study is among the first efforts that use state-of-the-art deep transfer learning to identify ECG patterns during the early course of cardiac conduction disease in mice. Our approach not only could help in cardiac conduction disease research in mice, but also suggest a feasibility for early clinical diagnosis of human cardiac conduction diseases and other types of cardiac arrythmias using deep transfer learning in the future.

QRS-T angle: is it a specific parameter associated with sudden cardiac death in type 2 diabetes? Results from the SURDIAGENE and the Mini-Finland prospective cohorts.

AIMS/HYPOTHESIS: Type 2 diabetes is associated with a high risk of sudden cardiac death (SCD), but the risk of dying from another cause (non-SCD) is proportionally even higher. The aim of the study was to identify easily available ECG-derived features associated with SCD, while considering the competing risk of dying from non-SCD causes. METHODS: In the SURDIAGENE (Survie, Diabete de type 2 et Genetique) French prospective cohort of individuals with type 2 diabetes, 15 baseline ECG parameters were interpreted among 1362 participants (mean age 65 years; HbA1c 62±17 mmol/mol [7.8±1.5%]; 58% male). Competing risk models assessed the prognostic value of clinical and ECG parameters for SCD after adjusting for age, sex, history of myocardial infarction, N-terminal pro b-type natriuretic peptide (NT-proBNP), HbA1c and eGFR. The prospective Mini-Finland cohort study was used to externally validate our findings. RESULTS: During median follow-up of 7.4 years, 494 deaths occurred including 94 SCDs. After adjustment, frontal QRS-T angle ≥90° (sub-distribution HR [sHR] 1.68 [95% CI 1.04, 2.69], p=0.032) and NT-proBNP level (sHR 1.26 [95% CI 1.06, 1.50] per 1 log, p=0.009) were significantly associated with a higher risk of SCD. Nevertheless, frontal QRS-T angle was the only marker not to be associated with causes of death other than SCD (sHR 1.08 [95% CI 0.84, 1.39], p=0.553 ). These findings were replicated in the Mini-Finland study subset of participants with diabetes (sHR 2.22 [95% CI 1.05, 4.71], p=0.04 for SCD and no association for other causes of death). CONCLUSIONS/INTERPRETATION: QRS-T angle was specifically associated with SCD risk and not with other causes of death, opening an avenue for refining SCD risk stratification in individuals with type 2 diabetes.

Prediction of Shock-Refractory Ventricular Fibrillation During Resuscitation of Out-of-Hospital Cardiac Arrest.

BACKGROUND: Out-of-hospital cardiac arrest due to shock-refractory ventricular fibrillation (VF) is associated with relatively poor survival. The ability to predict refractory VF (requiring ≥3 shocks) in advance of repeated shock failure could enable preemptive targeted interventions aimed at improving outcome, such as earlier administration of antiarrhythmics, reconsideration of epinephrine use or dosage, changes in shock delivery strategy, or expedited invasive treatments. METHODS: We conducted a cohort study of VF out-of-hospital cardiac arrest to develop an ECG-based algorithm to predict patients with refractory VF. Patients with available defibrillator recordings were randomized 80%/20% into training/test groups. A random forest classifier applied to 3-s ECG segments immediately before and 1 minute after the initial shock during cardiopulmonary resuscitation was used to predict the need for ≥3 shocks based on singular value decompositions of ECG wavelet transforms. Performance was quantified by area under the receiver operating characteristic curve. RESULTS: Of 1376 patients with VF out-of-hospital cardiac arrest, 311 (23%) were female, 864 (63%) experienced refractory VF, and 591 (43%) achieved functional neurological survival. Total shock count was associated with decreasing likelihood of functional neurological survival, with a relative risk of 0.95 (95% CI, 0.93-0.97) for each successive shock (P<0.001). In the 275 test patients, the area under the receiver operating characteristic curve for predicting refractory VF was 0.85 (95% CI, 0.79-0.89), with specificity of 91%, sensitivity of 63%, and a positive likelihood ratio of 6.7. CONCLUSIONS: A machine learning algorithm using ECGs surrounding the initial shock predicts patients likely to experience refractory VF, and could enable rescuers to preemptively target interventions to potentially improve resuscitation outcome.

Subclinical Atrial Fibrillation: A Silent Threat with Uncertain Implications.

Atrial fibrillation (AF) is one of the most common cardiac arrhythmias. Implantable and wearable cardiac devices have enabled the detection of asymptomatic AF episodes-termed subclinical AF (SCAF). SCAF, the prevalence of which is likely significantly underestimated, is associated with increased cardiovascular and all-cause mortality and a significant stroke risk. Recent advances in machine learning, namely artificial intelligence-enabled ECG (AI-ECG), have enabled identification of patients at higher likelihood of SCAF. Leveraging the capabilities of AI-ECG algorithms to drive screening protocols could eventually allow for earlier detection and treatment and help reduce the burden associated with AF.

Beating the heart failure odds: long-term survival after myocardial ischemia in juvenile rainbow trout.

Salmonid fish include some of the most valued cultured fish species worldwide. Unlike most other fish, the hearts of salmonids, including Atlantic salmon and rainbow trout, have a well-developed coronary circulation. Consequently, their hearts' reliance on oxygenation through coronary arteries leaves them prone to coronary lesions, believed to precipitate myocardial ischemia. Here, we mimicked such coronary lesions by subjecting groups of juvenile rainbow trout to coronary ligation, assessing histomorphological myocardial changes associated with ischemia and scarring in the context of cardiac arrhythmias using electrocardiography (ECG). Notable ECG changes resembling myocardial ischemia-like ECG in humans, such as atrioventricular blocks and abnormal ventricular depolarization (prolonged and fragmented QRS complex), as well as repolarization (long QT interval) patterns, were observed during the acute phase of myocardial ischemia. A remarkable 100% survival rate was observed among juvenile trout subjected to coronary ligation after 24 wk. Recovery from coronary ligation occurred through adaptive ventricular remodeling, coupled with a fast cardiac revascularization response. These findings carry significant implications for understanding the mechanisms governing cardiac health in salmonid fish, a family particularly susceptible to cardiac diseases. Furthermore, our results provide valuable insights into comparative studies on the evolution, pathophysiology, and ontogeny of vertebrate cardiac repair and restoration.NEW & NOTEWORTHY Juvenile rainbow trout exhibit a remarkable capacity to recover from cardiac injury caused by myocardial ischemia. Recovery from cardiac damage occurs through adaptive ventricular remodeling, coupled with a rapid cardiac revascularization response. These findings carry significant implications for understanding the mechanisms governing cardiac health within salmonid fishes, which are particularly susceptible to cardiac diseases.

Accessory pathway localization with probabilistic density maps generated by a mobile application: Assessment of a full pre-excitation net-vector method.

INTRODUCTION: Precise electrocardiographic localization of accessory pathways (AP) can be challenging. Seminal AP localization studies were limited by complexity of algorithms and sample size. We aimed to create a nonalgorithmic method for AP localization based on color-coded maps of AP distribution generated by a web-based application. METHODS: APs were categorized into 19 regions/types based on invasive electrophysiologic mapping. Preexcited QRS complexes were categorized into 6 types based on polarity and notch/slur. For each QRS type in each lead the distribution of APs was visualized on a gradient map. The principle of common set was used to combine the single lead maps to create the distribution map for AP with any combination of QRS types in several leads. For the validation phase, a separate cohort of APs was obtained. RESULTS: A total of 800 patients with overt APs were studied. The application used the exploratory data set of 553 consecutive APs and the corresponding QRS complexes to generate AP localization maps for any possible combination of QRS types in 12 leads. Optimized approach (on average 3 steps) for evaluation of preexcited electrcardiogram was developed. The area of maximum probability of AP localization was pinpointed by providing the QRS type for the subsequent leads. The exploratory data set was validated with the separate cohort of APs (n = 256); p = .23 for difference in AP distribution. CONCLUSIONS: In the largest data set of APs to-date, a novel probabilistic and semi-automatic approach to electrocardiographic localization of APs was highly predictive for anatomic localization.

Electrocardiographic abnormalities in patients with cardiomyopathies.

Abnormalities in impulse generation and transmission are among the first signs of cardiac remodeling in cardiomyopathies. Accordingly, 12-lead electrocardiogram (ECG) of patients with cardiomyopathies may show multiple abnormalities. Some findings are suggestive of specific disorders, such as the discrepancy between QRS voltages and left ventricular (LV) mass for cardiac amyloidosis or the inverted T waves in the right precordial leads for arrhythmogenic cardiomyopathy. Other findings are less sensitive and/or specific, but may orient toward a specific diagnosis in a patient with a specific phenotype, such as an increased LV wall thickness or a dilated LV. A "cardiomyopathy-oriented" mindset to ECG reading is important to detect the possible signs of an underlying cardiomyopathy and to interpret correctly the meaning of these alterations, which differs in patients with cardiomyopathies or other conditions.

Use of the energy waveform electrocardiogram to detect subclinical left ventricular dysfunction in patients with type 2 diabetes mellitus.

BACKGROUND: Recent guidelines propose N-terminal pro-B-type natriuretic peptide (NT-proBNP) for recognition of asymptomatic left ventricular (LV) dysfunction (Stage B Heart Failure, SBHF) in type 2 diabetes mellitus (T2DM). Wavelet Transform based signal-processing transforms electrocardiogram (ECG) waveforms into an energy distribution waveform (ew)ECG, providing frequency and energy features that machine learning can use as additional inputs to improve the identification of SBHF. Accordingly, we sought whether machine learning model based on ewECG features was superior to NT-proBNP, as well as a conventional screening tool-the Atherosclerosis Risk in Communities (ARIC) HF risk score, in SBHF screening among patients with T2DM. METHODS: Participants in two clinical trials of SBHF (defined as diastolic dysfunction [DD], reduced global longitudinal strain [GLS ≤ 18%] or LV hypertrophy [LVH]) in T2DM underwent 12-lead ECG with additional ewECG feature and echocardiography. Supervised machine learning was adopted to identify the optimal combination of ewECG extracted features for SBHF screening in 178 participants in one trial and tested in 97 participants in the other trial. The accuracy of the ewECG model in SBHF screening was compared with NT-proBNP and ARIC HF. RESULTS: SBHF was identified in 128 (72%) participants in the training dataset (median 72 years, 41% female) and 64 (66%) in the validation dataset (median 70 years, 43% female). Fifteen ewECG features showed an area under the curve (AUC) of 0.81 (95% CI 0.787-0.794) in identifying SBHF, significantly better than both NT-proBNP (AUC 0.56, 95% CI 0.44-0.68, p < 0.001) and ARIC HF (AUC 0.67, 95%CI 0.56-0.79, p = 0.002). ewECG features were also led to robust models screening for DD (AUC 0.74, 95% CI 0.73-0.74), reduced GLS (AUC 0.76, 95% CI 0.73-0.74) and LVH (AUC 0.90, 95% CI 0.88-0.89). CONCLUSIONS: Machine learning based modelling using additional ewECG extracted features are superior to NT-proBNP and ARIC HF in SBHF screening among patients with T2DM, providing an alternative HF screening strategy for asymptomatic patients and potentially act as a guidance tool to determine those who required echocardiogram to confirm diagnosis. Trial registration LEAVE-DM, ACTRN 12619001393145 and Vic-ELF, ACTRN 12617000116325.

Hyperventilation testing in the diagnosis of vasospastic angina: A clinical review and meta-analysis.

BACKGROUND: Given the limited access to invasive vasospastic reactivity testing in Western Countries, there is a need to further develop alternative non-invasive diagnostic methods for vasospastic angina (VSA). Hyperventilation testing (HVT) is defined as a class IIa recommendation to diagnose VSA by the Japanese Society of Cardiology. METHODS: In this systematic review and meta-analysis reported according to the PRISMA statement, we review the mechanisms, methods, modalities and diagnostic accuracy of non-invasive HVT for the diagnostic of VSA. RESULTS: A total of 106 articles published between 1980 and 2022 about VSA and HVT were included in the systematic review, among which 16 were included in the meta-analysis for diagnostic accuracy. Twelve electrocardiogram-HVT studies including 804 patients showed a pooled sensitivity of 54% (95% confidence intervals [CI]; 30%-76%) and a pooled specificity of 99% (95% CI; 88%-100%). Four transthoracic echocardiography-HVT studies including 197 patients revealed a pooled sensitivity of 90% (95% CI; 82%-94%) and a pooled specificity of 98% (95% CI; 86%-100%). Six myocardial perfusion imaging-HVT studies including 112 patients yielded a pooled sensitivity of 95% (95% CI; 63%-100%) and a pooled specificity of 78% (95% CI; 19%-98%). Non-invasive HVT resulted in a low rate of adverse events, ventricular arrhythmias being the most frequently reported, and were resolved with the administration of nitroglycerin. CONCLUSIONS: Non-invasive HVT offers a safe alternative with high diagnostic accuracy to diagnose VSA in patients with otherwise undiagnosed causes of chest pain.

Detection of focal to bilateral tonic-clonic seizures using a connected shirt.

OBJECTIVE: This study was undertaken to develop and evaluate a machine learning-based algorithm for the detection of focal to bilateral tonic-clonic seizures (FBTCS) using a novel multimodal connected shirt. METHODS: We prospectively recruited patients with epilepsy admitted to our epilepsy monitoring unit and asked them to wear the connected shirt while under simultaneous video-electroencephalographic monitoring. Electrocardiographic (ECG) and accelerometric (ACC) signals recorded with the connected shirt were used for the development of the seizure detection algorithm. First, we used a sliding window to extract linear and nonlinear features from both ECG and ACC signals. Then, we trained an extreme gradient boosting algorithm (XGBoost) to detect FBTCS according to seizure onset and offset annotated by three board-certified epileptologists. Finally, we applied a postprocessing step to regularize the classification output. A patientwise nested cross-validation was implemented to evaluate the performances in terms of sensitivity, false alarm rate (FAR), time in false warning (TiW), detection latency, and receiver operating characteristic area under the curve (ROC-AUC). RESULTS: We recorded 66 FBTCS from 42 patients who wore the connected shirt for a total of 8067 continuous hours. The XGBoost algorithm reached a sensitivity of 84.8% (56/66 seizures), with a median FAR of .55/24 h and a median TiW of 10 s/alarm. ROC-AUC was .90 (95% confidence interval = .88-.91). Median detection latency from the time of progression to the bilateral tonic-clonic phase was 25.5 s. SIGNIFICANCE: The novel connected shirt allowed accurate detection of FBTCS with a low false alarm rate in a hospital setting. Prospective studies in a residential setting with a real-time and online seizure detection algorithm are required to validate the performance and usability of this device.

Cardioprotective role of a magnolol and honokiol complex in the prevention of doxorubicin-mediated cardiotoxicity in adult rats.

Doxorubicin (DOXO) induces marked cardiotoxicity, though increased oxidative stress while there are some documents related with cardioprotective effects of some antioxidants against organ-toxicity during cancer treatment. Although magnolia bark has some antioxidant-like effects, its action in DOXO-induced heart dysfunction has not be shown clearly. Therefore, here, we aimed to investigate the cardioprotective action of a magnolia bark extract with active component magnolol and honokiol complex (MAHOC; 100 mg/kg) in DOXO-treated rat hearts. One group of adult male Wistar rats was injected with DOXO (DOXO-group; a cumulative dose of 15 mg/kg in 2-week) or saline (CON-group). One group of DOXO-treated rats was administered with MAHOC before DOXO (Pre-MAHOC group; 2-week) while another group was administered with MAHOC following the 2-week DOXO (Post-MAHOC group). MAHOC administration, before or after DOXO, provided full survival of animals during 12-14 weeks, and significant recoveries in the systemic parameters of animals such as plasma levels of manganese and zinc, total oxidant and antioxidant statuses, and also systolic and diastolic blood pressures. This treatment also significantly improved heart function including recoveries in end-diastolic volume, left ventricular end-systolic volume, heart rate, cardiac output, and prolonged P-wave duration. Furthermore, the MAHOC administrations improved the structure of left ventricles such as recoveries in loss of myofibrils, degenerative nuclear changes, fragmentation of cardiomyocytes, and interstitial edema. Biochemical analysis in the heart tissues provided the important cardioprotective effect of MAHOC on the redox regulation of the heart, such as improvements in activities of glutathione peroxidase and glutathione reductase, and oxygen radical-absorbing capacity of the heart together with recoveries in other systemic parameters of animals, while all of these benefits were observed in the Pre-MAHOC treatment group, more prominently. Overall, one can point out the beneficial antioxidant effects of MAHOC in chronic heart diseases as a supporting and complementing agent to the conventional therapies.

Heart rate reduction during voluntary deep diving in free-ranging loggerhead sea turtles.

Air-breathing vertebrates exhibit cardiovascular responses to diving including heart rate reduction (diving bradycardia). Field studies on aquatic mammals and birds have shown that the intensity of bradycardia can vary depending on diving behaviour, such as the depth of dives and dive duration. However, in aquatic reptiles, the variation in heart rate during deep dives under natural conditions has not been fully investigated. In this study, we released five loggerhead sea turtles (Caretta caretta) outfitted with recorders into the sea and recorded their electrocardiogram, depth, water temperature and longitudinal acceleration. After 3 days, the recorders automatically detached from the turtles. The heart rate signals were detected from the electrodes placed on the surface of the plastron. The mean (±s.d.) heart rate of 12.8±4.1 beats min-1 during dives was significantly lower than that of 20.9±4.1 beats min-1 during surface periods. Heart rate during dives varied with dive depth, although it remained lower than that at the surface. When the turtle dived deeper than 140 m, despite the relatively high flipper stroke rate (approximately 19 strokes min-1), the heart rate dropped rapidly to approximately 2 beats min-1 temporarily. The minimum instantaneous heart rate during dives was lower at deeper dive depths. Our results indicate that loggerhead sea turtles show variations in the intensity of diving bradycardia depending on their diving behaviour, similar to that shown by marine mammals and birds.

Artificial intelligence-enhanced electrocardiogram analysis for identifying cardiac autonomic neuropathy in patients with diabetes.

AIM: To develop and employ machine learning (ML) algorithms to analyse electrocardiograms (ECGs) for the diagnosis of cardiac autonomic neuropathy (CAN). MATERIALS AND METHODS: We used motif and discord extraction techniques, alongside long short-term memory networks, to analyse 12-lead, 10-s ECG tracings to detect CAN in patients with diabetes. The performance of these methods with the support vector machine classification model was evaluated using 10-fold cross validation with the following metrics: accuracy, precision, recall, F1 score, and area under the receiver-operating characteristic curve (AUC). RESULTS: Among 205 patients (mean age 54 ± 17 years, 54% female), 100 were diagnosed with CAN, including 38 with definite or severe CAN (dsCAN) and 62 with early CAN (eCAN). The best model performance for dsCAN classification was achieved using both motifs and discords, with an accuracy of 0.92, an F1 score of 0.92, a recall at 0.94, a precision of 0.91, and an excellent AUC of 0.93 (95% confidence interval [CI] 0.91-0.94). For the detection of any stage of CAN, the approach combining motifs and discords yielded the best results, with an accuracy of 0.65, F1 score of 0.68, a recall of 0.75, a precision of 0.68, and an AUC of 0.68 (95% CI 0.54-0.81). CONCLUSION: Our study highlights the potential of using ML techniques, particularly motifs and discords, to effectively detect dsCAN in patients with diabetes. This approach could be applied in large-scale screening of CAN, particularly to identify definite/severe CAN where cardiovascular risk factor modification may be initiated.

Calibration-free blood pressure estimation based on a convolutional neural network.

In this study, we conducted research on a deep learning-based blood pressure (BP) estimation model suitable for wearable environments. To measure BP while wearing a wearable watch, it needs to be considered that computing power for signal processing is limited and the input signals are subject to noise interference. Therefore, we employed a convolutional neural network (CNN) as the BP estimation model and utilized time-series electrocardiogram (ECG) and photoplethysmogram (PPG) signals, which are quantifiable in a wearable context. We generated periodic input signals and used differential and thresholding methods to decrease noise in the preprocessing step. We then applied a max-pooling technique with filter sizes of 2 × 1 and 5 × 1 within a 3-layer convolutional neural network to estimate BP. Our method was trained, validated, and tested using 2.4 million data samples from 49 patients in the intensive care unit. These samples, totaling 3.1 GB were obtained from the publicly accessible MIMIC database. As a result of a test with 480,000 data samples, the average root mean square error in BP estimation was 3.41, 5.80, and 2.78 mm Hg in the prediction of pulse pressure, systolic BP (SBP), and diastolic BP (DBP), respectively. The cumulative error percentage less than 5 mm Hg was 68% and 93% for SBP and DBP, respectively. In addition, the cumulative error percentage less than 15 mm Hg was 98% and 99% for SBP and DBP. Subsequently, we evaluated the impact of changes in input signal length (1 cycle vs. 30 s) and the introduction of noise on BP estimation results. The experimental results revealed that the length of the input signal did not significantly affect the performance of CNN-based analysis. When estimating BP using noise-added ECG signals, the mean absolute error (MAE) for SBP and DBP was 9.72 and 6.67 mm Hg, respectively. Meanwhile, when using noise-added PPG signals, the MAE for SBP and DBP was 26.85 and 14.00 mm Hg, respectively. Therefore, this study confirmed that using ECG signals rather than PPG signals is advantageous for noise reduction in a wearable environment. Besides, short sampling frames without calibration can be effective as input signals. Furthermore, it demonstrated that using a model suitable for information extraction rather than a specialized deep learning model for sequential data can yield satisfactory results in BP estimation.

Callous-unemotional traits and pre-ejection period in response to reward.

Callous-unemotional (CU) traits have important utility in distinguishing individuals exhibiting more severe and persistent antisocial behavior, and our understanding of reward processing and CU traits contributes to behavioral modification. However, research on CU traits often investigated reward alongside punishment and examined solely on average reward reactivity, neglecting the reward response pattern over time such as habituation. This study assessed individuals' pre-ejection period (PEP), a sympathetic nervous system cardiac-linked biomarker with specificity to reward, during a simple reward task to investigate the association between CU traits and both average reward reactivity and reward response pattern over time (captured as responding trajectory). A heterogeneous sample of 126 adult males was recruited from a major metropolitan area in the US. Participants reported their CU traits using the Inventory of Callous-Unemotional Traits and completed a simple reward task while impedance cardiography and electrocardiogram were recorded to derive PEP. The results revealed no significant association between average PEP reward reactivity and CU traits. However, CU traits predicted both linear and quadratic slopes of the PEP reactivity trajectory: individuals with higher CU traits had slower habituation initially, followed by a rapid habituation in later blocks. Findings highlight the importance of modeling the trajectory of PEP reward response when studying CU traits. We discussed the implications of individuals with high CU traits having the responding pattern of slower initial habituation followed by rapid habituation to reward and the possible mechanisms.

Arrhythmia detection by the graph convolution network and a proposed structure for communication between cardiac leads.

One of the most common causes of death worldwide is heart disease, including arrhythmia. Today, sciences such as artificial intelligence and medical statistics are looking for methods and models for correct and automatic diagnosis of cardiac arrhythmia. In pursuit of increasing the accuracy of automated methods, many studies have been conducted. However, in none of the previous articles, the relationship and structure between the heart leads have not been included in the model. It seems that the structure of ECG data can help develop the accuracy of arrhythmia detection. Therefore, in this study, a new structure of Electrocardiogram (ECG) data was introduced, and the Graph Convolution Network (GCN), which has the possibility of learning the structure, was used to develop the accuracy of cardiac arrhythmia diagnosis. Considering the relationship between the heart leads and clusters based on different ECG poles, a new structure was introduced. In this structure, the Mutual Information(MI) index was used to evaluate the relationship between the leads, and weight was given based on the poles of the leads. Weighted Mutual Information (WMI) matrices (new structure) were formed by R software. Finally, the 15-layer GCN network was adjusted by this structure and the arrhythmia of people was detected and classified by it. To evaluate the performance of the proposed new network, sensitivity, precision, specificity, accuracy, and confusion matrix indices were used. Also, the accuracy of GCN networks was compared by three different structures, including WMI, MI, and Identity. Chapman's 12-lead ECG Dataset was used in this study. The results showed that the values of sensitivity, precision, specificity, and accuracy of the GCN-WMI network with 15 intermediate layers were equal to 98.74%, 99.08%, 99.97% & 99.82%, respectively. This new proposed network was more accurate than the Graph Convolution Network-Mutual Information (GCN-MI) with an accuracy equal to 99.71% and GCN-Id with an accuracy equal to 92.68%. Therefore, utilizing this network, the types of arrhythmia were recognized and classified. Also, the new network proposed by the Graph Convolution Network-Weighted Mutual Information (GCN-WMI) was more accurate than those conducted in other studies on the same data set (Chapman). Based on the obtained results, the structure proposed in this study increased the accuracy of cardiac arrhythmia diagnosis and classification on the Chapman data set. Achieving such accuracy for arrhythmia diagnosis is a great achievement in clinical sciences.

Evaluation of 12-lead electrocardiogram at 0.55T for improved cardiac monitoring in magnetic resonance imaging.

BACKGROUND: The 12-lead electrocardiogram (ECG) is a standard diagnostic tool for monitoring cardiac ischemia and heart rhythm during cardiac interventional procedures and stress testing. These procedures can benefit from magnetic resonance imaging (MRI) information; however, the MRI scanner magnetic field leads to ECG distortion that limits ECG interpretation. This study evaluated the potential for improved ECG interpretation in a "low field" 0.55T MRI scanner. METHODS: The 12-lead ECGs were recorded inside 0.55T, 1.5T, and 3T MRI scanners, as well as at scanner table "home" position in the fringe field and outside the scanner room (seven pigs). To assess interpretation of ischemic ECG changes in a 0.55T MRI scanner, ECGs were recorded before and after coronary artery occlusion (seven pigs). ECGs was also recorded for five healthy human volunteers in the 0.55T scanner. ECG error and variation were assessed over 2-minute recordings for ECG features relevant to clinical interpretation: the PR interval, QRS interval, J point, and ST segment. RESULTS: ECG error was lower at 0.55T compared to higher field scanners. Only at 0.55T table home position, did the error approach the guideline recommended 0.025 mV ceiling for ECG distortion (median 0.03 mV). At scanner isocenter, only in the 0.55T scanner did J point error fall within the 0.1 mV threshold for detecting myocardial ischemia (median 0.03 mV in pigs and 0.06 mV in healthy volunteers). Correlation of J point deviation inside versus outside the 0.55T scanner following coronary artery occlusion was excellent at scanner table home position (r2 = 0.97), and strong at scanner isocenter (r2 = 0.92). CONCLUSION: ECG distortion is improved in 0.55T compared to 1.5T and 3T MRI scanners. At scanner home position, ECG distortion at 0.55T is low enough that clinical interpretation appears feasible without need for more cumbersome patient repositioning. At 0.55T scanner isocenter, ST segment changes during coronary artery occlusion appear detectable but distortion is enough to obscure subtle ST segment changes that could be clinically relevant. Reduced ECG distortion in 0.55T scanners may simplify the problem of suppressing residual distortion by ECG cable positioning, averaging, and filtering and could reduce current restrictions on ECG monitoring during interventional MRI procedures.

Reliability of single-lead electrocardiogram interpretation to detect atrial fibrillation: insights from the SAFER Feasibility Study.

BACKGROUND AND AIMS: Single-lead electrocardiograms (ECGs) can be recorded using widely available devices such as smartwatches and handheld ECG recorders. Such devices have been approved for atrial fibrillation (AF) detection. However, little evidence exists on the reliability of single-lead ECG interpretation. We aimed to assess the level of agreement on detection of AF by independent cardiologists interpreting single lead ECGs, and to identify factors influencing agreement. METHODS: In a population-based AF screening study, adults aged ≥65 years old recorded four single-lead ECGs per day for 1-4 weeks using a handheld ECG recorder. ECGs showing signs of possible AF were identified by a nurse, aided by an automated algorithm. These were reviewed by two independent cardiologists who assigned participant- and ECG-level diagnoses. Inter-rater reliability of AF diagnosis was calculated using linear weighted Cohen's kappa (kw). RESULTS: Out of 2,141 participants and 162,515 ECGs, only 1,843 ECGs from 185 participants were reviewed by both cardiologists. Agreement was moderate: kw = 0.48 (95% CI, 0.37-0.58) at participant-level; and kw = 0.58 (0.53-0.62) at ECG-level. At participant-level, agreement was associated with the number of adequate-quality ECGs recorded, with higher agreement in participants who recorded at least 67 adequate-quality ECGs. At ECG-level, agreement was associated with ECG quality and whether ECGs exhibited algorithm-identified possible AF. CONCLUSION: Inter-rater reliability of AF diagnosis from single-lead ECGs was found to be moderate in older adults. Strategies to improve reliability might include participant and cardiologist training and designing AF detection programmes to obtain sufficient ECGs for reliable diagnoses.

Real-Time Cardiac Abnormality Monitoring and Nursing for Patient Using Electrocardiographic Signals.

INTRODUCTION: Cardiovascular disease nursing is a critical clinical application that necessitates real-time monitoring models. Previous models required the use of multi-lead signals and could not be customized as needed. Traditional methods relied on manually designed supervised algorithms, based on empirical experience, to identify waveform abnormalities and classify diseases, and were incapable of monitoring and alerting abnormalities in individual waveforms. METHODS: This research reconstructed the vector model for arbitrary leads using the phase space-time-delay method, enabling the model to arbitrarily combine signals as needed while possessing adaptive denoising capabilities. After employing automatically constructed machine learning algorithms and designing for rapid convergence, the model can identify abnormalities in individual waveforms and classify diseases, as well as detect and alert on abnormal waveforms. RESULT: Effective noise elimination was achieved, obtaining a higher degree of loss function fitting. After utilizing the algorithm in Section 3.1 to remove noise, the signal-to-noise ratio increased by 8.6%. A clipping algorithm was employed to identify waveforms significantly affected by external factors. Subsequently, a network model established by a generative algorithm was utilized. The accuracy for healthy patients reached 99.2%, while the accuracy for APB was 100%, for LBBB 99.32%, for RBBB 99.1%, and for P-wave peak 98.1%. CONCLUSION: By utilizing a three-dimensional model, detailed variations in electrocardiogram signals associated with different diseases can be observed. The clipping algorithm is effective in identifying perturbed and damaged waveforms. Automated neural networks can classify diseases and patient identities to facilitate precision nursing.

The Association Between Urbanization and Electrocardiogram Abnormalities in China: a Nationwide Longitudinal Study.

The health effects of urbanization are controversial. The association between urbanization and reversible subclinical risks of cardiovascular diseases (e.g., electrocardiogram (ECG) abnormalities) has rarely been studied. This study aimed to assess the association between urbanization and ECG abnormalities in China based on the China National Stroke Screening Survey (CNSSS). We used changes in the satellite-measured impervious surfaces rate and nighttime light data to assess the level of urbanization. Every interquartile increment in the impervious surfaces rate or nighttime light was related to a decreased risk of ECG abnormalities, with odds ratios of 0.894 (95% CI, 0.869-0.920) or 0.809 (95% CI, 0.772-0.847), respectively. And we observed a U-shaped nonlinear exposure-response relationship curve between the impervious surfaces rate and ECG abnormalities. In conclusion, the current average level of urbanization among the studied Chinese adults remains a beneficial factor for reducing cardiovascular risks.