ST-segment Changes Research Articles

Prediction of mortality, future arrhythmia and cardiovascular disease: an artificial intelligence-enhanced electrocardiography platform

Abstract Background Artificial intelligence-enhanced electrocardiography (AI-ECG) can be used to identify existing disease, but could additionally be used to predict occurrence of future disease and death. Purpose We developed an AI-ECG platform that predicts mortality and a wide spectrum of future arrhythmia and cardiovascular disease. Methods The AI-ECG risk estimation platform (AIRE) was developed in a dataset of 1,163,401 ECGs from 189,539 patients from a secondary care setting in the USA. Uniquely, AIRE uses deep learning with a residual convolutional neural network with a discrete-time survival loss function to output subject-specific survival curves (Fig 1A). AIRE was fine-tuned to additionally predict the endpoints described below. Results AIRE accurately predicts risk of all-cause mortality (C-index 0.775 (0.773-0.776) and can differentiate prognosis in high- and low-risk subjects, even when only cardiologist-defined normal ECGs are considered (Fig 2B). Additionally, in Cox regression analyses, AIRE was superior to conventional risk factors (Fig 1B). AIRE accurately predicted future ventricular arrhythmia (c-index 0.760 (0.756-0.763)), future complete heart block (CHB) (0.809 (0.805-0.814), future atrial fibrillation (0.753 (0.751-0.756), future atherosclerotic cardiovascular disease (0.696 (0.694-0.698)) and future heart failure (0.787 (0.785-0.789)) . AIRE was superior to left ventricular ejection fraction (LVEF) in predicting risk of future ventricular arrhythmias in subjects with LVEF <50% (C-index 0.649 (0.638 – 0.660) vs 0.615 (0.603 – 0.626) p < 0.0001 ). For CHB prediction, AIRE was able to further risk stratify subjects with bifascicular block and syncope into low (1.9% 5 year CHB), intermediate (8.8%), and high risk (20.7%) groups, and could guide treatment decisions. We externally validated our findings in four diverse, transnational cohorts from Brazil and the UK, including volunteers, primary care subjects and patients with Chagas disease, and found AIRE accurately predicted all-cause mortality in all four external cohorts (Fig 2). Non-mortality endpoints were successful externally validated in the UKB. In explainability analyses, we found features of QRS morphology, low QRS voltage, poor precordial R wave progression, inverted and biphasic T waves and ST segment changes were the most significant morphological features associated with high predicted mortality (Fig 1D). Through phenome- and genome-wide association studies (GWAS), we identified candidate biological pathways including changes in cardiac structure (LV mass, LV trabeculation and left atrial size). GWAS identified variants adjacent to VGLL2, KCNQ1, CCDC91 and TBX3 which have been described in association with QT interval, biological aging and metabolic syndrome (Fig 1E). Conclusion AIRE could be used worldwide across a range of clinical contexts for risk estimation of not only mortality but a wide spectrum of future arrhythmia and cardiovascular diseases.Figure 1Figure 2

Functional correlates of ischemic electrocardiographic changes during stress echocardiography. data form stress echo 2030 survey

Abstract Background/Introduction Cardiac stress tests are carried out in populations with a low probability of ischemic heart disease (IHD) much more frequently than in the past. Stress ECG remains a frequently used modality for the diagnosis of IHD in vast areas of the world with limited facilities. Purpose To assess the diagnostic value of stress ECG for diagnosing IHD using inducible regional wall motion abnormalities (RWMA) on stress echocardiography (SE) as the gold standard method of diagnosis. Methods The 12-lead ECG response was retrospectively analyzed in 4317 patients (age 64±13 years, 59.6% males) undergoing SE for chronic coronary syndromes who were prospectively recruited from 39 cardiac centers between March 2021 and February 2024. Exclusion criteria were left bundle branch block or pacemaker rhythm. ECG response was considered ischemic according to standard criteria (if ST-segment deviated >1.0 mm from baseline in ≥2 contiguous leads at 80 ms from J point) during an exercise (n=2980, 69.8%), dobutamine (n = 766, 18.0%), or vasodilator (n=519, 12.2%) SE. All patients underwent a comprehensive SE protocol with an assessment of wall motion score index (WMSI), B-lines (4-site simplified score), left ventricular contractile reserve (LVCR) based on force, coronary flow velocity reserve (CFVR) in the mid-distal left anterior descending artery (LAD), and heart rate reserve (HRR). Results ECG changes occurred in 641 patients (14.8%, Group 1) for the overall studied population. Compared to patients without ECG changes (Group 2, n=3676, 85.2%), patients with ECG changes showed higher values of peak WMSI and lower values of CFVR and LVCR (see table).Amongst patients without inducible RWMA (n=3553), there were 392 (11%) patients with an ischemic ECG at stress (89% specificity). Of 764 patients with inducible RWMA during SE, 249 had an ischemic ECG trace (sensitivity 33%). In patients without inducible RWMA, those with ischemic ECG changes showed similar abnormal stress B-lines (23% vs. 21%, p=0.719), LVCR (61% vs. 63%, p=0.602), CFVR (31% vs 33%, p=0.607) and HRR (37% vs 41%, p=0.097) compared to those without ECG changes. Amongst patients with inducible RWMA and ECG changes, CFVR was significantly lower in patients with ECG changes (39.2% and 60.8%, respectively, p<0.001). Conclusions Simple standard stress ECG diagnostic value in the current era in populations with a low probability of IHD seems to be low. However, during SE, stress-induced ischemic ECG changes are associated with more extensive RWMA and blunted global LVCR, with reduced CFVR in the LAD. Therefore, analysis of ST segment changes during stress imaging studies can offer additional, significant information.

Smart watch for the detection of exercise-induced transient ST segment changes

Abstract Background Smartwatches are largely used and allowed to perform electrocardiogram one lead, usually a modified DI, used to diagnose atrial fibrillation. It is unknown whether or not smartwatches could be used to identify electrocardiographic transient ST changes during exercise-induced myocardial ischemia. The present study assessed the feasibility and reliability of using an Apple watch to record V5 in subjects scheduled for standard ECG stress tests. Methods One hundred eighty-nine subjects were included in this study. The mean age was 61+9 years, and 21.6 % were women (41 subjects). A single thoracic lead V5 was obtained with an Apple watch, positioned at the fifth intercostal space anterior axillary line, by creating a circuit between the back of the watch and the right index resting on the crown for 30 seconds. Four subjects were excluded because of the poor quality of the Apple watch signal. Forty-nine patients (25,92%) had a positive stress test with standard 12 lead ECG, 136 (71,96 %) negative stress test, and 4 (2,12%) the ECGs were non-diagnostic. The mean difference or bias between the Apple Watch and standard exercise-induced ST changes was quantified as 0.054, suggesting a generally minimal discrepancy in their readings. This consistency is critically affirmed by Cohen's Kappa (k) coefficient of 0.665. 9-1.0) Results A total of 189 subjects were included in the study; the mean age was 61 years (SD 9), and 21.6 % were women (41 subjects). Insightful outcomes were gleaned from the Bland-Altman analysis, which probed the concordance between the smartwatch ECG and the conventional standard ECG in measuring ST-segment deviations (Bias 0,054; SD 0.31, from -0.56 to 0.67, 95% limits of agreement), as vividly depicted in Figure. The dashed blue lines in Figure demarcate the 95% limits of agreement, which span from -0.56 to 0.67, offering a tangible visualization of the range within which most individual differences resided. A notable harmony was unveiled in the intricate exploration of the concordance between the two diagnostic methodologies, substantiated by an agreement of 87.6%. This demonstrates that, in most instances, the methodologies provided analogous results, exhibiting a commendable consistency between them in a substantial proportion of cases. Assuming the results of standard ECGs as the reference values, Apple Watch ST deviation showed a sensitivity of 69% and specificity of 94 %. The positive predictive value was 0.80952381, and the negative predictive value was 0,8951049. Conclusions In conclusion, this study demonstrated that the Apple Watch could detect transient ST changes with a sensitivity of 69% and a specificity of 94 %. Further prospective studies should be performed to assess the potential role of detecting transient myocardial ischemia with a smartwatch in a general population at risk.

The association between exercise-induced ventricular premature contractions and long-term mortality in patients without coronary artery disease

Abstract Background/Introduction The treadmill exercise test is widely used clinical test to determine cardiovascular risk and mortality, regardless of clinical risk factors (1). ST-segment changes detected in the exercise test are shown to predict myocardial ischemia (2) and premature ventricular complexes (PVCs) are frequently observed during exercise stress testing (3). Exercise-related PVC is observed in 14% to 23% of healthy individuals without significant heart disease (4,5). The literature on the role of PVCs observed during treadmill exercise testing in predicting prognosis is controversial. Purpose Therefore, we aimed to evaluate the clinical results of PVCs seen during exercise testing in patients who had been diagnosed with non-obstructive coronary artery disease after coronary angiography. Methods The study population consisted of 1624 consecutive patients who were considered high risk according to the Duke treadmill risk score and had no significant stenosis on coronary angiogram from January 2016 to April 2021. Patients with previous history of coronary revascularization, previous myocardial infraction, heart failure, moderate or severe heart valve disease, congenital heart disease, cardiomyopathy, bundle branch block, and left ventricular hypertrophy were excluded from the study. The primary endpoints of the study were long-term all-cause mortality of patients who had PVCs during the exercise test or during the resting phase. Results The long-term mortality was observed in 53 patients out of 1624 patients in the mean follow-up of 47 months. PVCs was observed in 293 (18.7%) patients without long-term mortality, while PVCs was observed in 24 (45.3%) patients with long-term mortality (p<0.001). The model adjusted for all covariates showed that the presence of PVCs in the recovery phase (p<0.007, HR (95% CI) 2.244 (1.244 – 4.047)) and advanced age (p<0.001, HR (95% CI) 1.194 (1.143 – 1.247)) were associated with long-term all-cause mortality (Figure 1). Considering Kaplan-Meier curve, individuals with PVCs in recovery had significantly higher risk of long-term mortality compared with those with without PVCs (log-rank statistic: 22.47, p<0.001) (Figure 2). Conclusion(s) The study highlights that PVCs monitored in the recovery phase of the treadmill exercise test were associated with long -term mortality in patients without structural heart disease and coronary artery disease.Figure 2Figure 1

Dynamics of changes in heart rate, ST segment and T-wave on patients with ventricular rhythm disturbances on the background of type 2 diabetes mellitus according to the results of 24-hour cardiac monitoring

The aim of the study was to analyze the dynamics of heart rate, assess the morphogenesis of the ST segment and T wave in patients with ventricular arrhythmias associated with type 2 diabetes mellitus (type 2 DM) based on the results of daily cardiac monitoring against the background of two regimens of metabolitotropic treatment. The study included 133 patients with type 2 DM with ventricular arrhythmias. The inclusion criteria for the study were: moderately severe type 2 diabetes in the stage of sub-/compensation on the background of combined glucose-lowering therapy without insulin, the presence of ventricular arrhythmias of classes III–V according to Lown B. and Wolf M. (1971). By random sampling, patients were randomized into 3 observation groups, statistically homogeneous in age, sex, duration of the diabetic syndrome, classes of ventricular arrhythmias. Patients of the 1st group (n = 44) received amiodarone and beta-blocker. Patients of the 2nd group (n = 45) received the same antiarrhythmic treatment, but in combination with meldonium for 3 consecutive months with the next 3-month course repeated after 6 months. Representatives of the 3rd group (n = 44) received treatment with amiodarone, beta-blocker and trimetazidine of the same duration. 24-hour ECG monitoring was performed at baseline, 3 months later, and 1 year later. Statistica 6.0 software was used for statistical processing. The examination revealed tachycardia syndrome and signs of pain and painless myocardial ischemia. It has been established that ventricular arrhythmias in type 2 DM are of a secondary nature, largely dependent on ischemic manifestations. Trimetazidine compared with meldonium showed a greater anti-ischemic effect, which made it possible to obtain a better antiarrhythmic effect. Trimetazidine is considered as one of the justified components of the treatment of ventricular arrhythmias of ischemic origin in patients with type 2 DM.

Diagnostic value of nocturnal trend changes in a dynamic electrocardiogram for coronary heart disease

ObjectiveTo explore the diagnostic value of intermittent changes in the nocturnal ST segment trend graph in a dynamic electrocardiogram (ECG) for coronary heart disease (CHD).MethodsA total of 205 patients who underwent coronary angiography were included in this retrospective study. The study sample was determined through a power analysis aimed at achieving power of 80% with a significance level of 0.05. The participants were divided into the CHD (n = 101) and the non-CHD (n = 104) group, based on the degree of coronary artery diameter stenosis. The morphological changes in the ST segment trend graph were observed and divided into two categories: ‘wall-shaped’ and ‘peak-shaped’ changes.ResultsAmong the 205 patients, 94 had nocturnal ST segment dynamic changes and 111 did not. The detection rate of CHD without nocturnal ST segment dynamic changes was 21.59%, significantly lower than the detection rate of 93.18% in those with nocturnal ST segment changes, reflecting a statistically significant difference (P < 0.05). The positive rate of ST segment in patients with single-vessel disease (71.88%) was lower than in patients with multi-vessel disease (78.57%), and both differences were statistically significant (P < 0.05). The duration of ST segment trend graph changes in 94 cases in the CHD group with intermittent changes in the nocturnal ST segment trend graph was higher than in the non-CHD group, but no significant difference was observed (P > 0.05). The detection rate of CHD in the peak-shaped dynamic change group of the nocturnal ST segment trend graph was significantly higher (76/82) than in the wall-shaped (6/82) dynamic change group (P < 0.05).ConclusionPeak-shaped changes in the nocturnal ST segment trend graph indicate coronary artery lesions. Nocturnal ST segment changes observed through dynamic ECG monitoring can serve as a valuable non-invasive predictor for CHD, providing a feasible method for early diagnosis and intervention in clinical practice.

Utility of the AngelMed Guardian System in myocardial bridging: a case report

BackgroundMyocardial bridging (MB) is a known congenital anomaly in which a segment of the coronary artery transverses from the epicardium through the myocardium. MB may clinically manifest as recurrent angina, acute coronary syndrome, ventricular dysrhythmia, and even sudden cardiac death. On electrocardiogram (EKG), MB can present with findings consistent with significant ST-segment changes. The AngelMed Guardian System (the Guardian device) was developed in an effort to optimize the time from the onset of myocardial ischemia to intervention. The device analyzes myocardial electrical changes and alerts the patient to seek emergent medical evaluation if an acute ST-segment deviation is detected. We describe the first documented case of the Guardian device detecting acute ST-segment changes secondary to myocardial bridging.Case PresentationA 50-year-old male, with a history of percutaneous coronary intervention of the proximal left anterior descending (LAD) artery, presented to his cardiologist’s office with reports of recurrent, atypical chest pain. The Guardian device was implanted. One month after implantation, the patient experienced chest pain and was alerted by the Guardian device to seek emergent medical evaluation. Initial EKG and high-sensitivity troponins were negative for acute ischemia. Guardian device interrogation revealed significant ST depressions, encouraging further ischemic evaluation. The exercise myocardial perfusion imaging revealed an apical reversible defect. Left heart catheterization revealed a large segment of mid-LAD MB with the patient’s previous LAD stent noted to be widely patent along with no evidence of new obstructive coronary disease. Following the identification of the MB, medication regimen adjusted and the patient denied recurrence of chest pain or Guardian alerts.ConclusionsWe describe the first documented case of the Guardian device detecting acute ST-segment changes that were secondary to myocardial bridging. The Guardian device appropriately documented an ischemic event not appreciated with initial EKG or troponin testing. With the assistance of the Guardian device, we were able to rapidly identify MB as the cause for the ischemic EKG changes and subsequent abnormal stress test, optimize medical management, and prevent recurrent atypical chest pain along with office and hospital visits.

Angiographic Outcomes in STEMI Patients: Evaluating Pre-dilatation and Thrombus Aspiration Effects

Introduction ST-elevation myocardial infarction (STEMI) poses significant challenges in cardiovascular care, necessitating rapid and effective reperfusion strategies. The present study assesses the angiographic outcomes of pre-dilatation and thrombus aspiration (PD+TA) versus conventional treatment without thrombus aspiration (NOTA) in patients undergoing PPCI for STEMI. Methods This prospective cohort study included a total of 155 patients, with 78 assigned to the PD+TA group and 77 to the NOTA group. Baseline demographics, cardiovascular risk factors, and angiographic assessments including TIMI flow, TMPG flow, corrected TIMI frame count (CTFC), ST segment changes, and ejection fraction were compared between the groups. Results The PD+TA group exhibited significantly lower systolic (p-value: 0.021) and diastolic blood pressures (p-value: 0.046), better glucose control (p-value: 0.015), and a more pronounced reduction in ST segment elevation (p-value: 0.027) compared to the NOTA group. Although ejection fraction at presentation was similar between groups, the PD+TA group (52.29±8.80%) demonstrated a statistically significant improvement at one-month follow-up from NOTA (49.14±8.20%). TIMI 3 and TMPG 3 flow rates were comparable between groups before and after drug administration, with significant improvements in CTFC observed in the PD+TA group. Conclusion Pre-dilatation and TA during PPCI for STEMI patients may lead to improved acute angiographic outcomes, including enhanced myocardial reperfusion and reduced ischemic burden. The significant improvement in ejection fraction at one-month follow-up further supports the potential benefits of PD+TA in cardiac function recovery. Larger studies with longer-term follow-up are needed to validate these findings and determine the broader clinical implications of TA in STEMI management. Clinical trial registration: CTRI/2019/02/017520, 7th February 2019, https://ctri.nic.in/Clinicaltrials/pmaindet2.php?EncHid=Mjk5Mjc=&amp;Enc=&amp;userName=CTRI/2019/02/017520

A change in QT interval and ST-segment after radiofrequency catheter ablation in pediatric patients with Wolff–Parkinson–White syndrome

BackgroundFew studies have examined QT, JT interval, and ST-segment changes due to radiofrequency catheter ablation (RFA) in manifest Wolff–Parkinson–White (WPW) syndrome in pediatric patients. MethodsThe study involved 27 patients (male-to-female, 13:14; age, 12 (5–16) years) who were diagnosed with WPW syndrome and underwent RFA in our hospital between 2009 and 2022. Electrocardiographic (ECG) changes were compared between the group with ventricular preexcitation due to an accessory pathway (manifest group, n = 16) and those without it (concealed group, n = 11). ResultsThe QT interval before RFA was significantly longer in the manifest group than in the concealed group (402 [362–482] vs. 344 [323–427]; p = 0.001). The QT interval was significantly shortened in the manifest group before and after RFA (402 [362–482] vs. 360 [298–422] msec; p = 0.01). At 1 month, the QT interval difference between the manifest and concealed groups disappeared (366 [305–437] vs. 335 [301–436] msec; p = 0.001). ST-segment changes were found after RFA in 56 % (9/16) of the patients in the manifest group but not in the concealed group. ECG changes presenting the Brugada-pattern was found in one patient. One month later, ECG abnormalities persisted in only one patient. ConclusionsIn pediatric patients, the QT interval was prolonged in manifest WPW syndrome but shortened after RFA. In the manifest group, transient ST-segment change and T-wave abnormalities were often observed after RFA; however, the ECG normalized in approximately 1 month.

T-wave Peak-to-End Changes Quantified by Time-Warping Predicts Ventricular Fibrillation in a Porcine Myocardial Infarction Model.

The T-peak-to-T-end ( Tpe) interval has shown potential in predicting ventricular arrhythmic risk. It is an appealing index to be measured during ischemia since it is less influenced by ST-segment changes than the early part of the T wave. A time-warping-based index, derived from a spatially transformed PCA lead, [Formula: see text], quantifying changes in the Tpe morphology, has previously demonstrated utility in tracking repolarization changes induced by a 5-minute ischemia model in humans. The value of [Formula: see text] as a predictor of ventricular fibrillation (VF) episodes is assessed in a porcine model of myocardial ischemia with ischemia maintained for 40 minutes. From 32 pigs undergoing a coronary occlusion, pre-occlusion and occlusion ECG recordings from 10 pigs suffering a VF episode after 10 min of occlusion (Delayed VF) and 16 that did not had any episode during the recording were analyzed. The [Formula: see text] series was measured by comparing Tpe morphologies at different stages of the occlusion relative to the peak-to-end morphology of a baseline T-wave. During baseline, [Formula: see text] remained stationary with an intra-recording median [IQR] value of 1.60 [1.33] ms. During artery occlusion, [Formula: see text] followed a well-marked gradual increasing trend as ischemia progressed, reaching a median of 14.58 [17.72] ms. [Formula: see text] averages were significantly higher ( ) in the VF group than in the Non-VF group at time intervals 0-5, 5-10, 10-15, 15-20, 20-25 min after occlusion onset and at 10-15, 5-10 and 5-0 minutes prior to VF episode, with median values of 12.5, 18.8, 26.8, 24.0, 31.0, 18.6, 25.0 and 28.8 vs 6.3, 7.6, 8.0, 7.8, 7.8, 8.5, 7.2 and 6.0 ms, respectively. The [Formula: see text] interval was also significantly higher in the VF group at all analyzed time periods, but with a lower significance level. Pigs with maximum [Formula: see text] ≥ 20.0 ms and [Formula: see text] ≥ 85.4 ms had significantly higher risk for VF occurring in the early 5-10 minutes interval, with 90.0%/75.0% and 80.0%/69.0% sensitivity/specificity, respectively. Univariate Cox analysis yielded hazard ratios of 12.5 for [Formula: see text] vs 5.5 for [Formula: see text]. The time-warping-based index, [Formula: see text], is a stronger VF predictor than [Formula: see text] during ischemia in a porcine model, advising for further clinical exploration studies in humans.

Preoperative electrocardiogram in prediction of 90-day postoperative mortality: retrospective cohort study

BackgroundThere are conflicting data on the relationship between preoperative electrocardiogram and postoperative mortality. We aimed to assess the predictive value of preoperative ECG on postoperative all-cause mortality in patients undergoing non-cardiac surgery (NCS).MethodsWe retrospectively reviewed records of hospitalized patients who underwent an internal preoperative examination and subsequent NCS in the years 2015–2021. We recorded patient comorbidities, vital functions, results of biochemical tests, ECG. The primary end point was 90-day postoperative all-cause mortality, acquired from the hospital records and the nationwide registry run by the Institute of Health Information and Statistics of the Czech Republic.ResultsWe enrolled a total of 2219 patients of mean age 63 years (48% women). Of these, 152 (6.8%) died during the 90-day postoperative period. There were statistically significant associations between increased 90-day postoperative all-cause mortality and abnormal ECG findings in resting heart rate (≥ 80 bpm, relative risk [RR] = 1.82 and ≥ 100 bpm, RR = 2.57), presence of atrial fibrillation (RR = 4.51), intraventricular conduction delay (QRS > 0.12 s, RR = 2.57), ST segment changes and T wave alterations, left bundle branch hemiblock (RR = 1.64), and right (RR = 2.04) and left bundle branch block (RR = 4.13), but not abnormal PQ and QT intervals, paced rhythm, incomplete right bundle branch block, or other ECG abnormalities. A resting heart rate (≥ 80 bpm, relative risk [RR] = 1.95 and ≥ 100 bpm, RR = 2.20), atrial fibrillation (RR = 2.10), and right bundle branch block (RR = 2.52) were significantly associated with 90-day postoperative all-cause mortality even in subgroup of patients with pre-existing cardiac comorbidities.ConclusionsPatients with abnormal preoperative ECG findings face an elevated risk of all-cause mortality within 90 days after surgery. The highest mortality risk is observed in patients with atrial fibrillation and left bundle branch block. Additionally, an elevated heart rate, right bundle branch block, and atrial fibrillation further increase the risk of death in patients with pre-existing cardiac conditions.

Abnormal recognition-assisted and onset-offset aware network for pathological wearable ECG delineation

Electrocardiogram (ECG) delineation is essential to the identification of abnormal cardiac status, especially when ECG signals are remotely monitored with wearable devices. The complexity and diversity of cardiac conditions generate numerous pathological ECG patterns, not only requiring the recognition of normal ECG but also addressing an extensive range of abnormal ECG patterns, posing a challenging task. Therefore, we propose an abnormal recognition-assisted network to integrate supplementary information on diverse ECG patterns. Simultaneously, we design an onset-offset aware loss to enhance precise waveform localization. Specifically, we establish a two-branch framework where ECG delineation serves as the target task, producing the final segmentation results. Additionally, the abnormal recognition-assisted network serves as an auxiliary task, extracting multi-label pathological information from ECGs. This joint learning approach establishes crucial correlations between ECG delineation and associated ECG abnormalities. The correlations enable the model to demonstrate sufficient generalization in the presence of diverse abnormal ECG patterns. Besides, onset-offset aware loss focuses intensively on wave onsets and offsets by applying biased weights to various waveform positions. This approach ensures a focus on precise localization, facilitating seamless integration into cross-entropy loss function. A large-scale wearable 12-lead dataset containing 4,913 signals is collected, offering an extensive range of ECG data for model training. Results demonstrate that our method achieves outstanding performance on two test datasets, attaining sensitivity of 94.97% and 94.27% and an error tolerance lower than 20 ms. Furthermore, our method is effective for various aberrant ECG signals, including ST-segment changes, atrial premature beats, and right and left bundle branch blocks.

Genesis of ischemic ST segment changes: A study using precordial bipolar leads and regional vectorcardiograms

BackgroundPrecordial Bipolar Leads (PBLs), Weighted Unipolar Leads (WUL), and Regional Vectorcardiograms (RVCGs) are constructed using the same data recorded by a standard 12‑lead ECG, but they provide additional information not visible in the standard 12‑lead ECG (ECG) tracings. ObjectivesIn previous studies during balloon occlusion of the LAD and RCA, we observed a complete ischemic inversion of the QRS waves, with folding of the loop and ST segment shift. In the present study, we aim to investigate this abnormality using new ECG methods. We hypothesize that utilizing PBL, WUL, and RVCG in patients with ischemia caused by total acute coronary artery occlusion enables the detection of specific abnormalities—such as changes in waveform time/amplitude, the presence of the omega sign, distortion and folding of RVCG loops, and alterations in loop direction in both the transverse and frontal planes—that are not easily discernible with a standard 12‑lead ECG. This enhanced detection aids in understanding the mechanisms underlying electrocardiographic changes and may assist in managing patients when diagnostic uncertainties arise. MethodsThirty-three patients undergoing elective PTCA were studied before and after acute LAD (16 patients) or RCA (17 patients) occlusion, and their data were processed with new methods based on PBLs, WULs, and RVCGs. Results1. In acute ischemia due to occlusion of the LAD and RCA, the most important current of injury occurs in the right to left axis. This axis is underestimated by the standard 12‑lead ECG and only partially complemented by leads V3R and V4R. 2. The two-dimensional presentation detects a new sign (the omega sign), not detectable in the classic ECG, but almost always present in ischemia. It also allows for an accurate identification of the J point. 3. Ischemic R wave peak delay results in distortion and folding of the RVCG loop and causes displacement of the J point and the ST segment. 4. Wave inversion changes the loop direction in the transverse and frontal plane. ConclusionsPrecordial bipolar leads, weighted unipolar leads, and regional vectorcardiograms provide essential information omitted by the standard 12‑lead ECG.

Characteristics of electrocardiogram in fulminant myocarditis

Objective: To investugate the unique electrocardiogram (ECG) characteristics of fulminant myocarditis (FM) patients and provide important clues for the diagnosis of FM. Methods: This was a retrospective study. Patients diagnosed with acute myocarditis at Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology from February 2017 to April 2022 were enrolled and divided into fulminant myocarditis group (FM) and non-fulminant myocarditis group (NFM) according to clinical diagnosis. A total of 246 healthy people who underwent physical examination in the Health examination Center of Tongji Hospital at the same period were selected as the control group. The clinical data and ECG characteristics of the above 3 groups were analyzed and compared. Logistic regression model was used to analyze the influence of ECG parameters on left ventricular ejection fraction in FM patients. Receiver operating curves were constructed to evaluate the predictive value of different ECG parameters for FM. Results: A total of 180 patients were included in this study (FM group: n=123; NFM group: n=57), with an age of (35.0±16.2) years and 106 males (58.89%). Compared with NFM group, ECG was significantly abnormal in FM group, with a higher incidence of sinus tachycardia, ventricular tachycardia or ventricular fibrillation, escape rhythm, right bundle branch block, third degree atrioventricular block, ST-segment elevation, low voltage, prolonged QTc interval, and widened QRS wave in the FM group (all P<0.05). The ECG parameters showed that the amplitude of the full lead QRS wave in FM group was lower than that in NFM group (P<0.01). The average heart rate and QTc interval of FM group were significantly higher than those of NFM and control groups (all P<0.05). Although ST-segment elevation had a higher incidence in the FM group, ECG parameters showed that except for leads Ⅲ and aVF, the ST segment levels in all leads in the FM group were lower than those in the control group (all P<0.05). There was a statistically significant difference in some ST segment changes between FM and NFM groups, while there was no statistical difference between the NFM and control groups. Multivariate regression analysis showed that widened QRS wave and increased heart rate were the influencing factors for left ventricular systolic dysfunction in FM patients (OR=16.914, 95%CI: 1.367-209.224, P=0.028; OR=1.026, 95%CI: 1.010-1.042, P=0.001). Receiver operating curve analysis showed that heart rate>86.90 beat/min, QTc>431.50 ms, and RV5+SV1<1.72 mV had certain predictive value for FM diagnosis. Conclusions: FM patients displayed marked and severe ECG abnormalities, and characteristic changes in ECG can provide important first clues for the diagnosis of FM.

Abstract We126: Myocarditis Following mRNA Vaccination for COVID-19 is Mediated by CXCL10 and IFN-γ

Introduction: mRNA vaccines have shown remarkable efficacy against symptomatic COVID-19, reshaping the pandemic's trajectory. Despite a robust safety profile, ongoing monitoring is crucial due to the rare but concerning myocarditis cases, predominantly affecting males under 30. Symptoms appear around 2.6 days post-vaccination, with chest pain, shortness of breath, and palpitations. Elevated cTnI and ST-segment changes are common, along with late gadolinium enhancement in cardiac MRI. Understanding these rare adverse effects is essential for the expanding scope of mRNA technology, spanning infectious disease vaccines and anti-cancer immunotherapies. Hypothesis: Myocarditis linked to COVID-19 mRNA vaccines involves cytokine production from myeloid cells, leading to impaired cardiac function. Methodology: a, Reanalysis of proteomics data of healthy and myocarditis individuals following COVID-19 vaccination; b, Macrophages (N = 7 lines) were exposed to BNT162b2 or mRNA-1273, and analyzed by cytokine array and RNA-seq; c, Cardiomyocytes (N = 4 lines) were treated with CXCL10 (1 and 10 ng/mL) and IFN-γ (0.5 and 5 ng/mL), with or without genistein (10 μM), followed by functional assessment, transcriptomic and proteomic profiling; d, Mice (6 per group) were administered with CXCL10 and IFN-γ, with or without genistein pretreatment (7 days). Myeloid cell infiltration in the heart, serum cTnI levels, RNA-seq, and immunoproteasome activity were analyzed. Results: Examination of post-vaccination plasma revealed a notable rise in CXCL10 and IFN-γ levels in patients. Similarly, macrophages exposed to mRNA vaccines displayed heightened production of these cytokines. When cardiomyocytes were exposed to these cytokines, they exhibited compromised contractility, increased arrhythmogenicity, and gene expression patterns reminiscent of myocarditis. Genistein, an anti-inflammatory phytoestrogen, demonstrated significant alleviation of these effects, preventing cytokine-induced proteasomal activation and preserving contractile function. Mouse model of cytokine-induced myocarditis showed that genistein substantially reduced cardiac injury markers and immune cell infiltration. Conclusion: These findings highlight CXCL10 and IFN-γ as pivotal contributors to myocarditis following mRNA vaccination and suggest genistein as a potential therapeutic intervention to mitigate associated cardiovascular risks.

Pulmonary embolism in patients with chronic coronary syndrome masquerading as acute coronary syndrome: a case report and literature review

BackgroundPulmonary embolisms (PEs) exhibit clinical features similar to those of acute coronary syndrome (ACS), including electrocardiographic abnormalities and elevated troponin levels, which frequently lead to misdiagnoses in emergency situations.Case presentationHere, we report a case of PE coinciding with chronic coronary syndrome in which the patient’s condition was obscured by symptoms mimicking ACS. A 68-year-old female with syncope presented to the hospital. Upon admission, she was found to have elevated troponin levels and an electrocardiogram showing ST-segment changes across multiple leads, which initially led to a diagnosis of ACS. Emergency coronary arteriography revealed occlusion of the posterior branches of the left ventricle of the right coronary artery, but based on the complexity of the intervention, the occlusion was considered chronic rather than acute. On the 3rd day after admission, the patient experienced recurrent chest tightness and shortness of breath, which was confirmed as acute PE by emergency computed tomography pulmonary angiography. Following standardized anticoagulation treatment, the patient improved and was subsequently discharged.ConclusionsThis case report highlights the importance of recognizing the nonspecific features of PE. Clinicians should be vigilant when identifying other clinical features that are difficult to explain accompanying the expected disease, and it is necessary to carefully identify the causes to prevent missed diagnoses or misdiagnoses.

Comparative Efficacy and Safety of Pulsed Field Ablation Versus Radiofrequency Ablation of Idiopathic LV Arrhythmias

BackgroundComparative efficacy and safety data on radiofrequency ablation (RFA) versus pulsed field ablation (PFA) for common idiopathic left ventricular arrhythmia (LV-VAs) locations are lacking. ObjectivesThis study sough to compare RFA with PFA of common idiopathic LV-VAs locations. MethodsTen swine were randomized to PFA or RFA of LV interventricular septum, papillary muscle, LV summit via distal coronary sinus, and LV epicardium via subxiphoid approach. Ablations were delivered using an investigational dual-energy (RFA/PFA) contact force (CF) and local impedance-sensing catheter. After 1-week survival, animals were euthanized for lesion assessment. ResultsA total of 55 PFA (4 applications/site of 2.0 KV, target CF ≥10 g) and 36 RFA (CF ≥10 g, 25–50 W targeting ≥50 Ω local impedance drop, 60-second duration) were performed. LV interventricular septum: average PFA depth 7.8 mm vs RFA 7.9 mm (P = 0.78) and no adverse events. Papillary muscle: average PFA depth 8.1 mm vs RFA 4.5 mm (P < 0.01). Left ventricular summit: average PFA depth 5.6 mm vs RFA 2.7 mm (P < 0.01). Steam-pop and/or ventricular fibrillation in 4 of 12 RFA vs 0 of 12 PFA (P < 0.01), no ST-segment changes observed. Epicardium: average PFA depth 6.4 mm vs RFA 3.3 mm (P < 0.01). Transient ST-segment elevations/depressions occurred in 4 of 5 swine in the PFA arm vs 0 of 5 in the RFA arm (P < 0.01). Angiography acutely and at 7 days showed normal coronaries in all cases. ConclusionsIn this swine study, compared with RFA, PFA of common idiopathic LV-VAs locations produced deeper lesions with fewer steam pops. However, PFA was associated with higher rates of transient ST-segment elevations and depressions with direct epicardium ablation.

Feasibility and efficacy of single-shot PFA technology for redo procedures after a previous atrial fibrillation ablation procedure

Abstract Introduction Despite significant technological advancements and a better understanding of atrial tachyarrhythmia pathophysiology, a non-negligible percentage of atrial fibrillation (AF) patients undergoing catheter ablation experiences arrhythmia relapse. Repeat procedures have been traditionally performed via thermal energy systems, which carry a certain risk of collateral damage to adjacent tissues. Pulsed Field Ablation (PFA) has emerged as an alternative non-thermal energy source for cardiac ablation. The main advantage is its selectivity to cardiac tissue. FarapulseTM is the first PFA technology to have received regulatory approval and includes a pentaspline PFA catheter. Although designed for pulmonary vein isolation, its use for extrapulmonary vein site ablation has been previously documented. Purpose To evaluate the feasibility and efficacy of the pentaspline FarawaveTM for redo procedures. Methods Patients referred for a redo procedure using FarapulseTM system were enrolled in 3 high-volume European centers. A workflow (Figure 1.A) was established based on rhythm at presentation (Group 1: sinus rhythm; Group 2: AFL; Group 3: AF). Results A total of 117 patients were included (64 in Group 1, 18 in Group 2, and 35 in Group 3). The mean number of previous procedures was 1.26, and 23 patients (19.66%) had already undergone ≥2 procedures. Previous ablation targets included PVI, either alone (46.15%) or in combination with other targets, including posterior mitral line (39.32%), posterior wall (6.84%), or anterior mitral line (2.56%). Electroanatomical mapping (EAM) was adopted in 15.38% of the cases. Specifically, in 27.78% (n=5) of group 2, 15.63% (n=10) of group 1 and 8.57% (n= 3) of group 3 cases. Additional focal radiofrequency ablation was required in 4 patients for CTI line ablation. Lesion sets are depicted in Figure 2. Mean procedural and LA dwelling time were 95.2 ± 38.0 and 50.7 ± 36.7 minutes, respectively. There was a total of one major complication (intracranial haemorrhage) and 5 minor complications (two vascular site related, and three reversible ST segment changes, related to applications on the mitral annulus area). A total of 100 patients completed at least 3 months of follow-up (FU), with a median FU time was 7.55 months (IQR 5.18 – 11.85). The total number of recurrences was 20, including 2 during the blanking period. Survival function (excluding blanking period) was 88.6 (95% CI 79.7 – 93.8) at 6 months and 80.0% (95% CI 67.3 – 88.3) 12 months. Atrial arrhythmia free-survival was higher in patients presenting in sinus rhythm, compared to the other two groups (p = 0.0135), as displayed in Figure 1.B. Conclusion The proposed stepwise approach to repeat AF ablation procedures based on the use of the single-shot PFA system (with or without EAM) was feasible, safe, fast and effective at one year follow-up.Flow chart and Kaplan Meier curveLesion sets

Artificial intelligence enabled electrocardiogram for mortality and ventricular arrhythmia prediction

Abstract Background Artificial intelligence-enhanced electrocardiograms (AI-ECG) can be used to predict risk of events but existing models suffer from lack of actionability, explainability and biological plausibility, and therefore are not used clinically. Purpose We sought to address these limitations of previous AI-ECG approaches by developing the AI-ECG risk estimator (AIRE). Methods AIRE was developed in a dataset of 1,163,401 ECGs from 189,539 patients from a secondary care setting in the USA. Uniquely, AIRE uses deep learning with a residual convolutional neural network with a discrete-time survival loss function to create a subject-specific survival curve using a single ECG. AIRE was trained to predict time-to-mortality and fine-tuned for the additional endpoints described below. Results AIRE outputs a subject-specific survival curve that predicts not only mortality but time-to-mortality, using only a single ECG (Figure 1A). AIRE accurately predicts risk of all-cause mortality (C-index 0.775 (0.773-0.776), Figure 2) and can differentiate prognosis in high and low risk subjects even when only cardiologist reported normal ECGs are considered (Figure 2). AIRE also accurately predicted cardiovascular (CV) death 0.832 (0.831-0.834), future ventricular arrhythmia (0.760 (0.756-0.763)), future atherosclerotic cardiovascular disease (0.696 (0.694-0.698)) and future heart failure (0.787 (0.785-0.889))). In particular AIRE was superior to left ventricular ejection fraction (LVEF) in predicting risk of future ventricular arrhythmias in subjects with LVEF &amp;lt;50% (C-index 0.649 (0.638 – 0.660) vs 0.615 (0.603 – 0.626) p &amp;lt; 0.0001 ) and in dilated cardiomyopathy (C-index 0.690 (0.669-0.711) vs 0.608 (0.584 – 0.631), p &amp;lt; 0.0001). We used a variational autoencoder (VAE) to visualise the features most correlated with the mortality predictions. Features of QRS morphology, particularly broader and more left bundle branch block morphologies, inverted and biphasic T waves as well as ST segment changes were associated with high predicted mortality (Figure 1B). We externally validated our findings in four diverse, transnational cohorts from Brazil and the UK including volunteers and primary care subjects (Figure 2), and found AIRE accurately predicted all-cause mortality in all four external cohorts. Through phenome- and genome-wide association studies, we identified candidate biological pathways for the prediction of increased risk, including changes in cardiac structure and function (LV mass, LVEF, LV trabeculation), and genes associated with cardiac structure, QT interval, biological aging and metabolic syndrome (VGLL2, KCNQ1, CCDC91, TBX3). Conclusion AIRE is an explainable, biologically plausible and actionable AI-ECG risk estimation platform that has the potential for use worldwide across a wide range of clinical contexts for short- and long-term risk estimation.Figure 1Figure 2

Does ChatGPT-4 succeed in the ECG interpretation: friend or foe to cardiologists?

Abstract Background/Introduction Artificial intelligence (AI) and large language models (LLMs) are increasingly being tested for medical purposes, especially in clinical settings and one of the most well-known LLMs is OpenAI’s ChatGPT-4. Recent explorations have considered using ChatGPT to answer medical questions, and the new ChatGPT-4 also allows graphical inputs, which could aid medical doctors in interpreting electrocardiograms (ECGs) in everyday practice. AI-powered ECG interpretation has shown promising results, improving the detection of arrhythmias, ST-segment changes, QT prolongation, and other ECG abnormalities. However, whether ChatGPT4’s interpretation of ECGs is comparable to that of experienced cardiologists has yet to be established. Purpose We sought to test whether ChatGPT-4 could analyze and interpret ECGs similarly to experienced cardiologists. Methods We tasked ChatGPT-4 with interpreting, for scientific purposes, 12-lead ECGs, from 150 patients included in our prospective CaRD registry, presenting with various cardiac pathologies, including acute coronary syndrome, arrhythmias (primarily atrial fibrillation), conduction abnormalities, pacemaker rhythms and normal ECGs. Four experienced cardiologists reviewed the ECG interpretations provided by ChatGPT-4. The model provided information on rate, rhythm, axis, P-wave, PR interval, QRS complex, ST segment, T wave, differential diagnoses, most likely diagnosis and further diagnostic step. Results In this observational study, ChatGPT-4 demonstrated low overall accuracy in interpreting ECGs, with only 24% of the most likely diagnosis being correct. ChatGPT-4 performed the best when interpreting normal ECGs with sinus rhythm, achieving 62% accuracy rate, followed by 17%, 10% and 7.3% for ECGs with arrhythmias, acute ischemic changes, and conduction abnormalities or pacing rhythms, respectively. Conclusion ChatGPT-4 exhibited very low accuracy in interpreting different categories of pathology in 12-lead ECG, yielding less than 20% success rate. While the use of AI in medical diagnostics is an appealing concept in theory, the results suggest that, in its current state, ChatGPT-4 would not provide significant aid to experienced cardiologists in clinical settings.