12-lead Electrocardiography Research Articles

The Interplay between Conventional Cardiovascular Risk Factors and Health-Related Quality of Life in a Cohort of Working Young and Middle-Aged Adults: A Prospective Study.

Psychosocial and work stress, socioeconomic status, and environmental health directly impact the onset and progression of cardiovascular diseases, irrespective of sex or conventional cardiovascular risk factors (cCRFs). On the other hand, the impact of cCRFs on health-related quality of life (HRQoL) is not well known, and the psychological socioeconomic environmental somatic health interaction is often neglected. Accordingly, we aimed to: (i) compare the self-reported HRQoL using the WHOQOL-BREF questionnaire between healthy subjects and those with cCRFs; and (ii) evaluate the interplay between HRQoL, cCRFs, and cardiovascular treatment adherence. We prospectively included 90 working adults (46 healthy and 44 with cCRFs age- and sex-matched adults) evaluated by clinical examination, 12-leads electrocardiography, and transthoracic echocardiography as part of a cardiovascular diseases screening program, that also filled in the WHOQOL-BREF questionnaire. Subjects with CRFs were less satisfied with their own individual health. The presence and the number of CRFs, as well as the need for cardiovascular treatment and the number of drugs taken correlated with reduced scores at the majority of HRQoL domains. The results in the social relationships domain were the best predictor of cardiovascular treatment adherence. Finally, the results of all HRQoL domains were strongly correlated to each other demonstrating the psychological socioeconomic environmental somatic health interaction.

Spectrum of transthyretin gene mutations and clinical characteristics of Polish patients with cardiac transthyretin amyloidosis.

Transthyretin amyloidosis (ATTR) is a rare, life-threatening systemic disorder. We present first findings on the cardiac hereditary ATTR in Poland. Sixty-eight consecutive patients with suspected or known cardiac amyloidosis were evaluated, including blood tests, standard 12-lead electrocardiography (ECG) and transthoracic echocardiography. ATTR was confirmed histologically or non-invasively using 99mTc-DPD scintigraphy. Transthyretin (TTR) gene sequencing was performed. In 2017-2019, 10 unrelated male patients were diagnosed with hereditary ATTR. All patients had very uncommon TTR gene mutations: 7 patients had p.Phe53Leu mutation, 2 patients had p.Glu109Lys mutation and 1 patient had p.Ala101Val mutation. The age of onset ranged from 49 to 67 years (mean [SD] age, 58.7 [6.4] years). On ECG, most patients (70%) had pseudoinfarct pattern and/or low QRS voltage. The maximal wall thickness (MWT) on echocardiography varied considerably among the patients from moderate (16 mm) to massively increased (30 mm). Most patients (90%) had decreased left ventricular ejection fraction (mean [SD], 43 [11] %). On follow-up, we observed progressive heart failure in almost all cases. The first patient with p.Phe53Leu mutation died of heart failure, the second died suddenly, the third successfully underwent combined heart and liver transplant with 15 months survival from the surgery. The patient with p.Ala101Val mutation died of stroke. According to available data, this is the first time that the types of TTR mutations and the clinical characteristics of Polish patients with cardiac hereditary ATTR have been described. Previous literature data about Polish background in families with p.Phe53Leu mutation and the present results, suggest that this TTR mutation might be endemic in the Polish population.

Non-Contact Monitoring of ECG in the Home Environment—Selecting Optimal Electrode Configuration

Capacitive electrocardiography (cECG) is most often used in wearable or embedded measurement systems. The latter is considered in the paper. An optimal electrocardiographic lead, as an individual feature, was determined based on model studies. It was defined as the possibly highest value of the R-wave amplitude measured on the back of the examined person. The lead configuration was also analyzed in terms of minimizing its susceptibility to creating motion artifacts. It was found that the direction of the optimal lead coincides with the electrical axis of the heart. Moreover, the electrodes should be placed in the areas preserving the greatest voltage and at the same time characterized by the lowest gradient of the potential. Experimental studies were conducted using the developed measurement system on a group of 14 people. The ratio of the R-wave amplitude (as measured on the back and chest, using optimal leads) was less than 1 while the SNR reached at least 20 dB. These parameters allowed for high-quality QRS complex detection with a PPV of 97%. For the "worst" configurations of the leads, the signals measured were practically uninterpretable.

The Role of Clinical Exercise Physiologists with Exercise Testing

Exercise testing is a widely accepted procedure that has historically been used in cardiopulmonary settings for the last 40 years (1). The most common use of exercise testing has been to detect latent cardiovascular disease in asymptomatic people undergoing routine medical evaluation or to assess patients after a cardiac event (2). Typical modes for testing include an ergometer or treadmill with 12-lead electrocardiograph (ECG) monitoring. Over the years, the versatility and use of exercise testing has evolved to include assessment of healthy and older adults, children, recreational and elite athletes, and a variety of persons with chronic diseases and conditions (3). In addition to ECG monitoring, additional methods of measurement such as pulmonary gas exchange, pulmonary function, and strength or physical function assessments (e.g., grip strength and 6-minute walk test) have become more common in clinical testing and allow for a comprehensive overview of exercise capacity, disease thresholds, and current fitness level (3). Exercise testing is also indicated when quantifying physical work capacity for occupational medicine, injury risk in sport, determining medical clearance, monitoring symptoms (e.g., dyspnea or syncope), identifying ischemic threshold, or posttesting for treatment or training program effectiveness (1,2).Due to the nature of clinical exercise testing, typically conducted on persons with chronic diseases or conditions, these tests must be administered by a qualified exercise professional (1). As recent as 2014, there has been debate on who are qualified exercise professionals and if it is safe to administer exercise testing without direct physician supervision (1). The most recent American Heart Association Scientific Statement, “Supervision of Exercise Testing by Non-physicians,” provides insight on the most qualified exercise professionals able to administer safe and effective clinical exercise testing (1). In this scientific statement, nonphysician exercise professionals are defined as allied health professionals, including clinical exercise physiologists, physical therapists, nurses, nurse practitioners, and physician assistants (1). Myers et al. (1) references complication rates associated with >2.1 million exercise tests conducted by both physicians and allied health professionals between 1971 and 2012, demonstrating extremely low occurrence of mortality, morbidity, and other complications per 1,000 tests. The tests referenced by Myers et al. (1) were conducted with a combination of asymptomatic adults, athletes, and persons with chronic disease. Although ~75% of the exercise tests were supervised by a physician, no differences in safety or adverse events appeared when comparing physician-supervised exercise tests with allied health professional–supervised exercise tests (1). Even though overlap with academic training and experience exists between allied health professionals, clinical exercise physiologists are highly qualified exercise professionals trained to provide independent supervision of clinical exercise testing. With formal training, the clinical exercise physiologist has strong familiarity with the multiple exercise testing settings, including high acuity units in hospitals, variety of protocols, range of patient conditions who are managing acute and chronic disease, and proficiency with the skills and abilities required for test administration.In a literature review by Warburton et al. (4), the safety and effectiveness of exercise tests conducted by qualified clinical exercise physiologists, with and without physician supervision, is supported. In that paper, they provide general recommendations for the formal training and preparation of the clinical exercise physiologist to work with clinical populations (4). In summary, these recommendations include (a) at minimum, completion of an undergraduate degree in exercise science and passage of a nationally recognized certification assessing entry level proficiencies; (b) training to deliver patient-centered care that is evidence-based and a part of a care team; (c) possession of discipline-specific core competencies (i.e., understanding different clinical populations); (d) completion of clinical rotations and internship hours; (e) direct assessment of clinical exercise testing skills and abilities which may require a specific number of tests (i.e., 50 tests); and (f) participation in continued professional education to maintain competencies (4). The above recommendations are aligned with recent work to advocate for advancement of clinical exercise physiologists being recognized as qualified health care providers (5). These recommendations also support the importance of academic program accreditation by the Commission on Accreditation of Allied Health Education Programs in the United States and available certifications such as the American College of Sports Medicine Certified Clinical Exercise Physiologist (5) or American Association of Cardiovascular and Pulmonary Rehabilitation Certified Cardiac Rehabilitation Professional (6). This also aligns with the standards of practice and continuing professional education as regulated by Exercise & Sports Science Australia (7). It is also important to mention that the clinical exercise physiologist is one component of the care team, and collaboration with physicians and other qualified allied health care professionals is critical for optimizing patient care that includes safe and effective exercise testing.The role of the clinical exercise physiologist continues to build momentum in exercise testing and other clinical spaces. The professional field of clinical exercise physiology has made significant progress over the past several decades and shows promise for continual advancement as a profession.

Predictors of tachycardia-induced cardiomyopathy in patients with first-time decompensation of chro­nic heart failure with reduced left ventricular ejection fraction of nonischemic etiology and persistent atrial tachyarrhythmia

Aim To identify possible predictors of tachycardia-induced cardiomyopathy (TICMP) in patients with newly developed decompensated chronic heart failure (CHF) of nonischemic origin with reduced left ventricular ejection fraction (LV EF) and with persistent atrial tachyarrhythmias.Material and methods This study included 88 patients with newly developed decompensated CHF of nonischemic origin with reduced LV EF and persistent atrial tachyarrhythmias. Resting 12-lead electrocardiography (EGC) and transthoracic echocardiography (EchoCG) were performed upon admission and following the electrical impulse therapy for all patients. Also, 24-h ECG monitoring was performed to confirm sinus rhythm stability. After recovery of sinus rhythm, outpatient monitoring was performed for three months, including repeated EchoCG to evaluate the dynamics of heart chamber dimensions and LV EF.Results The patients were divided into two groups based on the increase in LV EF: 68 responders (TICMP patients with a LV EF increase by >10%) and 20 non-responders (patients with an increase in LV EF by <10% during 3 months following the sinus rhythm recovery). According to results of the baseline EchoCG, LV EF did not significantly differ in the two subgroups (TICMP, 40±8.3 %, 18-50 % and non-responders, 38.55±7.9 %, 24-50 %); moreover, the incidence of cases with LV EF <30% did not differ either (9 patients TICMP and 2 non-responders, р=1.0). TICMP patients compared to non-responders, had significantly smaller left atrial dimensions (4.53±1.14 (2-7) cm and 5.68±1.41 (4-8) cm, р=0.034; 80.8±28.9 (27-215) ml and 117.8±41.3 (46-230) ml, р=0.03, respectively) and left ventricular end-systolic volume (ESV) (67.7±33.1 (29-140) ml and 104.5±44.7 (26-172) ml, р=0.02, respectively). The effect of major EchoCG parameters on the probability of TICMP development was assessed by one-factor and multifactor regression analyses with adjustments for age and sex. The probability of TICMP increased with the following baseline EchoCG parameters: end-diastolic volume (EDV) <174 ml [odd ratio (OR), 0.115, 95 % confidence interval (CI): 0.035-0.371], ESV <127 ml [OR, 0.034, 95 % CI: 0.007-0.181], left atrial volume <96 ml [OR, 0.08 , 95 % CI: 0.023-0.274], right ventricular dimension <4 cm [OR, 0.042 , 95 % CI: 0.005-0.389].Conclusion Among patients with newly developed decompensation of CHF with reduced LV EF of non-ischemic origin and persistent atrial arrhythmias, TICMP was detected in 72 % of patients. The probability of TICMP did not depend on baseline EF and duration of arrhythmias, but increased with the following baseline EchoCG parameters: EDV< 174 ml, ESV< 127 ml, left atrial volume <96 ml, right ventricular dimension <4 cm. The multifactorial analysis showed that a right atrial volume <96 ml is an independent predictor for the development of TICMP.

PECULIARITIES OF MYOCARDIAL BIOELECTRIC ACTIVITY IN PATIENTS WITH PROGRESSIVE MYLTIPLE MYELOMA RECEIVING BORTEZOMIB-CONTAINING CHEMOTHERAPY SCHEMES

Introduction. New approaches to the oncohematology management that also include multiple myeloma treatment, makes higher level of hematological remission and improve survival rates. But novel cytostatic drugs have higher incidence of cardiotoxicity. According to the modern multiple myeloma management guidelines, patients, who have no indications for bone morrow transplantation, should be treated by VRd chemotherapy scheme as a first line therapy. The VRd scheme includes: bortezomib, lenalidomid and dexamethasone.
 Both early cytostatic-induced cardiovascular toxicity risk factor indication and cardiovascular toxicity detection have high prognostic value due to influence on individual management strategy that include chemotherapy and supportive care. This, in turn, decreases level of late and remote cytostatic-induced myocardial injury.
 The aim of this study is to investigate changes of myocardial bioelectric activity in patients with progression of multiple myeloma during bortezomib-containing chemotherapy scheme.
 Materials and methods. 20 patients who had multiple myeloma and no concomitant cardiovascular disease were examined. All patients obtain bortezomib-containing chemotherapy scheme. The patients underwent the examination three times: before the chemotherapy, in 84th day and in 140th day. General and biochemical blood count findings were analyzed. Some points of Holter electrocardiography monitoring and standard 12-leads ECG were evaluated, including heart rate, PQ interval, and corrected QT interval.
 Results: multiple myeloma progression was associated with the development of anaemia in 19 (95%) of the patients and was characterized by the 1.3-fold decrease in the haemoglobin and red blood cells level compared to healthy individuals (p<0,05). Rate of conductivity disorder was in 1.4 times higher than rate of rhythm disorder in the patients with multiple myeloma. The following findings were obtained by Holter monitoring and standard 12-leads electrocardiography: rhythm disorder was found in 5 (25%) patients, while conductivity disorder was detected in 7 (35%) patients. Sinus bradycardia and premature ventricular contractions were found in 2 (10%) patients following the 4 course of chemotherapy that is 2,5 times lower than in case of multiple myeloma progression. The incidence of conductivity disorder during the specific treatment were higher in 1.1 (RR=1.1; 95% СІ 0.51-2.55) (p>0,05) times and includes first degree atrioventricular block detected in 5 (25%) patients, left anterior fascicular block found in 3 (15%) patients and incomplete right bundle branch block found in 1 (5%) patient.
 Conclusion. The use of bortezomib-containing chemotherapy scheme in multiple myeloma patients with low cardiovascular risk lead to the decrease on the incidence of heart rate disorders simultaneously with increasing incidence of heart conductivity disorder.

Multifunctional, breathable MXene-PU mesh electronic skin for wearable intelligent 12-lead ECG monitoring system

With the advent of an aging society and increasing concern for cardiovascular health, comfortable long-term electrocardiographic (ECG) monitoring systems in daily life are much in demand. If the system can give real-time feedback on cardiovascular status and offer timely personalized advice like doctors, it will be beneficial to promote cardiovascular health and alleviate the imbalance of medical resources. Herein, we report a multifunctional, conformal, and air-permeable electronic skin (e-skin) based on MXene-Polyurethane mesh (MPM). When used as ECG electrodes, the e-skin shows ultra-low electrode–skin contact impedance (4.68 kΩ at 1 kHz), high signal-to-noise ratio (16.5 dB), and high breathability (2.1838 kg/m2/day), and can be continuously worn for at least 7 days. As a strain sensor, the e-skin exhibits a large measurement range (>40 %) and unique segmental sensitivity (GF = 172.54 in 0 ∼ 18.64 % and 79.38 in 18.64 ∼ 50 %), which is suitable for detecting both subtle and large physiological signals. More significantly, by combining the MPM e-skin with a flexible printed circuit board (FPCB) and a merged convolutional neural network & long-short-term memory (CNN & LSTM) intelligent algorithm, the acquired wearable intelligent e-skin system can realize daily 12-hour 12-lead ECG monitoring with diagnostic accuracy over 99 % for four arrhythmias. These results show that the MPM e-skin has huge potential in multifunctional intelligent healthcare systems. In particular, an intelligent ECG system similar to a “daily doctor” is proposed for daily long-term cardiovascular health monitoring.

Multilevel hybrid accurate handcrafted model for myocardial infarction classification using ECG signals.

Myocardial infarction (MI) is detected using electrocardiography (ECG) signals. Machine learning (ML) models have been used for automated MI detection on ECG signals. Deep learning models generally yield high classification performance but are computationally intensive. We have developed a novel multilevel hybrid feature extraction-based classification model with low time complexity for MI classification. The study dataset comprising 12-lead ECGs belonging to one healthy and 10 MI classes were downloaded from a public ECG signal databank. The model architecture comprised multilevel hybrid feature extraction, iterative feature selection, classification, and iterative majority voting (IMV). In the hybrid handcrafted feature (HHF) generation phase, both textural and statistical feature extraction functions were used to extract features from ECG beats but only at a low level. A new pooling-based multilevel decomposition model was presented to enable them to create features at a high level. This model used average and maximum pooling to create decomposed signals. Using these pooling functions, an unbalanced tree was obtained. Therefore, this model was named multilevel unbalanced pooling tree transformation (MUPTT). On the feature extraction side, two extractors (functions) were used to generate both statistical and textural features. To generate statistical features, 20 commonly used moments were used. A new, improved symmetric binary pattern function was proposed to generate textural features. Both feature extractors were applied to the original MI signal and the decomposed signals generated by the MUPTT. The most valuable features from among the extracted feature vectors were selected using iterative neighborhood component analysis (INCA). In the classification phase, a one-dimensional nearest neighbor classifier with ten-fold cross-validation was used to obtain lead-wise results. The computed lead-wise results derived from all 12 leads of the same beat were input to the IMV algorithm to generate ten voted results. The most representative was chosen using a greedy technique to calculate the overall classification performance of the model. The HHF-MUPTT-based ECG beat classification model attained excellent performance, with the best lead-wise accuracy of 99.85% observed in Lead III and 99.94% classification accuracy using the IMV algorithm. The results confirmed the high MI classification ability of the presented computationally lightweight HHF-MUPTT-based model.

Heart rate-corrected QT interval prolongation is associated with decreased heart rate variability in patients with type 2 diabetes.

We investigated the association between the heart rate-corrected QT interval (QTc interval) measured by standard electrocardiography and heart rate variability (HRV) in patients with type 2 diabetes mellitus (T2DM). From March 1, 2009, to December 12, 2009, 411 patients with T2DM who underwent resting 12-lead electrocardiography and cardiovascular autonomic function testing concurrently without the exclusion criteria were consecutively recruited in this cross-sectional study. Time- and frequency-domain HRV variables were assessed for 5 minutes by beat-to-beat HRV recording. The QT interval was corrected for the heart rate using Bazett's formula. QTc interval measurements of >440 ms were considered abnormally prolonged. The mean age and diabetes duration were 56.3 ± 10.6 years and 9.6 ± 7.3 years, respectively. A total of 90 patients had QTc interval prolongation (21.9%). The participants with a prolonged QTc interval were older (59.4 ± 10.1 years vs 55.5 ± 10.6 years, P = .002), were more likely to be a woman (72.2% vs 51.7%, P = .001), had a higher prevalence of hypertension (46.7% vs 33.4%, P = .022), had a higher hemoglobin A1c level (8.8% ± 2.2% vs 8.2% ± 1.8%, P = .045), and had decreased values for the variables measuring HRV, except for the low frequency (LF)/high frequency (HF) ratio (total power [TP], 147.7 [74.1-335.9] ms vs 328.7 [185.7-721.7] ms, P = .002). After adjusting for multiple confounders, QTc interval prolongation was associated with the lowest quartile of the HRV parameters of TP (odds ratio [OR] = 3.99; 95% confidence interval [CI]: 2.29-6.96), HF (OR = 3.20; 95% CI: 1.84-5.58), LF (OR = 3.68; 95% CI: 2.10-6.43), standard deviation of the normal-to-normal interval (OR = 3.31; 95% CI: 1.89-5.77), and root-mean-square of the successive differences (OR = 1.98; 95% CI: 1.13-3.47) in patients with T2DM. Decreased values for the variables measuring HRV, except for the LF/HF ratio, might be associated with QTc interval prolongation in patients with T2DM.

Evaluation of index of cardiac-electrophysiological balance in patients with subarachnoid hemorrhage

BackgroundVarious electrocardiographic (ECG) changes occur after subarachnoid hemorrhage (SAH). Prolonged QT and corrected QT (QTc) intervals are notable changes. QT, QTc, T peak-to-end T(p-e) intervals, and Tp-e/QTc ratio are used as ventricular arrhythmia indices. In recent publications, the cardiac electrophysiological balance index (ICEB), which provides more information than other ECG parameters (QT, QTc, etc.), is recommended in predicting the risk of ventricular arrhythmia. This study aims to assess ICEB in aneurysmal SAH patients.MethodsThe study included 50 patients diagnosed with aneurysmal SAH and 50 patients diagnosed with hypertension without end-organ damage as the control group. All patients’ Fisher scores and Glasgow Coma Scale (GCS) scores were recorded. Both groups were given 12-lead ECGs. QT, QTc, Tp-e intervals, QRS duration, ICEB (QT/QRS), ICEBc (QTc/QRS), and T(p-e)/QTc values were calculated and analyzed between groups.ResultsCompared to the control group; QT (426,64 ± 14,62 vs. 348,84 ± 12,24 ms, p < 0,001), QTc (456,24 ± 28,84 vs. 392,48 ± 14,36 ms, p < 0,001), Tp-e (84,32 ± 3,46 vs. 70,12 ± 3,12, p < 0,001), Tp-e/QTc (0,185 ± 0,08 vs. 0,178 ± 0,02, p < 0,001), ICEB (4,53 ± 0,78 vs. 3,74 ± 0,28, p < 0,001) and ICEBc (4,86 ± 0,86 vs. 4,21 ± 0,24, p < 0,001) were significantly higher in patients with aneurysmal SAH. QT, QTc and Tp-e interval, Tp-e/QTc ratio, ICEB (QT/QRS) and ICEBc (QTc/QRS) were positively correlated with the Fisher score and were negatively correlated with the GCS. According to linear regression analyses, the ICEBc (QTc/QRS) found to be independently associated with the Fisher score.ConclusionThe values of the ICEB and ICEBc were significantly increased in patients with aneurysmal SAH. The severity of SAH was positively correlated with the ICEB and ICEBc. The ICEBc (QTc/QRS) independently associated with the Fisher score. This may that SAH suggest may predispose to malignant ventricular arrhythmias.

Abstract 12575: Subgroup Comparison of Deep-Learning Electrocardiogram Model Performance for Predicting New-Onset 1-Year Atrial Fibrillation Incidence

Background: Surveillance of high-risk individuals as determined by an atrial fibrillation (AF) prediction model would be a good strategy to prevent stroke and other complications from AF. Recently, several deep learning (DL) models to predict new onset AF using 12-lead electrocardiography (ECG) have been introduced. However, their performance has not been compared among different patient groups. Methods : Data of 99,281 patients who underwent 12-lead ECG at Korea University Anam Hospital from January 2017 to December 2019, excluding patients already diagnosed with AF, were studied. The data was split into a 60% training set, 20% validation set and 20% test set. Using age, sex, and raw ECG waveforms as inputs, DL models of ResNet and a multi-layered perceptron module were developed to predict 1-year new onset AF incidence. Results: The DL model using both ECG waves and simple demographic information (age and sex) as input (ECG-AS model) showed better performance compared to the DL model using only ECG waves (ECG model) for AF prediction in the test dataset (area under the receiver operating characteristics curves [AUROCs] 0.79 for ECG model and 0.89 for ECG-AS model, respectively). In subgroup analysis divided by clinical features such as CHA2DS2-VASC score, there was little difference in the performance of the DL model. Interestingly, The DL model performed worse in patients with normal sinus rhythm (NSR) compared to patients with non-NSR (AUROC 0.70 vs 0.81 for ECG model, 0.82 vs 0.90 for ECG-AS model, Table 1). Conclusions: ECG of NSR may not have sufficient information to predict AF. In applying the AF prediction DL model using 12-lead ECG to real-world clinical practice, it may be helpful to add clinical information to the input along with appropriate patient selection.

Abstract 11190: Subgroup Comparison of Electrocardiogram Deep-Learning Model Performance for Estimating Coronary Artery Calcium Score

Introduction: Despite the clinical usefulness of Coronary artery calcium score (CACS), it is difficult to use it as a routine practice due to its high cost and radiation hazard. Recently, several deep learning (DL) models to estimate CACS using 12-lead electrocardiography (ECG) have been introduced. However, their performance has not been compared among different patient groups. This study compared the performance of DL models to estimate CACS in different patient groups. Methods: The data of 5,427 patients who underwent both CT scan and 12-lead ECG at Korea University Anam Hospital from November 2012 to December 2021 was split into 80% training set and 20% test set. CNN-based DL model for predicting CACS ≥ 1 and CACS ≥ 100 using the raw ECG waveforms and several clinical factors as input was developed. Results: The DL model showed comparable performance for CACS estimation in the test dataset (area under the receiver operating characteristics curves [AUROCs] 0.77 for CACS ≥ 1 and 0.82 for CACS ≥ 100). The DL model showed better performance in patients with cardiovascular risks less than 3 compared to patients with cardiovascular risks more than 3 (AUROC 0.75 vs 0.71 for CACS ≥ 1, 0.77 vs 0.71 for CACS ≥ 100, Table 1). Among subgroups, the elderly (age &gt; 65 year-old) showed the lowest performance (AUROC 0.72 for both CACS ≥ 1 and ≥ 100). Interestingly, the model performance predicting CACS ≥ 1 is better in patients with normal sinus rhythm, whereas the model performance predicting CACS ≥ 100 is better in patients with non-normal sinus rhythm. This suggests that normal ECG can better predict healthy condition and abnormal ECG can better predict pathological condition. Conclusions: The performance of CACS estimation DL model could depend on the patient's cardiovascular risk factors. When applying the DL model to actual clinical practice, it is necessary to consider the performance of the DL model for the patient group to be applied and to selectively apply the appropriate DL model.

Abstract 13378: Association Between Social Connection and Biological Age as Determined by Artificial Intelligence-Enabled Electrocardiography

Introduction: Increasing evidence unravels the role of loneliness and social connection in cardiovascular diseases potentially mediating accelerated biological aging. The present study aims to explore the association between social connection and biological aging as determinate by artificial intelligence-enabled electrocardiography (ECG). Methods: This is an observational retrospective cohort of adults aged ≥18 seen at Mayo Clinic from 2019-2022 who completed the social determinants of health questionnaire and had a 12-lead ECG within one year of completing the questionnaire. Five questions were asked to understand each patient’s social connection . The answers were scored to assess their level of social connection from socially isolated (score of 0) to socially connected (score of 4). The biological age was predicted from ECGs using the previously developed convolutional neural network (AI-ECG age). Delta age (Δage) was defined as AI-ECG age minus chronological age, where positive values reflect an older than expected age. Results: We included 280,323 subjects (chronological age 59.7±16.4 years, 51% female). The average AI-ECG age was 59.5±13.5 year. Better social connection status correlated with lower delta age (β=-0.33 (95%CI, -0.38 and -0.28, p&lt;0.001, adjusted to chronological age and sex). Conversely, individuals reporting the least social connection were an average of 2 years older than expected whereas those with the most social connection were 2 years younger than expected by AI-ECG (Figure 1). Conclusions: Social connection is strongly associated with slower biological aging compared to chronological aging, independent of the conventional cardiovascular risk factors. This observation underscores the need to address social connection as a healthcare determinant.

Abstract 9374: Machine Learning on Automated Measurement of 12 Leads Electrocardiography Can Predict Appropriate Shock in Patients With Implantable Cardioverter Defibrillator

Introduction: Prediction for appropriate shock in patients with implantable cardioverter defibrillator (ICD) is still challenging. We tried to predict the shock by machine learning (ML) model on automated microvolt-level measurement of 12-leads electrocardiography (ECG). Hypothesis: ML on 12-leads ECG can predict appropriate ICD shock. Methods: Consecutive 177 patients (61.5±14.4years, 141males, organic heart disease: 121cases) with ICD were enrolled. ECG was measured by ECAPs12c system (Nihon-Koden) at ICD implantation. Shock was defined as appropriate ICD shock and anti-tachycardia overdrive pacing. Statistic significant predictors were extracted by univariate Cox regression analysis. Because of many correlation/confounding/multicollinearity among the predictors, multivariate Cox was not performed, and machine learning (ML) predictive model was utilized to compare the importance of the predictors. Results: Fifty-six patients were treated by appropriate shock during the observation period (median during implantation to shock: 1.85years). Thirteen significant predictors were extracted, and T-axis showed the smallest P value of univariate Cox (P=0.0007). Random Forest Classifier model demonstrated high accuracy (0.740) and T-axis showed the most important role to build the model. Receiver operating characteristics (ROC) curve analysis indicated the cut-off value as 105 degree, and Kapan-Meier curve analysis demonstrated T-axis ≥105 degree group showed worse prognosis than T-axis &gt;105 degree group. Conclusions: ML of microvolt-level measurement of 12-leads ECG potentially had high predictive value for appropriate shock of ICD, and T-axis played an essential role for the prediction.

Electrocardiographic changes in patients with raised intracranial pressure from supratentorial brain tumors.

A wide variety of electrocardiographic (ECG) changes has been described in the context of neurological catastrophe. There has been diverse and plentiful literature emphasizing the cardiac changes in acute cerebrovascular events and traumatic brain injury. In stark contrast, there is scarce literature on the incidence of cardiac dysfunction caused by raised intracranial pressure (ICP) resulting from brain tumors. The study aimed to observe the ECG changes concurrent with intracranial hypertension resulting from supratentorial brain tumors. This is a pre-specified subgroup analysis of a prospective and observational study on cardiac function in patients presenting for neurosurgery. Data of 100 consecutive patients of either sex between 18 and 60 years who presented with primary supratentorial brain tumors were analyzed. The patients were divided into two groups: Group 1 consisted of patients without clinical and radiological features of raised ICP and Group 2 consisted of patients with clinical and radiological features of raised ICP. A 12-lead ECG was obtained for every patient on the day before the neurosurgical procedure as part of the pre-anesthetic assessment. The cardiologist and the neuroanesthetist independently examined the ECG, and it was then classified and coded as per the standardized Minnesota code. Statistical analysis was performed with IBM SPSS (release 22.0; IBM Corp., Armonk, NY, USA). The normality of the distribution of continuous variables was tested using the Shapiro-Wilk test. Normally distributed variables were expressed as Mean ± SD. All nominal or categorical variables are described as frequencies and percentages. Categorical variables were compared using the Chi-square test or the Fisher's exact test. The normally distributed continuous variables were compared using Student's t-test. "P < 0.05" was considered statistically significant. About 6% in Group 1 and 32% in Group 2 had abnormal ECG. This was significantly different in Group 2 compared to Group 1 (P < 0.05). No patients in Group 1 had sinus bradycardia, whereas it was observed in 12% of the patients in Group 2 (P = 0.02). ST-segment depression was found in 12% of patients in Group 2, whereas none had it in Group 1 (P = 0.02). ST-segment elevation was noticed in 16 % in Group 2 and 2% in Group 1 (P = 0.01). T-wave abnormalities were found in 16% compared to 4% in Group 1 (P = 0.03). In patients with supratentorial tumors, we observed that those with raised ICP had a higher incidence of ECG changes than those with normal ICP. In addition, repolarization abnormalities and arrhythmias were significantly higher in patients with raised ICP.

Abstract 13052: Clinical Utilization of Natriuretic Peptide Levels Independent of WATCH-DM Score for Heart Failure Prediction in a Large-Scale Asian Diabetic Population - A Multi-Center Cohort Study

Introduction: Type 2 diabetes is an important co-morbid condition strongly associated with the risk of developing heart failure (HF). Risk scores such as the WATCH-DM score that predict the occurrence of HF among diabetes patients are largely based on data collected from white ethnicities. Hypothesis Here, we sought to investigate surrogate markers for predicting HF among type 2 diabetes patients of Asian ethnicities Methods Data on baseline characteristics (according to WATCH-DM scoring), laboratory information (mainly sugar profiles, renal function, and Natriuretic Peptide [NP]: N-Terminal Pro-B-Type Natriuretic Peptide [NT-proBNP], and 12-lead surface electrocardiography (ECG) findings were collected among adult Asians (aged ≥ 20 years old) with type 2 diabetes free from HF diagnosis from a multi-center cohort. We analyzed the clinical indicators for incident HF during the entire course of follow-up. Results: Among 6,668 study participants (mean age: 62.9±14.3 years, 49.3% male), the overall HF incidence was 13.7% (n=916) during a median of 3.6 years ([25 th ~75 th ]: 1.86~5.57 years) of follow-up period. Using backward multivariate selection, we identified aging (adjusted odd ratio [aOR]: 1.21, per 10-year increment), higher body mass index (aOR: 1.11, per 5 kg/m 2 increment), history of myocardial infarction (aOR: 2.26), atrial fibrillation rhythm (aOR: 1.72), prolonged QRS duration (aOR: 1.08, per 10-ms increment) by ECG (according to WATCH-DM score), higher NT-proBNP level (aOR: 1.47, per 1 log-transformed unit increment), and renal impairment (aOR: 1.06, eGFR per 10 mL/min/1.73m 2 decline) as independent predictors of incident HF. The optimal cutoff of NT-proBNP in predicting HF incidence was 77.3 pg/mL. Conclusions: In this large-scale survey, our findings highlighted the baseline clinical indicators and the potential utilization of ECG and NP in HF prediction among diabetic Asians. Additionally, we demonstrated that optimal predictive value of NP to be remarkably lower than contemporary HF cutoff independent of WATCH-DM score.

Abstract 13374: Effect of Moderate to Strenuous Exercise on Biological Aging as Determined by Artificial-Enabled Electrocardiography

Introduction: The physiological changes associated with aging have deleterious effects on cardiovascular function. In addition, increasing evidence showed the effect of exercise on improving cardiovascular health and reducing the aging process. The present study sought to demonstrate the association between exercise and biological age, estimated by our previously reported method using artificial intelligence-enabled electrocardiography (ECG). Methods: This retrospective observational study enrolled adults aged ≥18 years who have been evaluated at Mayo Clinic between 2019-2022 and completed the exercise questionnaire. The total time spent in moderate to strenuous exercise was calculated by multiplying the number of days engaging in exercise per week by the average minutes per day. The biological age was determined by applying our previously developed convolutional neural network model on the 12-lead ECG records (AI-ECG). The ECG records were within one year of subjects’ visits (in case of multiple visits, the closest one to the questionnaire was chosen). Positive Age-Gap (AI-ECG minus chronological age) reflects a person identified as being older by AI-ECG compared to his/her chronological age. Results: A total of 268,002 subjects (51% female) were recruited (mean age 59.7±16.4 years). Of those, 25.7% were not engaged in any exercise. The median day of engaging in exercise was 3 (Interquartile range, 2,5) per week, and the average time of exercising was 31.3±30 minutes/day. Age-Gap diminished progressively with increased duration of moderate to strenuous exercise (Figure 1). Linear regression analysis revealed exercise is an independent predictor of Age-Gap, (β= -0.043, 95%CI, -0.045 and -0.041, p&lt;0.001). Conclusions: Engaging in moderate to strenuous exercise is associated with slower biological aging relative to chronological age as determined by AI-enabled ECG.

Abstract 13811: A Percentile Approach to Refining ECG Criteria for Screening Female Athletes for Cardiac Risk

Introduction: Despite known differences in electrocardiographic (ECG) findings by sex, only empirical thresholds for both sexes exist in current ECG guidelines for screening athletes for risk of sudden cardiac death (SCD). We hypothesize that our large dataset - with diversity in age, race, and sport participation - can be utilized to improve ECG screening in female athletes. Methods: Computerized 12-lead ECGs were recorded and analyzed in female athletes who underwent PPE between 06/2010 and 09/2021. The 2017 international criteria for ECG interpretation were compared to either the 99th percentile in our cohort or the percentile that corresponded to the known disease prevalence for HCM and Long QT syndrome. For ST depression the 99.5th percentile, a marker for HCM, was used; for QTc prolongation, the 99.9th percentile was used. RS wave amplitude was considered a marker for hypertrophy or low voltage. Results: Of 3476 athletes, the 2017 international criteria classified 2.2% with at least one ECG abnormality requiring cardiological evaluation. Rates were similar across ages, race/ethnicity, and sporting discipline. Using a percentile approach based on our population, 3.3% would require additional workup. Surprisingly, ST depression up to 0.03 mV was a normal finding in this cohort. If RS voltage extremes were considered abnormal findings, an additional 9.6% of the population would be flagged using current definitions. This number decreases to 3.4% if using the 99th percentile. Conclusions: These results highlight a difference in the reported prevalence of ECG abnormalities when comparing empirically derived thresholds to statistically derived ranges that fall outside the 99th percentile. Consideration of new metrics specific to the female athlete population has the potential to further refine athlete ECG screening.

Clinical Validation of a Smartphone-based Handheld ECG Device: A Validation Study.

Remote cardiac monitoring and screening have already become an integral telemedicine component. The wide usage of several different wireless electrocardiography (ECG) devices warrants a validation study on their accuracy and reliability. Totally, 300 inpatients with the Nabz Hooshmand-1 handheld ECG device and the GE MAC 1200 ECG system (as the reference) were studied to check the accuracy of the devices in 1 and 6-limb lead performance. Simultaneous 10-second resting ECGs were assessed for the most common ECG parameters in lead I. Afterward, 6-lead ECGs (limb leads), were performed immediately and studied for their morphologies. Of the 300 patients, 297 had acceptable ECG quality in both devices for simultaneous lead I ECGs. The ECGs were inspected on-screen by a cardiologist for their rhythms, rates, axes, numbers, morphologies of premature atrial and ventricular beats, morphologies and amplitudes of PQRST waves, P-wave durations, QRS-wave durations, P-R intervals, and QT intervals. No significant differences were detected between the devices, and no major abnormalities were missed. Six-limb lead ECGs were obtained in 284 patients, of whom 281 had acceptable quality in ECGs by both devices. The morphology matching evaluation of the ECGs demonstrated an overall 98% compatibility rate, with the highest compatibility in lead I and the lowest in lead augmented vector foot. The diagnosis of critical pathological rhythms, including atrial fibrillation and high-grade atrioventricular node block, was not missed by the Nabz Hooshmand-1 and GE MAC 1200 ECG devices. Accordingly, rhythm detection as the primary purpose of handheld ECG devices was highly accurate. Both devices had acceptable sensitivity to diagnose long P-R and long and short QT intervals. Although the modern technology of smartphones and the physical inability for the 6-limb mode might cause old patients difficulty in utilizing such devices, their use for screening and follow-up is safe.

Real time system on chip based wearable cardiac activity monitoring sensor

In this research, a real time low power wearable cardiac activity monitoring device is introduced to display real time electrocardiography (ECG) signal and heart rate (HR). ECG records heart’s electrical activity and heart rate measures the contraction of the heart. The developed device consumes very less power as SoC used in this research has power consumption of 85 μW at 1.1V supply voltage. To measure heart rate and ECG waveform, the pre-gelled ECG electrodes are attached on the RA, LA and LL positon of the human’s body. These pre-gelled ECG electrodes attached to the ECG lead which is further connected to the ECG device. The ECG system is validated and the measured average HR of the subject was 71 to 82 beats per minute (BPM) and ECG graph was also plotted.