Electrocardiographic Variables Research Articles

Multi-Index Measurement of Fatigue Degree Under the Simulated Monitoring Task of a Nuclear Power Plant

The fatigue state of nuclear power operators is of vital importance to the safe operation of a nuclear power plant. With the development of the digital manipulation interface in recent years, the fatigue type and degree of operators have undergone changes. The interface of the nuclear power monitoring task is simulated in this experiment, and multiple fatigue detection modes are used to measure the fatigue state of operators. Results show that the subjective fatigue reporting method and PERCLOS P80 can reflect the change of fatigue state. The correlation between task performance and fatigue is not remarkable, and the sensitivity of the electrocardiographic heart rate variability indicator is poor. The accuracy also remains to be further verified.

Creatinine and NT-ProBNP levels could predict the length of hospital stay of patients with decompensated heart failure

Background Heart failure (HF) is a clinical syndrome that causes high morbidity and mortality with a high number of admissions and sometimes prolonged admissions. This study aimed at assessing whether parameters detected during the first 24 h of admission may predict a prolonged hospital stay in patients admitted to hospital for decompensated HF. Methods From January 2016 to December 2019, 2359 admissions of decompensated HF were recorded. In-hospital transfers, de novo HF, deaths and scheduled admissions were discarded to homogenise the sample. Finally, 1196 patients were included. The sample was divided into two groups: (a) non-prolonged admission (n = 643, admission ≤7 days) or (b) prolonged admission (n = 553, admission >7 days). Clinical, analytical, electrocardiographic and echocardiographic variables obtained during the first 24 h of admission were analysed. Results Univariate differences were found at admission in NT-ProBNP, creatinine, history of cardiac surgery, smoking and alcoholism, left and right ventricular ejection fraction, systolic blood pressure and heart rate. The ROC analysis showed significant areas under the curve for the NT-ProBNP (AUC: 0.63, 95% CI: 0.60–0.67; p < 0.001) and creatinine (AUC: 0.69, 95% CI: 0.66–0.72; p < 0.0001). The variables associated with prolonged hospital admission were NT-ProBNP (OR: 1, 95% CI: 1–1; p < 0.001), creatinine (OR: 2.2, 95% CI: 1.8–2.7; p < 0.0001) and previous smoking (OR: 1.5, 95% CI: 0.4–1; p < 0.02) Conclusions Variables such as creatinine and NT-ProBNP at hospital admission may define a subgroup of patients who will probably have a long hospital stay. Therefore, the planning of hospital care and transition to discharge may be enhanced.

Automated Electrocardiogram Analysis Identifies Novel Predictors of Ventricular Arrhythmias in Brugada Syndrome.

Background: Patients suffering from Brugada syndrome (BrS) are at an increased risk of life-threatening ventricular arrhythmias. Whilst electrocardiographic (ECG) variables have been used for risk stratification with varying degrees of success, automated measurements have not been tested for their ability to predict adverse outcomes in BrS.Methods: BrS patients presenting in a single tertiary center between 2000 and 2018 were analyzed retrospectively. ECG variables on vector magnitude, axis, amplitude and duration from all 12 leads were determined. The primary endpoint was spontaneous ventricular tachycardia/ventricular fibrillation (VT/VF) on follow-up.Results: This study included 83 patients [93% male, median presenting age: 56 (41–66) years old, 45% type 1 pattern] with 12 developing the primary endpoint (median follow-up: 75 (Q1–Q3: 26–114 months). Cox regression showed that QRS frontal axis > 70.0 degrees, QRS horizontal axis > 57.5 degrees, R-wave amplitude (lead I) <0.67 mV, R-wave duration (lead III) > 50.0 ms, S-wave amplitude (lead I) < −0.144 mV, S-wave duration (lead aVL) > 35.5 ms, QRS duration (lead V3) > 96.5 ms, QRS area in lead I < 0.75 Ashman units, ST slope (lead I) > 31.5 deg, T-wave area (lead V1) < −3.05 Ashman units and PR interval (lead V2) > 157 ms were significant predictors. A weighted score based on dichotomized values provided good predictive performance (hazard ratio: 1.59, 95% confidence interval: 1.27–2.00, P-value<0.0001, area under the curve: 0.84).Conclusions: Automated ECG analysis revealed novel risk markers in BrS. These markers should be validated in larger prospective studies.

Importance of Systematic Right Ventricular Assessment in Cardiac Resynchronization Therapy Candidates: A Machine Learning Approach

Despite all having systolic heart failure and broad QRS intervals, patients screened for cardiac resynchronization therapy (CRT) are highly heterogeneous, and it remains extremely challenging to predict the impact of CRT devices on left ventricular function and outcomes. The aim of this study was to evaluate the relative impact of clinical, electrocardiographic, and echocardiographic data on the left ventricular remodeling and prognosis of CRT candidates by the application of machine learning approaches. One hundred ninety-three patients with systolic heart failure receiving CRT according to current recommendations were prospectively included in this multicenter study. A combination of the Boruta algorithm and random forest methods was used to identify features predicting both CRT volumetric response and prognosis. Model performance was tested using the area under the receiver operating characteristic curve. The k-medoid method was also applied to identify clusters of phenotypically similar patients. From 28 clinical, electrocardiographic, and echocardiographic variables, 16 features were predictive of CRT response, and 11 features were predictive of prognosis. Among the predictors of CRT response, eight variables (50%) pertained to right ventricular size or function. Tricuspid annular plane systolic excursion was the main feature associated with prognosis. The selected features were associated with particularly good prediction of both CRT response (area under the curve, 0.81; 95% CI, 0.74-0.87) and outcomes (area under the curve, 0.84; 95% CI, 0.75-0.93). An unsupervised machine learning approach allowed the identification of two phenogroups of patients who differed significantly in clinical variables and parameters of biventricular size and right ventricular function. The two phenogroups had significantly different prognosis (hazard ratio, 4.70; 95% CI, 2.1-10.0; P<.0001; log-rank P<.0001). Machine learning can reliably identify clinical and echocardiographic features associated with CRT response and prognosis. The evaluation of both right ventricular size and functional parameters has pivotal importance for the risk stratification of CRT candidates and should be systematically performed in patients undergoing CRT.

In vivo analysis of concentration-dependent effects of halothane or isoflurane inhalation on the electrocardiographic and hemodynamic variables in dogs

We assessed concentration-dependent effects of halothane or isoflurane inhalation on the electrocardiographic and hemodynamic variables using a cross-over design in intact beagle dogs (n = 4). Elevation of inhaled halothane from 1.0% to 2.0% or isoflurane from 1.5% to 2.5% decreased the mean blood pressure and prolonged the QRS width without significantly altering the heart rate, PR interval or QT interval. However, the observed changes disappeared after regressions of both anesthetic conditions to their initial settings. These results indicate that hypotension-induced, reflex-mediated increase of sympathetic tone may have counterbalanced the direct negative chronotropic, dromotropic and repolarization slowing effects of the anesthetics.

Importance of systematic right ventricular assessment in patients undergoing cardiac resynchronisation therapy: A machine-learning approach

Patients undergoing cardiac resynchronisation therapy are heterogeneous. Therefore, the prediction of CRT-response and outcome is challenging. The aim of this study was to evaluate the relative impact of clinical, electrocardiographic, and echocardiographic variables on the left ventricular (LV) remodelling and prognosis of CRT-candidates by the application of machine-learning (ML) approaches. In total, 193 patients undergoing CRT (mean age 67 ± 11 years, QRS width: 167 ± 21 msec) were prospectively included in this multicentre study. We used a combination of the Boruta algorithm and random forest methods (RF) to identify features predicting both CRT-volumetric response and prognosis. The model performance was tested by the area under the receiver-operating curve (AUC). We also applied the K-medoid method to identify clusters of phenotipically-similar patients. From 28 clinical, electrocardiographic, and echocardiographic-derived variables, 16 features were predictive of CRT-response, and 11 features were predictive of prognosis. Among the predictors of CRT-response, 6 variables (38%) pertained to right ventricular (RV) size or function. The tricuspid annular plane systolic excursion was the main feature associated with prognosis. The selected features were associated with a very good prediction of both CRT-response (AUC: 0.81, 95% CI: 0.74–0.87) and outcome (AUC 0.84, 95% CI: 0.75–0.93) (Fig. 1A–B). An unsupervised ML approach allowed the identifications of two phenogroups of patients who differed significantly in clinical parameters, biventricular size and RV function and had significantly different prognosis (log-rank P < 0.0001; HR: 4.7, 95% CI: 2.1–10.0, P < 0.001) (Table 1). ML can reliably identify clinical and echocardiographic features associated with CRT-response and prognosis. Our results underscore the value of the assessment of RV-size and function parameters for the risk stratification of CRT-candidates.

Comparing of the First Electrocardiographic Variables in Patients with Newly Diagnosed COVID-19 with Healthy Men Volunteer: A Systematic Review and Meta-Analysis

Background:We aimed to report the findings of the first Electrocardiography (ECG), before therapy initiation and receiving medication in COVID-19 patients, and to compare them with the ECG findings of healthy men.Methods:A comprehensive and regular search was performed through the keywords (“Electrocardiographic” OR “ECG” OR; “COVID-19” OR “Coronavirus Disease 2019”) without time and language restrictions in the Web of Science, Scopus, ProQuest, Cochrane Library, Science Direct, Medline, PubMed and Google Scholar. After evaluating the quality and reviewing the biases, 27 studies were finally enrolled.Results:In 27 studies with a total number of 3994 COVID-19 patients, and mean age of 62.7 yr, 1993 subjects were male. The most common type of arrhythmia in them, especially in severe and critical cases, was 7% based on 10 studies (Atrial Fibrillation); while in 7 studies, QTc interval prolong (≥ 460 msec) was 15% and in 5 studies, QTc interval prolong (≥ 500 msec) was 18%. In COVID-19 patients at the time of admission and healthy men, HR (b per / min) was 85, 61.7 and PR interval (msec) was 285.4, 156 and QRS duration (msec) was 95, 94.3 and QT (msec) was 380. 384.1 and QTc (msec) (Bazett’s formula) was 437, 387.1, respectively. In most cases, the variables were higher for COVID-19 patients.Conclusion:ECG abnormalities at the time of admission and prior to the initiation of medication that cause arrhythmic may have a clinically substantial effect on the course of the disease and confirm the effect of COVID-19 on increased cardiovascular risk in long-term.

Deriving a parsimonious cardiac endpoint for use in epidemiological studies of Chagas disease: results from the Retrovirus Epidemiology Donor Study-II (REDS-II) cohort.

ABSTRACTChagas cardiomyopathy (ChCM) is a severe consequence of Trypanosoma cruzi infection and has a range of electrocardiographic (ECG) and echocardiographic (ECHO) manifestations. There is a need for a standard and parsimonious research cardiac end point that does not rely on expert panel adjudication, and it is not intended to change the ChCM definition. We use data from the REDS-II cohort to propose a simplified cardiac endpoint. A total of 499 T. cruzi-seropositive blood donors were included. All participants underwent a 12-lead ECG, echocardiogram and clinical examination, and those with abnormal findings were reviewed by a panel of cardiologists who classified cases as having Chagas cardiomyopathy or not. We created an exhaustive set of ECG and ECHO finding combinations and compared these with the panel’s classification. We selected the simplest combination that most accurately reproduced the panel’s results. Individual ECG and ECHO variables had low sensitivity for panel-defined cardiomyopathy. The best performing combination was right bundle branch block and/or ECHO evidence of left ventricular hypocontractility. This combination had 98% specificity and 85% sensitivity for panel-defined ChCM. It was not possible to improve the overall accuracy by addition of any other ECG or ECHO variable. Substituting right bundle branch block for the more inclusive finding of QRS interval > 120 ms produced similar results. The combination of prolonged QRS interval and/or left ventricular hypocontractility closely reproduced the REDS-II expert panel classification of Chagas ChCM. In conclusion, the simple and reproducible research endpoint proposed here captures most of the spectrum of cardiac abnormalities in Chagas disease.

Predicting the Development of Reduced Left Ventricular Ejection Fraction in Patients With Left Bundle Branch Block

Left bundle branch block (LBBB) increases the likelihood of developing reduced left ventricular (LV) ejection fraction (EF) but predicting which patients with LBBB and normal LVEF will develop decreased LVEF remains challenging. Fifty patients with LBBB and normal LVEF were retrospectively identified. Clinical, electrocardiographic, and echocardiographic variables were compared between patients who developed a decreased LVEF and those who did not. A total of 16 of 50 patients developed reduced LVEF after 4.3 (SD = 2.8) years of follow-up. Baseline patient and electrocardiographic variables were similar between patients who did and did not develop decreased LVEF. Baseline LVEF was lower in patients who developed decreased LVEF than in those who did not (51.9% [SD = 2.2%] vs 54.9% [SD = 4.4%], p <0.01). Diastolic filling time (DFT) accounted for a significantly smaller percentage of the cardiac cycle in patients who developed decreased LVEF than in those who did not (35.9%, [SD = 6.9%] vs 44.4% [SD = 4.5%] p <0.01). In univariable logistic regression, DFT had a C-statistic of 0.86 (p <0.0001) for prediction of development of decreased LVEF. In conclusion, patients in whom DFT accounted for <38% of the cardiac cycle had a relative risk of developing decreased LVEF of 7.0 (95% confidence interval 3.0 to 16.0) compared to patients with DFT accounting for ≥38% of the cardiac cycle.

Development and Validation of a Electrocardiographic Diagnostic Score of Heart Failure Among Patients with Hypertension Attending a Tertiary Hospital in Ibadan, Nigeria: The RISK-HHF Case-Control Study.

ObjectivesHypertension is the leading cause of HF in sub-Saharan Africa. Electrocardiography (ECG) is a cheap and easily available stratification tool for the diagnosis and prognostication of individuals with hypertension. The aim of this study was to develop an ECG-based HF diagnostic score among patients with hypertension attending a specialist cardiology clinic.MethodsOne hundred and one (101) case-control age- and sex-matched pairs were recruited. The study population were adults with a clinical diagnosis of hypertensive HF failure (cases) and systemic hypertension without HF (controls). Participants underwent clinical assessment and ECG. Associations between ECG variables and HF risk were tested with chi square test. Logistic regression modelling (age- and sex adjusted) was trained on a random subset of participants and tested on the remaining participants to determine the ECG abnormalities that are diagnostic of HF and develop a HF diagnostic score. The HF diagnostic score was then validated in an independent dataset of the ECG-Hypertension Audit. Goodness of fit and c-statistics of the HF summed diagnostic score in the training, testing and validation datasets are presented. A two-sided p value of <0.05 was considered statistically significant.ResultsThe independent ECG diagnostic markers of HF among hypertensive patients in this study in decreasing order of effect size were sinus tachycardia (aOR: 7.72, 95% CI: 2.31-25.85). arrhythmia (aOR: 7.14, 95% CI: 2.57-19.86), left ventricular hypertrophy (aOR: 4.47; 1.85-10.77) and conduction abnormality (aOR: 3.41, 95% CI: 1.21-9.65). The HF summed diagnostic score showed excellent calibration and discrimination in the training (Hosmer Lemeshow p = 0.90; c-statistic 0.82; 95% CI 0.76–0.89) and test samples (Hosmer Lemeshow p=0.31; c-statistic 0.73 95% CI 0.60 to 0.87) of the derivation cohort and an independent validation audit cohort (Hosmer Lemeshow p = 0.17; c-statistic 0.79 95% CI 0.74 to 0.84) respectively. The model showed high diagnostic accuracy in individuals with different intermediate pre-test probabilities of HF.ConclusionsA ECG based HF score consisting of sinus tachycardia, arrhythmia, conduction abnormality and left ventricular hypertrophy is diagnostic of HF especially in those with intermediate pre-test probability of HF. This has clinical importance in the stratification of individuals with systemic hypertension.

Correlation of obesity indices with QTc interval and Ankle Brachial Index in young adult population

Background: In recent times, obesity has acquired an epidemic status world over and in India. The association of obesity with vulnerability to cardiovascular ailments and peripheral vascular disease are well defined. The present study was designed to correlate between chosen obesity indices with electrocardiographic variables, Ankle brachial index(ABI) and systolic and diastolic blood pressure in asymptomatic young adults. Materials and Methods: A cross-sectional study performed on 100 subjects, with equal number of male and female participants. Blood pressure, Electrocardiogram, pulse rate were recorded in the participants after resting for ten minutes. Waist circumference, hip circumference, height and weight were measured using standard protocols defined by WHO. Student’s t test, ANOVA test and Pearsons correlation test were used to find the significance. Results: Among the randomly selected 100 subjects, 46% of male and female subjects were in the obese category (Body Mass Index >25.0). Almost 38% of male and 60% of female subjects had a Waist circumference more than the cut-off value. 28% of male and 88% of female subjects were found to have a Conicity Index (CI) more than the cut-off value. Leftward shift of the mean QRS axis correlated significantly with increasing obesity indices in both sexes. A persistent increase in systolic and diastolic blood pressure was observed among obese individuals. Results in male subject show that CI correlated with QTc interval (r=0.71; p=0.001) and diastolic blood pressure (r=0.32; p=0.02). Results among female subjects show that BMI correlated significantly with systolic(r=0.34; p=0.01) and diastolic blood pressure (r=0.35;p=0.01), WC positively correlated with systolic blood pressure(r=0.32; p=0.02) and there was a significant negative correlation between WC and ABI (r= -0.42; p=0.002) and CI correlated negatively with ABI (r= -0.36; p=0.01). Conclusion: Abdominal obesity is increasingly prevalent among young adults. The measurement of anklebrachial index by using oscillometric blood pressure instrument can be used in primary health centers and relatively unequipped clinics for provisional diagnosis of Peripheral arterial disorder and related disorders.

His-bundle pacing: A novel treatment for left bundle branch block-mediated cardiomyopathy.

Chronic left bundle branch block (LBBB) can lead to LBBB-mediated cardiomyopathy from left ventricular dysynchrony. His-bundle pacing (HBP) results in direct electrical synchrony using the native His-Purkinje system, providing a novel treatment for this cardiomyopathy. To assess the feasibility of HBP for cardiac resynchronization therapy (CRT) in LBBB-mediated cardiomyopathy patients. Retrospective database review was conducted on patients who underwent CRT by the HBP capable provider at Indiana University Health and Eskenazi Hospital from August 2015 to August 2017. A subset of patients who met the predefined syndrome criteria of LBBB-mediated cardiomyopathy who underwent HBP were identified. Clinical, echocardiographic, and electrocardiographic variables were extracted at baseline and follow-up. Nine patients had cardiomyopathy and LBBB. Among those two were lost to follow-up. Seven patients were included in the analysis. The average time from device implantation to the last follow-up was 14.5 months. Left ventricular ejection fraction improved on average from 25% to 50% (p = .0001). The left ventricular end-systolic dimension decreased from 47 to 37 mm (p = .003) and the left ventricular end-diastolic dimension decreased from 55 to 48 mm (p = .03). QRS duration with HBP-CRT decreased from 152 to 115 ms. New York Heart Association classification improved from an average of 2.7-2. HBP is a viable technique for pursuing CRT in patients with LBBB-mediated cardiomyopathy.

The value of electrocardiography and echocardiography in distinguishing Fabry disease from sarcomeric hypertrophic cardiomyopathy

Screening for Fabry disease is sub-optimal in non-specialised centres. To assess the diagnostic value of electrocardiographic scores of left ventricular hypertrophy and a combined electrocardiographic and echocardiographic model in Fabry disease. We retrospectively reviewed the electrocardiograms and echocardiograms of 61 patients (mean age 55.6±11.5 years; 57% men) with Fabry disease and left ventricular hypertrophy, and compared them with those from 59 patients (mean age 44.8±18.3 years; 66% men) with sarcomeric hypertrophic cardiomyopathy. Six electrocardiography criteria for left ventricular hypertrophy were specifically analysed: Sokolow-Lyon voltage index; Cornell voltage index; Gubner index; Romhilt-Estes score; Sokolow-Lyon product (voltage index×QRS duration); and Cornell product (voltage index×QRS duration). Right bundle branch block was more frequent in patients with Fabry disease (54% vs. 22%; P=0.001). QRS duration, Gubner score and Sokolow-Lyon product were significantly higher in patients with Fabry disease. Maximal wall thickness was higher in patients with sarcomeric hypertrophic cardiomyopathy (21.9±5.1 vs. 15.5±2.9mm; P<0.001). Indexed sinus of Valsalva diameter was larger in patients with Fabry disease. After multivariable analysis, right bundle branch block, Sokolow-Lyon product, maximal wall thickness and aortic diameter were independently associated with Fabry disease. A model including these four variables yielded an area under the receiver operating characteristic curve of 0.918 (95% confidence interval 0.868-0.968) for Fabry disease. Our model combining easy-to-assess electrocardiographic and echocardiographic variables may be helpful in improving screening and reducing diagnosis delay in Fabry disease.

Evaluation of electrocardiographic ventricular repolarization variables in patients with newly diagnosed COVID-19

IntroductionCoronavirus disease 2019 (COVID-19) is a newly recognized infectious disease that has spread rapidly. COVID-19 has been associated with a number of cardiovascular complications, including arrhythmias. The mechanism of ventricular arrhythmias in patients with COVID-19 is uncertain. The aim of the present study was to evaluate the ventricular repolarization by using the Tp-e interval, QT dispersion, Tp-e/QT ratio, and Tp-e/QTc ratio as candidate markers of ventricular arrhythmias in patients with newly diagnosed COVID-19. In addition, the relationship between the repolarization parameters and the CRP (C-reactive protein) was investigated. Methods75 newly diagnosed COVID-19 patients, 75 age and sex matched healthy subjects were included in the study between 20th March 2020 and 10th April 2020. The risk of ventricular arrhythmias was evaluated by calculating the electrocardiographic Tp-e and QT interval, Tp-e dispersion, corrected QT(QTc), QT dispersion (QTd), corrected QTd, Tp-e/QT and Tp-e/QTc ratios. CRP values were also measured in patients with newly diagnosed COVID-19. ResultsTp-e interval (80.7 ± 4.6 vs. 70.9 ± 4.8; p < .001), Tp-e / QT ratio (0.21 ± 0.01 vs. 0.19 ± 0.01; p < .001) and Tp-e/QTc ratio (0.19 ± 0.01 vs.0.17 ± 0.01; p < .001) were significantly higher in patients with newly diagnosed COVID-19 than the control group. There was a significant positive correlation between Tp-e interval, Tp-e/QTc ratio and CRP in patients with newly diagnosed COVID-19 (rs = 0.332, p = .005, rs = 0.397, p < .001 consecutively). During their treatment with hydroxychloroquine (HCQ), azithromycin and favipiravir, ventricular tachycardia episodes were observed in in two COVID-19 patients during their hospitalization in the intensive care unit. ConclusionOur study showed for the first time in literature that the Tp-e interval, Tp-e/QT ratio, and Tp-e/QTc ratio, which are evaluated electrocardiographically in patients with newly diagnosed COVID-19, were prolonged compared with normal healthy individuals. A positive correlation was determined between repolarization parameters and CRP. We believe that pre-treatment evaluation of repolarization parameters in newly diagnosed COVID-19 would be beneficial for predicting ventricular arrhythmia risk.

Eletrocardiografia computadorizada em ovinos adultos da raça Sulffolk: estudo comparativo

Computerized electrocardiography is a method widely used in veterinary medicine in several species and currently, with the availability of several devices in the market. In sheep, studies have shown variations in electrocardiographic values according to race, age, and methods of capture, but the values obtained in different computerized devices have not been compared. Thus, the present study sought to determine and compare the values of electrocardiographic variables between two computerized devices in healthy sheep. Fifty sheep (n = 50), Suffolk breed, female, launched, adult, non-pregnant, with average age and weight of two years and 50kg, respectively, were studied properly selected and clinically fit. The electrocardiographic tracings were obtained in two computerized electrocardiography devices (Apparatus A and B) individually and subsequently, with subsequent recording and interpretation of the tracings. The results showed a predominance of sinus rhythm in 78% (n = 39) and 22% (n = 11) with sinus arrhythmia in both devices. Significant differences among the devices (p <0.05) were identified in the duration variables (ms), such as P wave, P-R interval and segment, QRS complex, Q-T interval, S-T segment and T wave; and in the P-wave and R-wave amplitudes (mV). However, the values obtained were within the normal ranges recommended for the species, regardless of the capture method used. Thus, it is possible to conclude the presence of different values among the computerized electrocardiographs, suggesting variations in the tracking uptake sensitivity among the devices in released Suffolk sheep.

Applying machine learning to detect early stages of cardiac remodelling and dysfunction.

Both left ventricular (LV) diastolic dysfunction (LVDD) and hypertrophy (LVH) as assessed by echocardiography are independent prognostic markers of future cardiovascular events in the community. However, selective screening strategies to identify individuals at risk who would benefit most from cardiac phenotyping are lacking. We, therefore, assessed the utility of several machine learning (ML) classifiers built on routinely measured clinical, biochemical, and electrocardiographic features for detecting subclinical LV abnormalities. We included 1407 participants (mean age, 51 years, 51% women) randomly recruited from the general population. We used echocardiographic parameters reflecting LV diastolic function and structure to define LV abnormalities (LVDD, n = 252; LVH, n = 272). Next, four supervised ML algorithms (XGBoost, AdaBoost, Random Forest (RF), Support Vector Machines, and Logistic regression) were used to build classifiers based on clinical data (67 features) to categorize LVDD and LVH. We applied a nested 10-fold cross-validation set-up. XGBoost and RF classifiers exhibited a high area under the receiver operating characteristic curve with values between 86.2% and 88.1% for predicting LVDD and between 77.7% and 78.5% for predicting LVH. Age, body mass index, different components of blood pressure, history of hypertension, antihypertensive treatment, and various electrocardiographic variables were the top selected features for predicting LVDD and LVH. XGBoost and RF classifiers combining routinely measured clinical, laboratory, and electrocardiographic data predicted LVDD and LVH with high accuracy. These ML classifiers might be useful to pre-select individuals in whom further echocardiographic examination, monitoring, and preventive measures are warranted.

Prevalence of ECGs Exceeding Thresholds for ST-Segment-Elevation Myocardial Infarction in Apparently Healthy Individuals: The Role of Ethnicity.

BackgroundEarly prehospital recognition of critical conditions such as ST‐segment–elevation myocardial infarction (STEMI) has prognostic relevance. Current international electrocardiographic STEMI thresholds are predominantly based on individuals of Western European descent. However, because of ethnic electrocardiographic variability both in health and disease, there is a need to reevaluate diagnostic ST‐segment elevation thresholds for different populations. We hypothesized that fulfillment of ST‐segment elevation thresholds of STEMI criteria (STE‐ECGs) in apparently healthy individuals is ethnicity dependent.Methods and ResultsHELIUS (Healthy Life in an Urban Setting) is a multiethnic cohort study including 10 783 apparently healthy subjects of 6 different ethnicities (African Surinamese, Dutch, Ghanaian, Moroccan, South Asian Surinamese, and Turkish). Prevalence of STE‐ECGs across ethnicities, sexes, and age groups was assessed with respect to the 2 international STEMI thresholds: sex and age specific versus sex specific. Mean prevalence of STE‐ECGs was 2.8% to 3.4% (age/sex‐specific and sex‐specific thresholds, respectively), although with large ethnicity‐dependent variability. Prevalences in Western European Dutch were 2.3% to 3.0%, but excessively higher in young (<40 years) Ghanaian males (21.7%–27.5%) and lowest in older (≥40 years) Turkish females (0.0%). Ethnicity (sub‐Saharan African origin) and other variables (eg, younger age, male sex, high QRS voltages, or anterolateral early repolarization pattern) were positively associated with STE‐ECG occurrence, resulting in subgroups with >45% STE‐ECGs.ConclusionsThe accuracy of diagnostic tests partly relies on background prevalence in healthy individuals. In apparently healthy subjects, there is a highly variable ethnicity‐dependent prevalence of ECGs with ST‐segment elevations exceeding STEMI thresholds. This has potential consequences for STEMI evaluations in individuals who are not of Western European descent, putatively resulting in adverse outcomes with both over‐ and underdiagnosis of STEMI.

Electrocardiographic Risk Markers for Heart Failure in Women Versus Men

Heart failure (HF) is one of the leading causes of hospitalization in the Western world. Women have a lower HF hospitalization rate and mortality compared with men. The role of electrocardiography as a risk marker of future HF in women is not well known. We studied association of electrocardiographic (ECG) risk factors for HF hospitalization in women from a large middle-aged general population with a long-term follow-up and compared the risk profile to men. Standard 12-lead ECG markers were analyzed from 10,864 subjects (49% women), and their predictive value for HF hospitalization was analyzed. During the follow-up (30 ± 11 years), a total of 1,743 subjects had HF hospitalization; of these, 861 were women (49%). Several baseline characteristics, such as age, body mass index, blood pressure, and history of previous cardiac disease predicted the occurrence of HF both in women and men (p <0.001 for all). After adjusting for baseline variables, ECG sign of left ventricular hypertrophy (LVH) (p <0.001), and atrial fibrillation (p <0.001) were the only baseline ECG variables that predicted future HF in women. In men, HF was predicted by fast heart rate (p = 0.008), T wave inversions (p <0.001), abnormal Q-waves (p = 0.002), and atrial fibrillation (p <0.001). Statistically significant gender interactions in prediction of HF were observed in ECG sign of LVH, inferolateral T wave inversions, and heart rate. In conclusion, ECG sign of LVH predicts future HF in middle-aged women, and T wave inversions and elevated heart rate are associated with HF hospitalization in men.

Short-Period Temporal Dispersion Repolarization Markers Predict 30-Days Mortality in Decompensated Heart Failure.

Background and Objectives: Electrocardiographic (ECG) markers of the temporal dispersion of the myocardial repolarization phase have been shown able to identify chronic heart failure (CHF) patients at high mortality risk. The present prospective single-center study sought to investigate in a well-characterized cohort of decompensated heart failure (HF) patients the ability of short-term myocardial temporal dispersion ECG variables in predicting the 30-day mortality, as well as their relationship with N-terminal Pro Brain Natriuretic Peptide (NT-proBNP) plasmatic values. Method: One hundred and thirteen subjects (male: 59, 67.8%) with decompensated CHF underwent 5 min of ECG recording, via a mobile phone. We obtained QT end (QTe), QT peak (QTp) and T peak to T end (Te) and calculated the mean, standard deviation (SD), and normalized index (VN). Results: Death occurred for 27 subjects (24%) within 30 days after admission. Most of the repolarization indexes (QTe mean (p < 0.05), QTeSD (p < 0.01), QTpSD (p < 0.05), mean Te (p < 0.05), TeSD (p < 0.001) QTeVN (p < 0.05) and TeVN (p < 0.01)) were significantly higher in those CHF patients with the highest NT-proBNP (>75th percentile). In all the ECG data, only TeSD was significantly and positively related to the NT-proBNP levels (r: 0.471; p < 0.001). In the receiver operating characteristic (ROC) analysis, the highest accuracy for 30-day mortality was found for QTeSD (area under curve, AUC: 0.705, p < 0.01) and mean Te (AUC: 0.680, p < 0.01), whereas for the NT-proBNP values higher than the 75th percentile, the highest accuracy was found for TeSD (AUC: 0.736, p < 0.001) and QTeSD (AUC: 0.696, p < 0.01). Conclusion: Both mean Te and TeSD could be considered as reliable markers of worsening HF and of 30-day mortality. Although larger and possibly interventional studies are needed to confirm our preliminary finding, these non-invasive and transmissible ECG parameters could be helpful in the remote monitoring of advanced HF patients and, possibly, in their clinical management. (ClinicalTrials.gov number, NCT04127162).

Associations between Intrinsic Heart Rate, P Wave and QT Interval Durations and Pulse Wave Analysis in Patients with Hypertension and High Normal Blood Pressure.

The present study aimed to explore the relationship between electrocardiographic (ECG) and pulse wave analysis variables in patients with hypertension (HT) and high normal blood pressure (HNBP). A total of 56 consecutive, middle-aged hypertensive and HNBP patients underwent pulse wave analysis and standard 12-lead ECG. Pulse wave velocity (PWV), heart rate, intrinsic heart rate (IHR), P wave and QT interval durations were as follows: 7.26 ± 0.69 m/s, 69 ± 11 beats/minute, 91 ± 3 beats/minute, 105 ± 22 mm and 409 ± 64 mm, respectively. Significant correlations were obtained between PWV and IHR and P wave duration, respectively, between early vascular aging (EVA) and P wave and QT interval durations, respectively. Linear regression analysis revealed significant associations between ECG and pulse wave analysis variables but multiple regression analysis revealed only IHR as an independent predictor of PWV, even after adjusting for blood pressure variables and therapy. Receiver-operating characteristic (ROC) curve analysis revealed P wave duration (area under curve (AUC) = 0.731; 95% CI: 0.569–0.893) as a predictor of pathological PWV, and P wave and QT interval durations were found as sensitive and specific predictors of EVA. ECG provides information about PWV and EVA in patients with HT and HNBP. IHR and P wave durations are independent predictors of PWV, and P wave and QT interval may predict EVA.