Body mass index related electrocardiographic findings in healthy young individuals with a normal body mass index

Deep Learning Algorithms for Estimation of Demographic and Anthropometric Features from Electrocardiograms

The electrocardiogram (ECG) has been known to be affected by demographic and anthropometric factors. This study aimed to develop deep learning models to predict the subject's age, sex, ABO blood type, and body mass index (BMI) based on ECGs. This retrospective study included individuals aged 18 years or older who visited a tertiary referral center with ECGs acquired from October 2010 to February 2020. Using convolutional neural networks (CNNs) with three convolutional layers, five kernel sizes, and two pooling sizes, we developed both classification and regression models. We verified a classification model to be applicable for age (<40 years vs. ≥40 years), sex (male vs. female), BMI (<25 kg/m² vs. ≥25 kg/m²), and ABO blood type. A regression model was also developed and validated for age and BMI estimation. A total of 124,415 ECGs (1 ECG per subject) were included. The dataset was constructed by dividing the entire set of ECGs at a ratio of 4:3:3. In the classification task, the area under the receiver operating characteristic (AUROC), which represents a quantitative indicator of the judgment threshold, was used as the primary outcome. The mean absolute error (MAE), which represents the difference between the observed and estimated values, was used in the regression task. For age estimation, the CNN achieved an AUROC of 0.923 with an accuracy of 82.97%, and a MAE of 8.410. For sex estimation, the AUROC was 0.947 with an accuracy of 86.82%. For BMI estimation, the AUROC was 0.765 with an accuracy of 69.89%, and a MAE of 2.332. For ABO blood type estimation, the CNN showed an inferior performance, with a top-1 accuracy of 31.98%. For the ABO blood type estimation, the CNN showed an inferior performance, with a top-1 accuracy of 31.98% (95% CI, 31.98-31.98%). Our model could be adapted to estimate individuals' demographic and anthropometric features from their ECGs; this would enable the development of physiologic biomarkers that can better reflect their health status than chronological age.

The Relationship between Body Composition and ECG Ventricular Activity in Young Adults

This study aimed to determine the correlation between body composition (measured as weight, body mass index, and body fat percentage (BFP)) and electrocardiographic ventricular parameters (the QT and TQ intervals and the ratios between the electrical diastole and electrical systole (TQ/QT) and between the cardiac cycle and electrical diastole (RR/TQ), both for uncorrected and corrected intervals) in a sample of 50 healthy subjects (age interval 19-23 years, mean age 21.27 ± 1.41 years, 33 women and 17 men). Subjects' measurements were performed with a bioimpedancemetry body composition analyzer and a portable ECG monitor with six leads. Starting from the correlations obtained between the investigated continuous variables, we performed a standard linear regression analysis between the body composition parameters and the ECG ones. Our results revealed that some of our regression models are statistically significant (p < 0.001). Thus, a specific part of the variability of the dependent variables (ECG ventricular activity parameters for corrected QT intervals) is explained by the independent variable BFP. Therefore, body composition influences ventricular electrical activity in young adults, which implies a differentiated interpretation of the electrocardiogram in these situations.

Patterns and associated factors of electrocardiographic abnormality among type 2 diabetic patients in Amhara National Regional State Referral Hospitals, Ethiopia: a multicenter institution-based cross-sectional study

BACKGROUND

Cardiovascular diseases are the most causes of mortality and morbidity among diabetes mellitus (DM) patients. Electrocardiographic (ECG) changes are common in the early course of the disease. Little is known about the electrocardiographic abnormalities among type 2 DM patients in Ethiopia. This study determined the overall prevalence, its patterns, and the associated factors of ECG abnormalities among people living with T2DM in Amhara National Regional State referral hospitals, Ethiopia.

METHODS

A multicenter institution-based cross-sectional study was conducted from 01 April to 30 May 2021. A simple random sampling and systematic sampling techniques were employed to select the referral hospitals and study participants, respectively. A digital electrocardiograph was used to measure the ECG parameters and the other data were collected using an interviewer-administered questionnaire. Epi-data version-4.6 and Stata-14 were used for data entry and statistical analysis, respectively. The descriptive statistics were presented with tables and graphs. A binary logistic regression model was fitted to identify associated factors of ECG abnormality. In the final model, statistical significance was decided at p≤0.05, and the strength of association was indicated using an adjusted odds ratio with 95% CI.

RESULTS

Two-hundred and fifty-eight participants (response rate = 99.6%) were included for the analysis. The prevalence of overall ECG abnormality was 45% (95% CI: 39, 51%). On the basis of the electrocardiographic patterns, 57 (21.1%; 95% CI: 14.6, 32.6%) were presented with T-wave abnormality, 36 (14%; 95% CI: 10.1, 18.8%) left axis deviation, and 24 (9.3% [6.3, 13.5%]) sinus tachycardia. Higher monthly income (> 90$) (AOR = 0.51 [0.31, 0.83]), over 10 years duration of DM (AOR = 4.5[1.05, 18.94]), hypertension (AOR = 3.9 [1.6, 9.40]), fasting blood sugar of ≥ 130 mg/dl (AOR = 5.01[2.13, 12.20]), and overweight (AOR = 2.65[1.17, 5.98]) were statistically significant factors of overall ECG abnormality.

CONCLUSIONS

Nearly, half of the participants had at least one ECG abnormality. Higher-income, prolonged disease duration, hypertension, higher fasting blood sugar, and overweight were significantly associated with ECG abnormality. The findings of this study suggest the need to institute routine ECG screening for all T2DM patients to reduce ECG abnormalities and further complications.

The Influence of Obesity on Care of Adults with Cardiovascular Disease

Obesity is a strong independent predictor of cardiovascular disease. In this article, we briefly review the physiologic effects of obesity on the cardiovascular system, discuss how obesity influences history taking, physical assessment, diagnostic testing, and treatment of patients with common cardiovascular conditions such as hypertension, coronary heart disease, and chronic heart failure. Implications for nursing practice will be shared with a focus on lifestyle modifications to be included in patient education.

Deep-learning model for screening sepsis using electrocardiography

Background

Sepsis is a life-threatening organ dysfunction and a major healthcare burden worldwide. Although sepsis is a medical emergency that requires immediate management, screening for the occurrence of sepsis is difficult. Herein, we propose a deep learning-based model (DLM) for screening sepsis using electrocardiography (ECG).

Methods

This retrospective cohort study included 46,017 patients who were admitted to two hospitals. A total of 1,548 and 639 patients had sepsis and septic shock, respectively. The DLM was developed using 73,727 ECGs from 18,142 patients, and internal validation was conducted using 7774 ECGs from 7,774 patients. Furthermore, we conducted an external validation with 20,101 ECGs from 20,101 patients from another hospital to verify the applicability of the DLM across centers.

Results

During the internal and external validations, the area under the receiver operating characteristic curve (AUC) of the DLM using 12-lead ECG was 0.901 (95% confidence interval, 0.882–0.920) and 0.863 (0.846–0.879), respectively, for screening sepsis and 0.906 (95% confidence interval (CI), 0.877–0.936) and 0.899 (95% CI, 0.872–0.925), respectively, for detecting septic shock. The AUC of the DLM for detecting sepsis using 6-lead and single-lead ECGs was 0.845–0.882. A sensitivity map revealed that the QRS complex and T waves were associated with sepsis. Subgroup analysis was conducted using ECGs from 4,609 patients who were admitted with an infectious disease, and the AUC of the DLM for predicting in-hospital mortality was 0.817 (0.793–0.840). There was a significant difference in the prediction score of DLM using ECG according to the presence of infection in the validation dataset (0.277 vs. 0.574, p < 0.001), including severe acute respiratory syndrome coronavirus 2 (0.260 vs. 0.725, p = 0.018).

Conclusions

The DLM delivered reasonable performance for sepsis screening using 12-, 6-, and single-lead ECGs. The results suggest that sepsis can be screened using not only conventional ECG devices but also diverse life-type ECG machines employing the DLM, thereby preventing irreversible disease progression and mortality.

Visceral fat level correction of the left ventricular hypertrophy electrocardiographic criteria

Background

Left ventricular hypertrophy (LVH) is a well‐known risk factor for cardiovascular events. Even though there are many electrocardiographic (ECG) criteria for LVH, they still provide poor performance, especially among obese patients. The aim of this study was to examine whether adding visceral fat to ECG LVH criteria improves accuracy in the diagnosis.

Methods

One thousand seven hundred twenty two patients were included in the study. All patients underwent a complete physical examination, office blood pressure measurement, analysis of body composition, 12‐lead ECG, and M‐mode two‐dimensional echocardiography. Four standard ECG criteria for LVH were analyzed, including Cornell voltage criteria, Cornell duration criteria, Sokolow–Lyon voltage criteria, and Sokolow–Lyon product criteria. Adjustments of ECG LVH criteria were performed using visceral fat level (VFATL) and BMI. Transthoracic echocardiography was used as a reference method to compare the quality of ECG LVH criteria.

Results

Multivariate logistic regression models were created and revealed a significant increase of area under curve (AUC) after VFATL and BMI addition to ECG LVH criteria. Improvement of sensitivity at 90% specificity was observed in all created models. The odds ratio (OR) of the analyzed ECG criteria increased after adding VFATL and BMI to the models. Furthermore, ROC curves analysis exposed better characteristics in detecting LVH of VFATL‐adjusted criteria than BMI‐adjusted and unadjusted criteria.

Conclusions

Adjusting ECG indexes to BMI or VFATL improves the sensitivity of LVH detection. VFATL‐corrected indexes are more sufficiently than BMI‐corrected. After advancements in indexes, both lean and morbidly obese individuals outcomes show a greater prevalence of correct LVH diagnosis.