Atrial fibrillation (AF) is a common arrhythmia that can lead to stroke, heart failure, and premature death. Manual screening of AF on electrocardiography (ECG) is time-consuming and prone to errors. To overcome these limitations, computer-aided diagnosis systems are developed using artificial intelligence techniques for automated detection of AF. Various machine learning and deep learning (DL) techniques have been developed for the automated detection of AF. In this review, we focused on the automated AF detection models developed using DL techniques. Twenty-four relevant articles published in international journals were reviewed. DL models based on deep neural network, convolutional neural network (CNN), recurrent neural network, long short-term memory, and hybrid structures were discussed. Our analysis showed that the majority of the studies used CNN models, which yielded the highest detection performance using ECG and heart rate variability signals. Details of the ECG databases used in the studies, performance metrics of the various models deployed, associated advantages and limitations, as well as proposed future work were summarized and discussed. This review paper serves as a useful resource for the researchers interested in developing innovative computer-assisted ECG-based DL approaches for AF detection.

Introduction: The most important way to reduce CVD-related mortality is to apply appropriate treatment according to the risk status of the patients. For this purpose, the SCORE risk model is used in Europe. In addition to these risk models, some anthropometric measurements are known to be associated with CVD risk and risk factors. Objectives: This study aimed to investigate the association of these anthropometric measurements, especially neck circumference (NC), with the SCORE risk chart. Methods: This was planned as a cross-sectional study. The study population were classified according to their SCORE risk values. The relationship of NC and other anthropometric measurements with the total cardiovascular risk indicated by the SCORE risk was investigated. Results: A total of 232 patients were included in the study. The patients participating in the study were analysed in four groups according to the SCORE ten-year total cardiovascular mortality risk. As a result, the NC was statistically significantly lower among the SCORE low and moderate risk group than all other SCORE risk groups (low-high and very high 36(3)–38(4) (IQR) p: 0.026, 36(3)–39(4) (IQR) p < 0.001, 36(3)–40(4) (IQR) p < 0.001), (moderate-high and very high 38(4) vs. 39(4) (IQR) p: 0.02, 38(4) vs. 40(4) (IQR) p < 0.001, 39(4) vs. 40(4) (IQR) p > 0.05). NC was found to have the strongest correlation with SCORE than the other anthropometric measurements. Conclusions: Neck circumference correlates strongly with the SCORE risk model which shows the ten-year cardiovascular mortality risk and can be used in clinical practice to predict CVD risk.

Background: Hypertension (HTN) remains a major global health problem, and inadequate blood pressure (BP) control contributes substantially to cardiovascular risk. The endothelial activation and stress index (EASIX), derived from routine laboratory parameters, has been proposed as a marker of vascular stress. Existing studies in hypertensive populations relied on office BP measurements and included patients with multiple comorbidities. This study evaluated the association between EASIX and 24-h ambulatory BP monitoring (ABPM) in a homogeneous cohort with isolated primary HTN. Methods: This retrospective cross-sectional study included 192 adults aged 18–70 years diagnosed with HTN and undergoing 24-h ABPM. Patients were categorized into controlled and uncontrolled BP groups according to 24-h, daytime, and nighttime ABPM thresholds defined by the 2024 European Society of Cardiology guideline. The EASIX score was calculated as [lactate dehydrogenase × creatinine]/platelets and log ₂ -transformed for analysis. Group comparisons, correlation analyses, multivariable logistic regression, and ROC analyses were performed. Results: The EASIX score was significantly higher in the uncontrolled BP group than in the controlled BP group. Logistic regression identified ascending aortic diameter, serum sodium, serum albumin, and log ₂ (EASIX) as independent factors associated with BP control status. EASIX demonstrated good discriminative performance in identifying hypertensive patients with inadequate BP control on 24-h ABPM. Conclusions: EASIX demonstrated good discriminative performance for identifying hypertensive patients with inadequate BP control on ABPM. These findings suggest its potential role in risk stratification, warranting validation in prospective studies. Graphical