Background/Objectives: Cardiovascular diseases are among the leading causes of death worldwide. Early diagnosis of these conditions minimizes the risk of future death. Listening to heart sounds with a stethoscope is one of the easiest and fastest methods for diagnosing heart conditions. While heart sounds are a quick and easy diagnostic method, they require significant expert interpretation. Recently, artificial intelligence models trained based on these expert interpretations have become popular in the development of decision support systems. Methods: The proposed approach uses the popular 2016 PhysioNet/CinC Challenge dataset for PCG signals. Spectrogram image transformation was then performed to increase the representativeness of these signals. A deep learning-based model that allows for the simultaneous training of residual and attention blocks and the MLP-mixer model was used for feature extraction. A new algorithm combining the strengths of NCA and ReliefF algorithms was proposed to select the strongest features in the feature set. The SVM algorithm was used for classification. Results: With this proposed approach, over 98% success was achieved in all accuracy, sensitivity, specificity, precision, and F1-score metrics. Conclusions: As a result, an artificial intelligence-based decision support system that detects cardiovascular diseases with high accuracy is presented.

Background/Objectives: Heart attacks are the leading cause of sudden death worldwide. Early diagnosis of the main coronary arteries is vital to prevent sudden death. While occluded coronary arteries are easy to detect from electrocardiogram (ECG) signals in ST-elevation myocardial infarction (STEMI), they are not in Non-ST-Elevation Myocardial Infarction (NSTEMI) cases. This is because ECG abnormalities in NSTEMI cases are visually indistinguishable to physicians. This study aims to develop a deep learning-based method that can directly detect occluded main coronary arteries in NSTEMI patients from 12-lead ECG data without performing coronary angiography (CAG). Methods: In this study, 12-channel digital ECG signals of NSTEMI cases were collected by expert physicians and labelled by CAG processing. Thus, a unique dataset has been created in this field. In the proposed approach, the labelled signals are used to predict the occluded main coronary artery or arteries with deep learning-based models. A hybrid classification strategy has been developed. Results: A classification accuracy of 73% was achieved with the Residual & Attention & Long Short-Term Memory (LSTM)-Convolution Neural Network (CNN) (RAL-CNN) model developed on the seven-class data set. With the classification strategy ReliefF-Based Weighted Subspace—Support Vector Machine (SVM)—Ensembles (RBWSSE), the classification performance was significantly increased (about 8%), and 81.3% classification accuracy was achieved. Classification accuracies obtained with popular pre-trained CNN models are also given. Although the classification results are not top-level, they serve as a baseline model for future studies. With newer models to be developed in the future, the classification performance will be further improved for this unique data set.

Objective: Myocardial bridging (MB) is a congenital anomaly in which an epicardial coronary artery courses intramyocardially. MB-related compression is often asymptomatic but can rarely cause sudden cardiac death, arrhythmia, or ischemia. This study aimed to investigate the prevalence, demographic characteristics, and gender differences of MB. Materials and Methods: A total of 2950 patients who underwent invasive coronary angiography (CA) were retrospectively evaluated. Clinical characteristics, biochemical/hematological parameters, and angiographic findings were compared between genders. Results: MB was identified in 119 (4%) patients, of whom 75 (63%) were males and 44 (37%) were females. The mean age of patients was 61.4±10.6 yr. Among patients with MB, 60.5% had hypertension, 31.9% had diabetes mellitus, 53.8% had coronary artery disease, and 47.9% were smokers. MB was most frequently detected in the mid segment of the left anterior descending artery (LAD) in 61 patients (51.3%). No significant gender differences were observed in MB length, vessel distribution, or compression rate. Conclusion: MB is not an uncommon finding during invasive CA in middle-aged patients. The prevalence was 4% in our study. The most common site was the mid segment of the LAD. No gender-based differences were observed in MB length, vessel distribution, or compression rate.

Background and Objectives: There are few studies suggesting that the Triglyceride–Glucose Index (TyG), which is mostly defined as a predictor of diabetes, can be used as a predictor of coronary artery disease. In this study, we investigated the relationship between TyG index and acute coronary syndrome (ACS). Materials and Methods: Patients who were hospitalized in the coronary intensive care unit between January 2023–December 2024 were included in the study regardless of the admission diagnosis. ACS defined as ST elevation myocardial infarction (STEMI) and non-STEMI. The TyG index was calculated with the formula LN [fasting triglycerides (mg/dL) × fasting glucose (mg/dL)/2]. The relationship between the presence of acute coronary syndrome and troponin level was compared with the TyG index. Results: A total of 586 individuals, 353 (60.2%) males and 233 (39.8%) females, were included in this study. The mean TyG index value was calculated as 75 ± 0.31 (4.03–5.99). ACS was detected in 36.9% (n = 216) of the participants. The mean TyG index was higher in the group with ACS (4.92 ± 0.29) than in the group without ACS (4.65 ± 0.27), p < 0.001). Similarly, the mean value of triglyceride (171.58 ± 114.45 vs. 120.92 ± 63.02, CI 95%, p < 0.001) and glucose (133.57 ± 48.87 vs. 104.88 ± 34.76, CI 95%, p < 0.001) were also higher in the group with acute coronary syndrome. In logistic regression analysis, the TyG index was identified as the most significant predictor of ACS, associated with a 30.994-fold increase in ACS probability. Conclusions: This study demonstrated that the TyG index is a significant predictor of acute coronary syndrome independent of the hospitalization reason. The TyG index can be used as a valuable marker in clinical practice because it includes modifiable risk factors for coronary artery disease.

Objective: Coronary artery tortuosity (CAT) is frequently observed in invasive angiography, though its aetiology and clinical significance remain ambiguous. The aim of our study was to investigate the parameters affecting CAT in patients without normal coronary artery disease (CAD). Materials and Methods: 110 patients with CAT and no CAD and and 140 patients with no CAT and CAD were evaluated retrospectively. CAT was defined by ≥3 bends with a change in vessel direction of ≥45° present in both systole and diastole along the main trunk of at the least one coronary artery. Demographic, biochemical, echocardiogrphic and angiographic parameters were compared between groups. Results: Patients with CAT were older and more often female gender. 24 (21.8%) were males and 86 (78.2%) were females in patients with CAT. The mean age of the patients with CAT were 61.4±10.6 years and the control group was 55.9±10.9 years. Among the patients with CAT, 62.7% had hypertension, 27.3% had diabetes mellitus and 30% were smokers. But, there was not significant difference between groups (p=0.469, p=0.446, p=0.242, respectively) . Left anterior descending artery (LAD) was the most commonly affected tortuous coronary artery (86.4%). Multivariate analysis showed significant relationship between age (p=0.019), female gender (p

Objective: Atrial fibrillation (AF) is the most common cardiac arrhythmia worldwide. Its prevalence increases significantly with age. Therefore, it is particularly important in the elderly population. Despite this, elderly patients have been underrepresented in clinical studies, and optimal medical treatment is less frequently provided to this group. The aim of this study is to identify age-related patterns in elderly patients and to evaluate their relationships with comorbidities. Materials and Methods: 118 patients with permanent AF aged ≥75 years (middle-old) and 153 patients with permanent AF aged 65-75 years (youngest-old) were retrospectively evaluated. Demographic, biochemical and echocardiographic parameters were compared between groups. Results: There were 85 cases (72%) of hypertension, 43 cases (36%) of diabetes mellitus, 56 cases (48%) of coronary artery disease in patients with AF aged ≥75 years. There were 91 cases (60%) of hypertension, 43 cases (28%) of diabetes mellitus, 60 cases (39%) of coronary artery disease in patients with AF aged 65-75 years. Patients with AF aged ≥75 years had more hypertension, diabetes mellitus and coronary artery disease compared to the patients with AF aged 65-75 years (p=0.021, p=0.092, p=0.108, respectively). However, only hypertension reached statistical significance. Also, creatinine [1.15±0.36 mg/dl vs 1.03±0.23 mg/dl, p=0.003], urea [53.4±29.8 mg/dl vs 41.4±15.5 mg/dl, p<0.001] levels were higher; while eGFR [54.9±14.8 ml/min vs 69.5±17.7 ml/min, p<0.001], hemoglobin (11.5±2.1 g/dl vs 12.9±1.8 g/dl, p<0.001) and albumin [3.67±0.54 g/dl vs 4±0.44 g/dl, p=0.003] levels were lower in patients with AF aged ≥75 years compared to the patients with AF aged 65-75 years. Conclusion: Comorbidities especially hypertension and chronic kidney disease are more frequently observed in patients with AF as age increases. It is important to remember that in elderly patients with AF, it is essential to manage not only the arrhythmia itself but also any additional comorbidities.