Tarık Kıvrak

Purpose: To evaluate whether quantitative retinal microvascular and structural parameters, measured by optical coherence tomography angiography (OCTA), are associated with disease severity and right ventriculo-arterial coupling in patients with pulmonary arterial hypertension (PAH). Methods: This cross-sectional study included 45 patients with confirmed PAH, stratified by New York Heart Association (NYHA) functional class (I-III). Patients with coexisting ocular pathologies were strictly excluded. Vessel density (VD) in the superficial (SCP) and deep capillary plexuses (DCP), foveal avascular zone characteristics, and ganglion cell complex (GCC) thickness were analyzed. These parameters were correlated with functional capacity (6-minute walk test [6-mWT]), NT-proBNP levels, and the echocardiographic TAPSE/sPAP ratio. Results: Retinal VD in both SCP and DCP progressively decreased with worsening NYHA functional class (p < 0.05). Retinal VD showed a significant negative correlation with NT-proBNP levels (r = –0.355, p = 0.017) and a positive correlation with 6-mWT distance (r = 0.499, p < 0.001). Crucially, retinal microvascular density demonstrated a robust positive correlation with the TAPSE/sPAP ratio (r = 0.420, p = 0.004), a surrogate for right ventriculo-arterial coupling. GCC thickness exhibited variations across NYHA classes but lacked a consistent linear progression. Conclusion: Retinal microvascular attenuation in PAH is strongly associated not only with functional and biochemical severity but also with central hemodynamic impairment represented by the TAPSE/sPAP ratio. These findings suggest that OCTA-derived vessel density may serve as a promising, non-invasive biomarker for monitoring systemic microvascular compromise and right heart function in PAH.

Paroxysmal atrial fibrillation (PAF) may be missed on intermittent electrocardiographic (ECG) recordings. We evaluated MK545Pat, a deterministic one-dimensional descriptor derived from the first-appearance order of the notes in Mozart’s Piano Sonata K.545. The CPSC 2021 dataset contains 1436 records from 105 patients, from which 116,042 15 s segments were analyzed. Each segment produced 2304 histogram features from 2942 unit-stride 59-sample blocks. Segment-level 10-fold cross-validation achieved 97.49 ± 0.18% accuracy (range, 97.16–97.71%), and a separate 90:10 segment-level holdout achieved 97.49% accuracy and 95.85% macro-F1. A separate patient-wise leave-one-subject-out (LOSO) analysis held out all records and segments from one patient at a time. The unweighted mean of the 105 held-out patient-specific segment accuracies was 71.29% (median, 78.17%; SD, 24.22%; range, 0.00–96.00%). Pattern controls were lower for identity, reverse, and interleaved assignments, while a within-group permutation retained 97.49%, as predicted by the invariance analysis. The results support MK545Pat as a reproducible feature-engineering approach and show the expected performance gap between segment-level and cross-patient evaluation.

Background/aim: Pulmonary arterial hypertension (PAH) is a progressive disorder with systemic vasculopathy, and noninvasive assessment remains challenging. The retina, sharing anatomical similarities with the cerebral microcirculation, is an accessible site for visualizing systemic vascular compromise. This study quantitatively evaluated retinal microvascular and neuroretinal structural changes in PAH patients compared to healthy controls using optical coherence tomography angiography (OCTA). Materials and methods: In this single-center, cross-sectional case-control study, 40 patients with group 1 PAH and 38 healthy controls were enrolled. For statistical independence, only the right eye of each participant was analyzed (total: 78 eyes). All participants underwent high-resolution OCTA imaging. Key metrics including vascular density (VD) in the superficial (SCP) and deep capillary plexus (DCP), foveal avascular zone (FAZ) flow density (FD), and neuroretinal thicknesses (ganglion cell complex [GCC] and retinal nerve fiber layer [RNFL]) were quantified and compared using nonparametric tests. Results: Comparison of PAH patients and controls revealed significantly reduced VD in the PAH group. In the SCP, VD was significantly lower in the whole image (p = 0.004) and the ETDRS grid (p = 0.005). Similarly, the DCP showed reduced VD in the whole image (p = 0.006). Quadrant analysis indicated marked reduction in the superior quadrant for both plexuses (p < 0.01). While FAZ area was similar between the groups (p = 0.779), FAZ FD was significantly decreased in PAH patients (p = 0.001). Structurally, mean GCC thickness was significantly reduced (p = 0.006), but RNFL thickness remained preserved (p = 0.267). Conclusion: PAH is associated with significant retinal microvascular density reduction across all plexuses. These findings provide evidence corroborating the systemic nature of PAH vasculopathy. OCTA is a promising noninvasive tool for assessing systemic microvascular involvement in this population. However, further longitudinal studies are needed to validate its utility for disease monitoring.

The Anatolian Journal of Cardiology - Peer-reviewed cardiology journal publishing original research, reviews, case reports. Impact Factor 1.5. The Anatolian Journal of Cardiology - Leading international cardiology journal with Impact Factor 1.5. Publishing original research, reviews, and case reports in cardiovascular medicine. Indexed in PubMed, Scopus, and Web of Science.

Bacteria underpin human health, environmental balance, and industrial processes. Rapid and accurate identification is essential for diagnosis and responsible antibiotic use. Culture, biochemical tests, and microscopy are slow, expensive, and depend on expert judgment, which introduces subjectivity and errors. This research aims to recommend a new generation deep learning architecture for bacterial species classification. We curated a bacterial image dataset, and this dataset contains 18,221 microscopic images from 24 species under standard laboratory conditions. All images passed clarity and focus checks. We developed a compact CNN, the Multiple Activation Network (MACNeXt). The recommended MACNeXt preserves local feature extraction and improves representation with two activation functions (GELU and ReLU) and a multi-branch design. The aim is high accuracy with low computational cost for routine clinical use. MACNeXt achieved 90.97% accuracy, 89.63% precision, 88.64% recall, and 88.99% F1-score on the test set. The calculated results and findings showcase balanced and stable performance across species with an efficient, lightweight design since the introduced MACNeXt has about 4.4 million learnable parameters. The results of the MACNeXt openly demonstrate that this CNN is a compact, lightweight, and highly accurate CNN model.

Objective: The main objective of this study is to determine the incidence and predictors of clinical outcomes in patients with AF treated with factor Xa inhibitors in a real‐world setting.Methods: The present study was a multicentre and observational study that included patients with AF who were treated with factor Xa inhibitors. The primary outcome was the composite of ischemic stroke, TIA, systemic embolism, major bleeding, and all‐cause mortality.Results: A total of 1162 patients from 26 cardiology centers were included in this study, with a median age of 72 years. During the median 12‐month follow‐up period, the primary outcome occurred in 195 patients (16.8%). Treatment with rivaroxaban compared with apixaban and edoxaban showed a lower rate of ischemic stroke, TIA, and/or systemic embolism (2.2% vs. 4.7% vs. 6.5%, respectively, p = 0.014). The major bleeding rate was similar between all three factor Xa inhibitors. The all‐cause mortality rate in the rivaroxaban group was lower compared with the apixaban and edoxaban groups (9.8% vs. 15.1% vs. 12.4%, respectively, p = 0.042). Overall, the frequency of primary outcome was 13.8%, 19.6%, and 20.6% for patients treated with rivaroxaban, apixaban, and edoxaban, respectively (p = 0.019). Older age, male sex, low body weight, high bleeding risk, heart failure, hypertension, liver failure, and treatment with apixaban 2.5 mg b.i.d. were independently associated with the development of primary outcome.Conclusion: The follow‐up data from the ANATOLIA‐AF study provides detailed data about the incidence and independent predictors of adverse clinical outcomes in patients with AF treated with factor Xa inhibitor treatment.

Background: Electrocardiography (ECG) signals are commonly used to detect cardiac disorders, with 12-lead ECGs being the standard method for acquiring these signals. The primary objective of this research is to propose a new feature engineering model that achieves both high classification accuracy and explainable results using ECG signals. To this end, a symbolic language, named Cardioish, has been introduced. Methods: In this research, two publicly available datasets were used: (i) a mental disorder classification dataset and (ii) a myocardial infarction (MI) dataset. These datasets contain ECG beats and include 4 and 11 classes, respectively. To obtain explainable results from these ECG signal datasets, a new explainable feature engineering (XFE) model has been proposed. The Cardioish-based XFE model consists of four main phases: (i) lead transformation and transition table feature extraction, (ii) iterative neighborhood component analysis (INCA) for feature selection, (iii) classification, and (iv) explainable results generation using the recommended Cardioish. In the feature extraction phase, the lead transformer converts ECG signals into lead indexes. To extract features from the transformed signals, a transition table-based feature extractor is applied, resulting in 144 features (12 × 12) from each ECG signal. In the feature selection phase, INCA is used to select the most informative features from the 144 generated, which are then classified using the k-nearest neighbors (kNN) classifier. The final phase is the explainable artificial intelligence (XAI) phase. In this phase, Cardioish symbols are created, forming a Cardioish sentence. By analyzing the extracted sentence, XAI results are obtained. Additionally, these results can be integrated into connectome theory for applications in cardiology. Results: The presented Cardioish-based XFE model achieved over 99% classification accuracy on both datasets. Moreover, the XAI results related to these disorders have been presented in this research. Conclusions: The recommended Cardioish-based XFE model achieved high classification performance for both datasets and provided explainable results. In this regard, our proposal paves a new way for ECG classification and interpretation.

An accurate diagnosis of pulmonary hypertension (PH) is crucial to ensure that patients receive timely treatment. One of the used imaging models to detect pulmonary hypertension is the X-ray. Therefore, a new automated PH-type classification model has been presented to depict the separation ability of deep learning for PH types. We retrospectively enrolled 6642 images of patients with PH and the control group. A new X-ray image dataset was collected from a multicentre in this work. A transfer learning-based image classification model has been presented in classifying PH types. Our proposed model was applied to the collected dataset, and this dataset contains six categories (five PH and a non-PH). The presented deep feature engineering (computer vision) model attained 86.14% accuracy on this dataset. According to the extracted ROC curve, the average area under the curve rate has been calculated at 0.945. Therefore, we believe that our proposed model can easily separate PH and non-PH X-ray images.

Objective: This study aimed to define the association between altitude and ticagrelor-associated dyspnea in patients with acute coronary syndrome (ACS). Methods: We studied consecutive patients with de novo ACS who were admitted to two centers at a low altitude (18 and 25 m, n = 65) and two centers at a high altitude (1313 and 1041 m, n = 136). We managed them with ticagrelor between May 2017 and September 2017. Patients with ACS underwent an interventional procedure within <90 minutes in those with ST elevation and within <3 hours in those without ST elevation. We recorded the incidence of dyspnea in patients with ACS receiving ticagrelor therapy. Results: The mean age was 59.5 ± 10 years, and the mean ejection fraction was 43% ± 18%. A total of 110 (56.7%) patients had ST elevation and 84 (43.3%) did not. There were no significant differences in cardiac risk factors, concurrent medications, or procedural variables between the two groups. Dyspnea developed during hospitalization in 53 (38%) patients from high-altitude centers and in 13 (20%) patients from low-altitude centers (66 patients represented 32% of the total ACS cohort). Conclusions: Dyspnea is a common multifactorial symptom in patients following development of ACS. Ticagrelor-induced dyspnea appears to be associated with altitude.