Background/Objectives: Early and accurate discrimination of neurological conditions, dementia, stroke and healthy aging, remains a critical clinical challenge. Electroencephalography (EEG) is a non-invasive measure of brain dynamics and entropy-based features obtained from multichannel EEG have shown strong discriminative ability. However, existing deep learning approaches do not sufficiently address the combined challenges of small clinical cohorts and high-dimensional entropy feature spaces. In this study, a novel architecture is proposed for multi-class neurological EEG classification under extreme small-sample conditions. Methods: A novel dual-branch Channel-wise Transformer and Attention-Branch Network (EEG-ChTABNet) are pr to

Introduction: Surgical removal of impacted lower wisdom teeth is one of the most commonly performed proce- dures in oral and maxillofacial surgery. Objectives: This study aimed to compare the operative and post-operative outcomes of 2 flap designs (limited vs. extended 2-sided flap) in surgical extractions of lower third molars (M3) regarding fully impacted teeth. Material and methods: A prospective, randomized, controlled split-mouth trial was designed, and included 27 patients with bilateral (symmetrically positioned) impacted M3. Limited 2-sided flap was performed on one side (group 1) and extended 2-sided flap on the other side (group 2). The effect of flap design on intra-operative (visibility, accessibility, and duration of surgery) a

This investigation provides a comprehensive anatomical, histological, and endocrine profile of the thyroid gland in adult guinea fowls (Numida meleagris), a species for which detailed morphological data remain scarce in avian literature. A total of ten clinically healthy specimens, representing both sexes, were subjected to morphometric analysis of their thyroid glands, including lobar dimensions and weight. Anatomical dissection revealed that the glands are bilaterally positioned at the thoracic inlet, symmetrically located near the carotid arteries. Histological examinations—conducted using Hematoxylin and Eosin and Masson\'s trichrome stains—demonstrated the presence of structurally uniform follicles surrounded by a highly vasculariz

Metabolic syndrome has emerged as an important health concern globally, especially in developing countries where urbanization and lifestyle changes are rapidly increasing. No reliable epidemiological information regarding the prevalence and risk factors associated with metabolic syndrome is available among Iraqi adults in primary health care (PHC) clinics. This study was designed to determine the prevalence rate of metabolic syndrome and identify potential risk factors among adults attending PHC centers in Baghdad. Methods: An analytical cross-sectional study design was used, targeting 412 adult subjects selected randomly from multiple PHC centers in Baghdad. Sociodemographic, lifestyle, anthropometric, and biochemical data were col

This paper proposes a hybrid artificial intelligence (AI) model that combines an Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) to predict the Quality of Service (QoS) in 5G networks. The model utilizes radio channel indicators such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Received Signal Strength Indicator (RSSI), and Channel Quality Indicator (CQI) to forecast throughput and latency levels. These indicators are critical factors affecting network performance; however, the nonlinear relationship among them makes traditional analytical models inadequate for accurate QoS prediction. The importance of the current study lies in estimating QoS in 5G networks by combining

Background: Kidney failure is the leading cause of early death for diabetic patients and is regarded as the most dangerous consequence of the disease. This can only be reversed through early detection and intervention. The incidence of type 1 diabetes, which comprises 5-10 per cent of all diabetic diseases, is rising across the globe with a rate of 15 per 100,000 people per year. Methods: 90 samples were collected and used in this study. Thirty healthy children served as controls (aged 5-15 years), 30 patients with Type 1 Diabetes Mellitus (T1DM, aged 5-15 years) and 30 patients with type 1 diabetic nephropathy (DN), aged 5-20 years). Results: highly significant increase in Urea and Creatinine levels when compared control with DN al

Problem: Cancer is regarded as one of the world's deadliest diseases. Machine learning and its new branch (deep learning) algorithms can facilitate the way of dealing with cancer, especially in the field of cancer prevention and detection. Traditional ways of analyzing cancer data have their limits, and cancer data is growing quickly. This makes it possible for deep learning to move forward with its powerful abilities to analyze and process cancer data. Aims: In the current study, a deep-learning medical support system for the prediction of lung cancer is presented. Methods: The study uses three different deep learning models (EfficientNetB3, ResNet50 and ResNet101) with the transfer learning concept. The three models are trained using a

Smoking and central obesity have both been linked to periodontitis, but their combined relationship with periodontal disease may be influenced by demographic and behavioral factors. This cross-sectional study analyzed records of 420 adult dental patients attending the College of Dentistry at the University of Baghdad. Data included demographic characteristics, smoking status, periodontal clinical findings, body mass index (BMI), and waist-to-height ratio (WHtR). Periodontitis was defined according to the 2018 classification framework, and logistic regression models were used to examine the associations of smoking and obesity-related indicators with periodontitis. The overall prevalence of periodontitis was 36.4%. Participants with p