Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97–100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with

In this investigation, Rayleigh–Ritz method is used to calculate the natural frequencies of rectangular isotropic and laminated symmetric and anti-symmetric cross and angle ply composite plate with general elastic supports along its edges. Each of the admissible functions here is composed of a trigonometric function and an arbitrary continuous function that is introduced to ensure the sufficient smoothness of the so-called residual displacement function at the edges. Perhaps more importantly, this study has developed a general approach for deriving a complete set of admissible functions that can be applied to various boundary conditions. Several numerical examples are studied to demonstrate the accuracy and convergence of the current s

Ticks (Acari: Ixodidae) are ectoparasites that infest livestock in every geographic region of the world and are vectors of several viral, bacterial, and protozoan pathogens to both animals and humans. There is little information is available is about tick presence in Buffalo Bubalus bubalis (Linnaeus, 1758) (Artiodactyla, Bovidae) in Iraq. The current study determined the species of ticks parasitizing Buffalo in some central and southern regions included: Baghdad (Al Fathelia), Karbala (Al-Hussainia), Wasit (Kut and Al-Suwairah), Al-Qadisia (Al- Diwaniyah, Al- Saniya, Al-Mihnawea, and Afak), Thi Qar (Al-Nasiriyah and Al-chibayish), Missan (Amara and Qalaat Salih) and Basrah (Al-Haretha, Al-Madena and Al-Deer). A total of 150 Buffal

The present study aims to study the correlation between visfatin levels and metabolic syndrome in Iraqi obese adolescence (with and without metabolic syndrome) and its relation with other studied biochemical parameters. Sixty obese adolescences were depended in this study (with and without metabolic syndrome), compared with (30) non-obese children as control group. This study was done in the period from April 2020 until the end of December 2020, in the National Diabetes Centre/Mustansiriya University, Baghdad/Iraq. There were no significant differences in age, height, waist circumferences (WC), and diastolic blood pressure (DBP) in the patients' groups. In contrast, a significant increase differs (p<0.05) was recorded in the values of

This paper is concerned with the numerical solutions of the vorticity transport equation (VTE) in two-dimensional space with homogenous Dirichlet boundary conditions. Namely, for this problem, the Crank-Nicolson finite difference equation is derived.  In addition, the consistency and stability of the Crank-Nicolson method are studied. Moreover, a numerical experiment is considered to study the convergence of the Crank-Nicolson scheme and to visualize the discrete graphs for the vorticity and stream functions. The analytical result shows that the proposed scheme is consistent, whereas the numerical results show that the solutions are stable with small space-steps and at any time levels.

Autism Spectrum Disorder, also known as ASD, is a neurodevelopmental disease that impairs speech, social interaction, and behavior. Machine learning is a field of artificial intelligence that focuses on creating algorithms that can learn patterns and make ASD classification based on input data. The results of using machine learning algorithms to categorize ASD have been inconsistent. More research is needed to improve the accuracy of the classification of ASD. To address this, deep learning such as 1D CNN has been proposed as an alternative for the classification of ASD detection. The proposed techniques are evaluated on publicly available three different ASD datasets (children, Adults, and adolescents). Results strongly suggest that 1D

Insulin-induced hyperglycemia is the hallmark of diabetes mellitus (DM), including various metabolic disorders. Diabetic people are more likely to develop dyslipidemia, hypertension, and obesity. Type 2 diabetes ‎(T2DM), the most common illness, is generally asymptomatic in its early stages and can go misdiagnosed for years. Diabetes screening may be beneficial in some cases since early identification and treatment can lessen the burden of diabetes and its consequences.‎ This study aimed to find the relationship between Glycated hemoglobin (HbA1c) ‎and lipid profile components in T2DM‎ patients. This descriptive-analytical and cross-sectional study was performed on the control group and T2DM patients in ‎Medical City in Baghdad be