A transfer learning enabled approach for ocular disease detection and classification.

Ocular diseases pose significant challenges in timely diagnosis and effective treatment. Deep learning has emerged as a promising technique in medical image analysis, offering potential solutions for accurately detecting and classifying ocular diseases. In this research, we propose Ocular Net, a novel deep learning model for detecting and classifying ocular diseases, including Cataracts, Diabetic, Uveitis, and Glaucoma, using a large dataset of ocular images. The study utilized an image dataset comprising 6200 images of both eyes of patients. Specifically, 70% of these images (4000 images) were allocated for model training, while the remaining 30% (2200 images) were designated for testing purposes. The dataset contains images of five categories that include four diseases, and one normal category. The proposed model uses transfer learning, average pooling layers, Clipped Relu, Leaky Relu and various other layers to accurately detect the ocular diseases from images. Our approach involves training a novel Ocular Net model on diverse ocular images and evaluating its accuracy and performance metrics for disease detection. We also employ data augmentation techniques to improve model performance and mitigate overfitting. The proposed model is tested on different training and testing ratios with varied parameters. Additionally, we compare the performance of the Ocular Net with previous methods based on various evaluation parameters, assessing its potential for enhancing the accuracy and efficiency of ocular disease diagnosis. The results demonstrate that Ocular Net achieves 98.89% accuracy and 0.12% loss value in detecting and classifying ocular diseases by outperforming existing methods.

Knowledge of symptoms, risk factors, and treatment centers of stroke among the general population of Al-Ahsa, Saudi Arabia.

Background: In Saudi Arabia, stroke is a significant cause of illness and mortality progressively becoming more serious. Studies have indicated that modifiable cardiovascular risk factors are responsible for a significant portion of the burden caused by stroke, which could be targeted through public awareness. Objective: We evaluated the level of knowledge about stroke among the general population of the Al-Ahsa, Saudi Arabia. Furthermore, association between stroke level of knowledge and sample characteristics was analyzed. Methods: This was a cross-sectional study conducted from February 22, 2023, to March 22, 2023, using a convenience sampling technique. An electronic Google Forms survey was distributed through social media, to reach the maximum number of participants. Results: This study included a total of 500 participants from Al-Ahsa, Saudi Arabia. Forty-three percentage of participants were male, while 57% were females. Most participants were of a younger age, where 66.6% were 18-39 years. The most recognized stroke symptom, risk factor, and stroke treatment center were dizziness/vertigo (91%), hypertension (97%), and King Fahad Hospital, respectively. Those with higher education possessed a greater level of stroke-related knowledge than other demographic groupings. Conclusion: The general public of Al-Ahsa demonstrated a high level of knowledge about stroke symptoms (82.6%), risk factors (90%), and treatment facilities (80%). However, it was evident that the general public failed to recognize the proper course of action in the event of a stroke.

Résumé Contexte: En Arabie Saoudite, les accidents vasculaires cérébraux sont une cause importante de maladie et de mortalité, qui s'aggrave progressivement. Des études ont indiqué que les facteurs de risque cardiovasculaires modifiables sont responsables d'une part importante du fardeau causé par les accidents vasculaires cérébraux, qui pourraient être ciblés par la sensibilisation du public. Objectif : Nous avons évalué le niveau de connaissances sur les accidents vasculaires cérébraux au sein de la population générale d'Al-Ahsa, en Arabie Saoudite. De plus, l'association entre le niveau de connaissance de l'AVC et les caractéristiques de l'échantillon a été analysée. Méthodes : Il s'agit d'une étude transversale menée du 22 février 2023 au 22 mars 2023, en utilisant une technique d'échantillonnage de convenance. Une enquête électronique Google Forms a été diffusée sur les réseaux sociaux afin d'atteindre le nombre maximum de participants. Résultats : Cette étude a inclus un total de 500 participants d'Al-Ahsa, en Arabie Saoudite. Quarante-trois pour cent des participants étaient des hommes, tandis que 57 % étaient des femmes. La plupart des participants étaient plus jeunes, 66,6 % ayant entre 18 et 39 ans. Les symptômes d'accident vasculaire cérébral, les facteurs de risque et les centres de traitement des accidents vasculaires cérébraux les plus reconnus étaient respectivement les étourdissements/vertiges (91 %), l'hypertension (97 %) et l'hôpital King Fahad. Les personnes ayant fait des études supérieures possédaient un niveau de connaissances plus élevé sur les accidents vasculaires cérébraux que les autres groupes démographiques. Conclusion : Le grand public d'Al-Ahsa a démontré un niveau élevé de connaissances sur les symptômes de l'AVC (82,6 %), les facteurs de risque (90 %) et les installations de traitement (80 %). Cependant, il était évident que le grand public ne reconnaissait pas la marche à suivre en cas d'accident vasculaire cérébral. Mots-clés: Al-Ahsa, neurologie, connaissance publique, Arabie Saoudite, accident vasculaire cérébral.

Coalition excision and corrective osteotomies versus coalition excision and arthroereisis in management of pes planovalgus with talo-calcaneal coalition in adolescents: A randomized controlled trial.

BACKGROUND: Talocalcaneal coalition is the most common cause of rigid flat foot in adolescents. It presents with recurrent ankle sprains, foot and ankle pain, and foot deformity. Management is still controversial. Multiple options were utilized during the last 40 years, including coalition excision only or coalition excision with hind foot arthrodesis or corrective osteotomies. However, the effect of arthroereisis after coalition excision is still questionable. PATIENTS AND METHODS: Thirty feet in 28 patients with rigid flat foot due to talocalcaneal coalition, who presented to our institution between September 2018 and April 2020, were prospectively analyzed. Randomization was performed by random allocation using a computer-based system into two groups: group A for coalition excision and arthroereisis, group B for coalition excision and osteotomies. Functional and radiological outcomes and complications were recorded and analyzed using Statistical Package for the Social Sciences software. RESULTS: Thirty feet in 28 patients were included in the final analysis (15 feet in each group). One patient in each group had bilateral affection. The mean age was 14.5 years, and the mean follow-up duration was 24 months. At final follow-up, the mean AOFAS was 78.8 ± 4.04 in group A and 76.73 ± 4.66 in group B, while the FAAM scores were 80 ± 5 and 79 ± 3 in groups A and B, respectively. The complication rate was higher in group A, however with no statistical significance. CONCLUSION: The combination of talocalcaneal coalition resection with either corrective osteotomies or arthroereisis had a significant improvement of functional and radiological outcomes in the management of rigid pes planovalgus.

Whole-genome sequencing of the clinical isolate of Legionella pneumophila ALAW1 from the West Bank allows high-resolution typing and determination of pathogenicity mechanisms.

Background: Legionella pneumophila is water-based bacterium causing Legionnaires' disease (LD). We describe the first documented case of nosocomial LD caused by L. pneumophila sequence type (ST) 461 and serogroup 6. The etiology of LD was confirmed by culturing the bronchoalveolar lavage sample retrieving L. pneumophila strain ALAW1. A 7-days treatment of the LD patient with Azithromycin and Levofloxacin allowed complete recovery. Methods: In details, we sequenced the whole genome of the L. pneumophila ALAW1 using Illumina HiSeq platform. The sequence of ALAW1 was aligned with the genome sequence from the closely related reference strain Alcoy 2300/99 and a whole-genome phylogeny based on single nucleotide polymorphisms (SNPs) was created using Parsnp software. Also, the TYGS web-server was used in order to compare the genome with type strain. Results: An analysis of the population structure by SNP and TYGS comparison clustered ALAW1 with the reference genome Alcoy 2300/99. Blastp analysis of the type IV secretion Dot/Icm system genes showed that these genes were highly conserved with (≤25%) structural differences at the protein level. Conclusions: Overall, this study provides insights into detailed genome structure and demonstrated the value of whole-genome sequencing as the ultimate typing tool for Legionella.

Pseudomyogenic Hemangioendothelioma Involving the Esophagus: A Case Report.

Herein, we describe the case of a 20-year-old woman who presented with dysphagia of 2 months' duration associated with vomiting, moderate abdominal pain, decreased oral intake, and significant weight loss. During the past 3 years, the patient experienced intermittent mild abdominal pain with infrequent vomiting. Endoscopy at Jordan University Hospital showed a mass in the esophagus, and endoscopic biopsies were performed. The preliminary histopathological report excluded malignancy. Two days after endoscopy, the patient presented to the emergency department complaining of severely worsening pain and total dysphagia. The pain persisted despite intravenous paracetamol administration, which was concerning for esophageal perforation; therefore, an urgent surgical intervention was performed. The mass was removed surgically, along with a para-esophageal lymph node. The final histopathological results of the endoscopic and resected specimens supported the diagnosis of pseudomyogenic hemangioendothelioma (PMHE). This is the first case reporting esophageal involvement of PMHE.

Seasonal behavior and forecasting trends of tuberculosis incidence in Holy Kerbala, Iraq.

Background: Pulmonary tuberculosis (PTB) remains major public health problem over the world. Cities witnessing religious event throughout of the year like Kerbala/Iraq require great efforts to minimize the incidence of deadly communicable diseases like TB. The aim of this study is to model the monthly incidence rates of PTB cases in Kerbala/Iraq. Methods: This is a retrospective study in which records of confirmed PTB patients whom they referred to the chest and respiratory illnesses center of Holy Kerbala governorate were obtained. Monthly registered new smear-positive PTB cases from January 2010 to December 2016 were analyzed. Seasonal autoregressive integrated moving average (SARIMA), SARIMA-exponential smoothing method (ETS), SARIMA-neural network autoregressive, and SARIMA-adaptive neuro-fuzzy inference system (SARIMA-ANFIS) were used for forecasting monthly incidence rate of TB in Kerbala, Iraq. Mean absolute percentage error, root mean square error, and mean absolute square error were used to compare the models, and Akaike information criterion (AIC) and Bayesian information criterion (BIC) were used to selected best model. Results: The trend of PTB incidence showed a seasonal characteristic, with peaks in spring and winter. Predicted estimates using all models proposed to forecast the number of PTB cases from 2016 to 2018 showed that the PTB cases indicated marginal decrease trends and best forecasted in SARIMA-ANFIS model (the lower AIC and BIC values, 712.69 and 731.05, respectively). Conclusion: Seasonal characteristic of PTB incidence was observed with peaks during spring and winter. Forecasting of PTB incidence between the period 2016 and 2018 showed marginal decrease trends, and the best forecasting model was SARIMA-ANFIS model.

Snapshot of the genetic diversity of Mycobacterium tuberculosis isolates in Iraq.

UNLABELLED: This study explored the genetic diversity of Mycobacterium tuberculosis isolates in Iraq by spoligotyping and 15-locus-based mycobacterial interspersed repetitive unit-variable number tandem repeat (MIRU-VNTR) methods. Initially, 270 isolates from 134 patients were collected and then 134 non-duplicating isolates (1 isolate/patient) were subjected to the study analyses, 70 isolates were found to be multidrug resistant (MDR) upon testing by proportion method on Löwenstein-Jensen medium. Spoligotyping yielded 39 patterns; 111/134 (82.2%) isolates being grouped in 16 clusters vs. 23/134 (17.2%) isolates being unique. SIT1144/T1 represented the largest cluster (n=20, 14.9%), followed by SIT25/CAS1_Delhi (n=19, 14.2), SIT22/CAS1_Delhi (n=12, 9%); the other clusters ranged from 2 to 8 isolates. The SIT1144 is not reported in neighboring countries and only 4 isolates were reported worldwide (2 in USA, 1 in Venezuela, and 1 in Greece). This study reported 4 isolates belonging to SIT41/Turkey family, and thus it seems that this family is not exclusive to Turkey as previously thought. CAS lineage was predominant in this study (42.5%), followed by ill-defined T (29.9%). Highly diverse MIRU-VNTR genotypes were displayed; 100 distinct MIRU-VNTR genotypes were detected (8 clusters with 2-8 strains/cluster and 92 unique). The clustering rate was 18.03%. The discriminatory efficiency of MIRU-VNTR was high (Hunter-Gaston discriminatory index [HGDI]=0.992); it was higher than that of spoligotyping (HGDI; 0.930). However, the highest discriminatory power was provided by spoligotyping and MIRUs together. Owing to the low clustering rate by MIRU-VNTR, these results suggest that drug-resistance TB in Iraq is due to acquired resistance as opposed to transmission. CONCLUSION: Iraq is specific in having its own most predominant lineage (SIT1144/T1) which is not found among neighboring countries. The 15-locus MIRU-VNTR can be useful in discriminating M. tuberculosis isolates in Iraq.