Predicting stroke events with a proactive fusion system: a comprehensive study on imbalance class handling in computational biomechanics.

Stroke, as a critical global health concern and the second leading cause of death, occurs when blood flow to the brain is interrupted. Although machine learning has advanced in medical safety, there is limited research on stroke prediction using information fusion systems. This study presents a fusion framework that combines multiple base classifiers and a Meta classifier to improve stroke prediction performance. The research utilizes Grid Search optimized models, such as Random Forest, Support Vector Machine, K Nearest Neighbors, AdaBoost, Gradient Boosting, Light Gradient Boosting, Categorical Boosting, and eXtreme Gradient Boosting for in-depth stroke analysis. Since stroke events are rare and unpredictable, classification outcomes can be deceptive due to imbalanced data. This article examines stroke probability by comparing three data balancing methods: over-sampling, under-sampling, and tomek-link synthetic minority over-sampling (SMOTE-TL) to enhance prediction accuracy. The findings reveal that AdaBoost as a meta-classifier attains the highest performance in the fusion framework, with a peak of 88.09% Recall and 83.66% F1 score. This innovative approach provides crucial insights into stroke prediction and can be a valuable resource for strengthening intervention efforts in advanced healthcare systems.

Frequency of the Main Human Leukocyte Antigen A, B, DR, and DQ Loci Known to Be Associated with the Clearance or Persistence of Hepatitis C Virus Infection in a Healthy Population from the Southern Region of Morocco: A Preliminary Study.

Hepatitis C Virus (HCV) infection represents a significant global health challenge, with its natural course largely influenced by the host's immune response. Human Leukocyte Antigen (HLA) molecules, particularly HLA class I and II, play a crucial role in the adaptive immune response against HCV. The polymorphism of HLA molecules contributes to the variability in immune response, affecting the outcomes of HCV infection. This study aims to investigate the frequency of HLA A, B, DR, and DQ alleles known to be associated with HCV clearance or persistence in a healthy Moroccan population. Conducted at the University Hospital Center Mohammed VI, Marrakech, this study spanned from 2015 to 2022 and included 703 healthy Moroccan individuals. HLA class I and II typing was performed using complement-dependent cytotoxicity and polymerase chain reaction-based methodologies. The results revealed the distinct patterns of HLA-A, B, DRB1, and DQB1 alleles in the Moroccan population. Notably, alleles linked to favorable HCV outcomes, such as HLA-DQB1*0301, DQB1*0501, and DRB1*1101, were more prevalent. Conversely, alleles associated with increased HCV susceptibility and persistence, such as HLA-DQB1*02 and DRB1*03, were also prominent. Gender-specific variations in allele frequencies were observed, providing insights into genetic influences on HCV infection outcomes. The findings align with global trends in HLA allele associations with HCV infection outcomes. The study emphasizes the role of host genetics in HCV infection, highlighting the need for further research in the Moroccan community, including HCV-infected individuals. The prevalence of certain HLA alleles, both protective and susceptibility-linked, underscores the potential for a national HLA data bank in Morocco.

Immunoglobulin E-Mediated Food Sensitization in a Moroccan Pediatric Population with Celiac Disease.

INTRODUCTION: Celiac disease is a chronic autoimmune disorder that occurs following the ingestion of gluten, in genetically predisposed individuals. Patients with celiac disease, especially children, are likely prone to develop allergic reactions to different food allergens. However, the relationship between food allergy and celiac disease remains not elucidated. The aim of this pioneering study was to evaluate the prevalence of allergic food sensitization in children with celiac disease in Morocco. METHODS: A total of 57 children with confirmed celiac disease, including 25 males and 32 females with a mean age of 8.6 ± 4.4 years, underwent a food allergen-specific immunoglobulin E (IgE) screening. This screening was conducted using a multiparametric immunodot assay (Euroline Food "Maghreb," Euroimmun). Statistical analysis was performed using R software. RESULTS: Among the 57 cases tested, the overall rate of IgE-mediated sensitization to food allergens was found to be 48% (27/57), dominated by chicken, with 51.9% (14/27), followed by almond, 40.7% (11/27), sesame, 40.7% (11/27), potato 33.3% (9/27), and apple 18.5% (5/27). Of the s-IgE positive cases, 74% were sensitized at least to one allergen, 37% (10/27) were sensitized to both chicken and almond allergens. A significant correlation was observed between almond, sesame, chicken, and potato. CONCLUSION: The current study highlighted a high prevalence of food allergen sensitization in children with celiac disease. This underlines the potential benefit in screening for food allergy in celiac patients.