ABSTRACT
The coronavirus disease 2019 (COVID-19) pandemic is challenging healthcare systems worldwide. The prediction of disease prognosis has a critical role in confronting the burden of COVID-19. We aimed to investigate the feasibility of predicting COVID-19 patient outcomes and disease severity based on clinical and hematological parameters using machine learning techniques. This multicenter retrospective study analyzed records of 485 patients with COVID-19, including demographic information, symptoms, hematological variables, treatment information, and clinical outcomes. Different machine learning approaches, including random forest, multilayer perceptron, and support vector machine, were examined in this study. All models showed a comparable performance, yielding the best area under the curve of 0.96, in predicting the severity of disease and clinical outcome. We also identified the most relevant features in predicting COVID-19 patient outcomes, and we concluded that hematological parameters (neutrophils, lymphocytes, D-dimer, and monocytes) are the most predictive features of severity and patient outcome.
ABSTRACT
Objectives In Saudi Arabia, the prevalence of generalized anxiety disorder (GAD) was reported to be 29%. As a result, our goal was to examine the association between GAD and gastroesophageal reflux disease (GERD) within the general Saudi Arabian population, as well as to access the risk factors for GAD in order to gain a better understanding. Method This cross-sectional study involved 4,224 participants who completed a questionnaire. Anxiety was assessed using the General Anxiety Disorder-7 (GAD-7) scale, and the GerdQ tool was used to evaluate GERD. Result The prevalence of anxiety among participants was 29% at cutoff 10, with 73% of anxiety-positive participants being female and only 26.9% being male. Furthermore, the associations between anxiety and GERD were significant as 31.4% of participants with anxiety had GERD, compared to 15.0% of those without anxiety. Conclusion In our finding, there was a significant association between anxiety and GERD among the general Saudi population. In terms of anxiety risk factors, female, younger age, social status, body mass index, eating fried food, caffeinated drinks, diabetes miletus, high blood cholesterol, NSAID use, antidepressants, and anti-anxiety medication were found to have a significant association.
ABSTRACT
Background and ObjectivesEpilepsy is a chronic brain disease, with inherent and noninherent factors. Although over 20 anti-seizure medications (ASMs) are commercially available, nearly one-third of patients develop drug-resistant epilepsy. We evaluated the association between the clinical features and the methyl tetrahydrofolate (MTHFR) rs1801133 polymorphism and ASMs response among pediatric patients with epilepsy. Materials and Methods This was a multicenter, retrospective, case-control study of 101 children with epilepsy and 59 healthy children in Jeddah. The MTHFR rs1801133 polymorphism was genotyped using the real-time polymerase chain reaction TaqMan Genotyping Assay. Results Among the patients with epilepsy, 56 and 45 showed good and poor responses to ASMs, respectively. No significant genetic association was noted between the single-nucleotide polymorphism (SNP) rs1801133 within the MTHFR gene and the response to ASMs. However, a significant association was noted between reports of drug-induced toxicity and an increase in allele A frequencies. The MTHFR rs1801133 genotype was significantly associated with the development of electrolyte disturbance among good and poor responders to ASMs. Conclusion This is the first pharmacogenetic study of MTHFR in patients with epilepsy in Saudi Arabia that found no significant association between the MTHFR SNP rs1801133 and gene susceptibility and drug responsiveness. A larger sample size is needed for testing gene polymorphisms in the future.
