A Universal Screening Tool for Dyslexia by a Web-Game and Machine Learning

Children with dyslexia have difficulties learning how to read and write. They are often diagnosed after they fail school even if dyslexia is not related to general intelligence. Early screening of dyslexia can prevent the negative side effects of late detection and enables early intervention. In this context, we present an approach for universal screening of dyslexia using machine learning models with data gathered from a web-based language-independent game. We designed the game content taking into consideration the analysis of mistakes of people with dyslexia in different languages and other parameters related to dyslexia like auditory perception as well as visual perception. We did a user study with 313 children (116 with dyslexia) and train predictive machine learning models with the collected data. Our method yields an accuracy of 0.74 for German and 0.69 for Spanish as well as a F1-score of 0.75 for German and 0.75 for Spanish, using Random Forests and Extra Trees, respectively. We also present the game content design, potential new auditory input, and knowledge about the design approach for future research to explore Universal screening of dyslexia. universal screening with language-independent content can be used for the screening of pre-readers who do not have any language skills, facilitating a potential early intervention.

A Comparison of the Malnutrition Universal Screening Tool (MUST) and the Mini Nutritional Assessment-Short Form (MNA-SF) Tool for Older Patients Undergoing General Surgery

The optimal malnutrition screening tool in geriatric surgery has yet to be determined. Herein, we compare two main tools in older patients undergoing general surgery operations. Older patients (>65 years old) who underwent general surgery operations between 2012 and 2017 in a tertiary centre were included. The Malnutrition Universal Screening Tool (MUST) and the Mini Nutritional Assessment Short Form (MNA-SF) were used for nutritional risk assessment. Preoperative variables as well as postoperative outcomes were recorded prospectively. Agreement between tools was determined with the weighted kappa (κ) statistic. Multiple regression analysis was used to assess the association of the screening tools with postoperative outcomes. A total of 302 patients (median age 74 years, range: 65–92) were included. A similar number of patients were classified as medium/high risk for malnutrition with the MNA-SF and MUST (26% vs. 36%, p = 0.126). Agreement between the two tools was moderate (weighted κ: 0.474; 95%CI: 0.381–0.568). In the multivariate analysis, MNA-SF was associated significantly with postoperative mortality (p = 0.038) and with postoperative length of stay (p = 0.001). MUST was associated with postoperative length of stay (p = 0.048). The MNA-SF seems to be more consistently associated with postoperative outcomes in elderly patients undergoing general surgery compared with the MUST tool.

Diagnostic Criteria and Lipid Screening of Dyslipidemia in Children

Obesity is associated with significant morbidities and life-threatening conditions. Evidence shows that obesity in the pediatric population has increased by ten folds recently. This has been attributed to the remarkable recent alternations in socioeconomic factors and the overall increase in the incidence of obesity among the different populations. The pathogenesis of atherosclerosis and cardiovascular diseases is usually initiated in childhood. Previous studies indicates that early identification and proper treatment of dyslipidemia in the pediatric population can significantly reduce the risk of developing cardiovascular diseases and associated morbidities. Therefore, it is vital to screen children's lipid profiles to identify dyslipidemia and apply better interventions. This can significantly reduce the risk of premature cardiovascular diseases and accelerated atherosclerosis. The present study aims to identify the diagnostic criteria and various lipid screening approaches proposed in the literature to identify dyslipidemia in children. Two main approaches for screening dyslipidemia in children were reported. These include universal and selective screening approaches. While the latter is recommended to identify high-risk children, universal screening is also recommended to identify children missed by targeted screening (usually treated by pharmacological modalities).