recommendations for treating hypoglycaemic episodes with 0.3 g/kg of fast acting carbohydrates. Aim The aim of this audit was to evaluate patients' management of hypoglycaemia in accordance to BSPED guidance and to assess the impact of standardising advice on patient management and patients' HbA1c. Patient population The target population was children and young people managed for Type 1 diabetes mellitus in the NHS trust. Method Between January and March 2018, patients' management of hypoglycaemia was reviewed with a questionnaire when they attended a multidisciplinary clinic. They were educated and given a patient leaflet including an individualised plan in line with BSPED guidance. Their management of hypoglycaemic episodes was subsequently re-evaluated at future clinic appointments. Results Of the 121 patients initially assessed, 83% used the correct threshold of blood glucose <4 mmol/L to treat hypoglycaemia and 34% managed hypoglycaemic episodes appropriately. After education in clinic and the provision of a patient leaflet this improved to 90% of patients using the correct threshold. For the 52 patients who were assessed pre and post education, initially 23% had appropriate management of hypoglycaemic episodes and this improved to 60%. Over the audit period the average HbA1c dropped from 66.6 to 64.7 mmol/ mol on one site and 70 to 66 mmol/mol on the other. Conclusion This audit shows that verbal and written education on management of hypoglycaemic episodes in paediatric patients with T1DM is effective in improving the diagnosis and treatment of hypoglycaemic episodes and therefore can enhance patient care.
performance of the machine learning classifiers was compared to a baseline logistic regression model. Results There were 564 patients in the study population, of whom 307 had a LOS greater than three days and 105 had a LOS greater than seven days. Using the seven-day threshold, the optimal model was the random forest, which achieved an AUC of 0.785 and correctly classified 42.9% of long LOS patients. Using the three-day threshold, the optimal model was the multilayer perceptron, which achieved an AUC of 0.737 and correctly classified 85.7% of long LOS patients. The performance of the machine learning models was variable, and they did not unanimously outperform the baseline models. Conclusions The machine learning models performed poorly in predicting long LOS. Further work is required to assess the clinical utility and value of deep learning methods in an operational setting.
BackgroundResearch suggests that improving communication skills of healthcare professionals improves treatment adherence, patient safety and health outcomes for children and young people (CYP). There are significant challenges to putting CYP centred communication into practice, and young people report that they often feel left out of conversations. Me first has developed innovative educational resources to help address these challenges and promote CYP centred communication.Design
Me first aims to improve health outcomes of CYPs by enhancing the knowledge, skills and confidence of health and social care professionals (HSCPs) in communicating with CYPs.Strategy
Me first training and resources have been co-developed with children, young people and HCSPs and have a strong evidence base in research. The Me first communication model is the first communication model designed specifically for CYPs. Me first masterclasses facilitate peer-to-peer learning, and provide practical advice, resources, and quality improvement techniques. In addition to this, the Me first website (www.mefirst.org.uk) contains learning materials to support Me first training, including the model, a hub of resources and tips for practitioners that can be filtered for the user’s specific needs. The impact of Me first masterclasses on CYP-centred care has been evaluated by the Evidence Based Practice Unit at University College London and the Anna Freud Centre using self-report questionnaires and interviews.Results and conclusion98% of professionals attending the Me first masterclass rate the experience overall as four or five out of five (1=poor and 5=excellent). Findings from the independent evaluation demonstrate a significant improvement in HSCPs attitudes towards collaborative practice with CYPs. This was maintained at the four–to-six week follow-up. It also showed that HSCP’s communication behaviours improved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.