Explore the vast range of titles available.

Patient-centered care is important in yielding positive health outcomes, particularly in the era of precision child health, where the values, preferences, goals, and unique experiences of children and their families ought to be at the forefront of care planning and delivery. Shared decision-making (SDM) is one facilitator of patient-centered care that allows patients, families and caregivers, and their healthcare providers (HCPs), to communicate and work collaboratively to ensure the childs care aligns with their personalized needs. There are immense benefits of SDM, including improved hospitalization experiences and outcomes. For children and youth, there are added benefits including improved coping mechanisms, improved communication and decision-making skills, enhanced knowledge in healthcare, and positive impacts to their developing autonomy and capacity. Despite these benefits, there is a lack of SDM in practice, particularly for children and youth with medical complexity (CMCs). Some of these barriers can include uncertainty about the childs needs, knowledge gaps on implementation, uncertainty regarding the childs capacity and desire for involvement, concern around navigating conversations, and power imbalances between families and HCPs. To better understand the prevalence and impact of SDM in paediatric complex care (PCC), we must first understand the experiences of SDM for patients and families. To achieve this, a co-design research study was created involving HCPs and parents of CMCs. While the aim of this study was to ideate strategies for improved SDM during hospitalization, it is also important to consider the ethical implications of collaborative research, specifically within PCC. As such, this presentation aims to evaluate the ethics of co-design methodology, particularly as it relates to family experiences and the impacts of meaningful engagement on their interactions and hospitalization, as well as assess whether this со-design study was able to reduce barriers to SDM. Through a literature search of current practices and a thematic analysis of the co-design study, it was evident that collaborative research is a valuable experience. By working with patient partners to understand their needs and experiences, participants felt that they were valued members of their childs team, and felt optimistic about the future of SDM and PCC.

BackgroundViral respiratory tract infections (vRTIs) are a leading cause of paediatric hospitalisation and healthcare utilisation. Existing syndromic surveillance tools, including the WHO Severe Acute Respiratory Infection definition, demonstrate limited diagnostic accuracy in children whose symptom profiles vary widely. This study aimed to develop a machine learning (ML) model to predict microbiologically confirmed vRTIs in hospitalised children and to evaluate performance across age groups and viral pathogens.MethodsWe conducted a retrospective cross-sectional study of 2050 paediatric patients (<18 years) admitted with acute respiratory infections to two tertiary paediatric hospitals in Canada. Predictors included age, sex, hospital transfer status, chronic comorbidity status and 22 presenting symptoms. The primary outcome was microbiologically confirmed vRTI, determined by multiplex PCR or rapid antigen testing. Six ML algorithms were trained and the best-performing model, identified by area under the receiver operating characteristic curve (auROC), was tested on age subgroups, viral pathogens and sites.ResultsAmong 2050 patients (median (IQR) age 2.4 (0.8–5.2) years), 1831 (89.3%) tested positive, most commonly for respiratory syncytial virus (RSV) (38.7%) and enterovirus/rhinovirus (32.8%). Logistic regression with L2 regularisation demonstrated the best performance (auROC, 0.754; 95% CI 0.697 to 0.808; sensitivity, 69.2%; specificity, 69.9%), with greatest performance among children <1 year (auROC, 0.763) and RSV cases (auROC, 0.727).ConclusionsAn ML-based logistic regression model using admission data accurately predicted paediatric vRTIs, outperforming traditional syndromic surveillance definitions, especially among infants <1 year. By integrating ML models into hospital electronic medical records, healthcare systems can achieve enhanced respiratory virus surveillance, faster outbreak detection, greater diagnostic efficiency and improved pandemic preparedness.