To develop machine-learning (ML) models during the COVID-19 pandemic and adjacent time periods to evaluate the impact of data drift on model performance.

This prognostic study used population-level administrative health data to develop ML prediction models.

Alberta, Canada during 2019–2023.

All patients over 18 who received at least one opioid dispensation from a community pharmacy within the province of Alberta between 2019–2023.

Each opioid dispensation served as the unit-of-analysis.

Opioid-related outcomes were identified from linked health administrative datasets. Light Gradient Boosting-machine models were developed on pre-pandemic, pandemic and endemic data and temporally validated on 2023 data (pre-pandemic model was also validated on 2020–2021 data) to predict the risk of emergency department visit, hospitalisation or mortality within 30-days of an opioid dispensation. We described key feature distributions across the study time period and changes in model prediction performance on the validation sets using relevant metrics.

Among 1.2 million study participants representing over 13 million opioid dispensations, there were 59 809 (2.1%), 134 402 (2.4%) and 62 143 (2.3%) events reported in the pre-pandemic (2019), pandemic (2020 and 2021) and endemic (2022) time periods, respectively (estimated 2023 validation set pre-test probability of 2.8%). Notable differences in key features were observed in the 2020–2021 model relative to other years. In the 2023 validation set, discrimination performance was highest for the pre-pandemic and endemic models compared with the pandemic model (0.81, 0.83, 0.74, respectively). A similar trend regarding changes from pre-test to post-test probabilities in higher categories of predicted risk (23%, 40%, 16%) was observed. 2020–2021 had the lowest discrimination performance (0.71) and uninformative post-test probabilities (

COVID-19 pandemic health data contributed to significant ML drift. Although ML approaches allow for quick re-training to mitigate drift, health regulators should approach ML prediction with caution when using pandemic-times data.

Insomnia disorder imposes a significant burden on children and adolescents; however, treatment options are limited. This paper describes the first controlled study to investigate the efficacy and safety of daridorexant, a dual orexin receptor antagonist, in children and adolescents with or without comorbid neurodevelopmental disorders, allowing its evaluation in a broad paediatric population.

This multicentre, double-blind, randomised, placebo-controlled, parallel-group, dose-finding Phase 2 trial includes male and female participants aged ≥10 to

This study has been approved by the respective health authorities and institutional review boards/independent ethics committees for each participating site and country and is conducted in accordance with the Declaration of Helsinki. Ethics approval has been obtained for each participating country/site. Regardless of the outcomes, the results will be published in an international peer-reviewed scientific journal.

NCT05423717.

Hand-arm Bimanual Intensive Therapy Including Lower Extremities (HABIT-ILE) is an intensive rehabilitation programme for children with cerebral palsy (CP) delivered in a day camp setting recognised to promote the acquisition of specific functional abilities and independence. Currently, during HABIT-ILE camps, families are minimally involved in their child’s motor learning processes. This explains the challenges reported by both families and therapists, including difficulties in reinforcing skills at home, limited transfer to other functional goals and a lack of confidence in parents’ adaptive competence (self-determination and empowerment). Increasing family involvement in intensive motor rehabilitation programmes and the child’s developmental process by reinforcing skills at home could help reduce the parental impact of the child’s disability, enhance family satisfaction and strengthen their resources to support their child’s daily learning during and after the camp.

To address this, we developed the PARTNER programme, which combines HABIT-ILE with a structured home component focused on parent coaching.

We designed a non-inferiority, mixed-methods, multicentre randomised controlled trial to compare the efficacy at 3 months of the PARTNER programme (35 hours HABIT-ILE+15 hours home programme) with the standard HABIT-ILE programme (50 hours) on the bimanual performance (Assisting Hand Assessment) of children with unilateral CP aged 3–5 years. The secondary aims are to compare the 3-month efficacy of the programmes on occupational performance, functional skills and upper limb activity levels, as well as families’ resources, the parent–child relationship, the quantity and quality of resources available in the home to stimulate the child’s motor development, and parental perceptions of their child’s disability and their child’s abilities (qualitative study). The tertiary aim is to conduct a cost-effectiveness analysis of care consumption in each group up to 6 months after the end of the programmes.

Target recruitment is 66 children (33 in each group) from 3 centres in France. Outcomes will be evaluated before the interventions, immediately after, at 3 months and up to 6 months for the cost-effectiveness analysis. Families in the PARTNER group will receive specific coaching and extensive support to perform the home programme. The coaching will focus on enhancing their resources.

The study protocol has been reviewed, and ethics approval obtained from the Protection of Persons Committee (PPC) (PPC number: 2024-A01051-46). The results from this study will be actively disseminated through manuscript publications and conference presentations.

NCT06963151.

Primary care nurses (PCNs) are the second largest workforce in primary care and play a critical role in facilitating access to coordinated care and reducing health disparities. There is renewed interest in team-based primary care as a solution for health workforce challenges. Some team models enable PCNs (ie, nurse practitioners, registered nurses, licensed/registered practical nurses) to leverage one another’s expertise to work to optimal scope; the extent to which this happens depends on multiple context-dependent factors. We will conduct an umbrella review to synthesise and compare international knowledge syntheses focused on scope of practice enactment (ie., roles and activities) of PCNs in primary care.

We will conduct the umbrella review according to the Joanna Briggs Institute methodology, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocol (PRISMA-P) guidelines, and using the Nursing Care Organization Framework as guidance. We will search a wide range of scientific electronic databases and grey literature sources, and consider articles published in English and French by the Organization for Economic Cooperation and Development and designated key partner countries for inclusion, with no publication date limits. Two independent reviewers will screen titles, abstracts and full-text articles, and any disagreements will be resolved through discussion or by a third reviewer. We will use the Risk of Bias Assessment Tool for Systematic Reviews to assess the quality and risk of bias in the included systematic and scoping reviews.

Results will be presented in a PRISMA Scoping Review flow diagram. We will synthesise data from included studies in a detailed literature review table and develop visual aids to communicate the shared and unique roles and activities of PCN scope of practice. We will disseminate the results of the review through peer-reviewed publications and conferences related to this field. Ethics approval is not required.