Conectar
To predict nurses' turnover intention using machine learning techniques and identify the most influential psychosocial, organisational and demographic predictors across three countries.
A cross-sectional, multinational survey design.
Data were collected from 1625 nurses in the United States, Türkiye and Malta between June and September 2023 via an online survey. Twenty variables were assessed, including job satisfaction, psychological safety, depression, presenteeism, person-group fit and work engagement. Turnover intention was transformed into a binary variable using unsupervised machine learning (k-means clustering). Six supervised algorithms—logistic regression, random forest, XGBoost, decision tree, support vector machine and artificial neural networks—were employed. Model performance was evaluated using accuracy, precision, recall, F1 score and Area Under the Curve (AUC). Feature importance was examined using logistic regression (coefficients), XGBoost (gain) and random forest (mean decrease accuracy).
Logistic regression achieved the best predictive performance (accuracy = 0.829, f1 = 0.851, AUC = 0.890) followed closely by support vector machine (polynomial kernel) (accuracy = 0.805, f1 0.830, AUC = 0.864) and random forest (accuracy = 0.791, f1 = 0.820, AUC = 0.859). In the feature importance analysis, job satisfaction consistently emerged as the most influential predictor across all models. Other key predictors identified in the logistic regression model included country (USA), work experience (6–10 years), depression and psychological safety. XGBoost and random forest additionally emphasised the roles of work engagement, group-level authenticity and person–group fit. Job-stress-related presenteeism was uniquely significant in XGBoost, while depression ranked among the top predictors in both logistic regression and random forest models.
Machine learning can effectively predict turnover intention using multidimensional predictors. This methodology can support data-driven decision-making in clinical retention strategies.
This study provides a data-driven framework to identify nurses at risk of turnover. By integrating machine learning into workforce planning, healthcare leaders can develop targeted, evidence-based strategies to enhance retention and improve organisational stability.
This study adhered to STROBE reporting guideline.
This study did not include patient or public involvement in its design, conduct or reporting.
To determine the association between patient characteristics, techniques, and technologies with first-time peripheral intravenous catheter insertion in paediatric acute care.
Single-centre, prospective cohort study.
Data on patient, provider, and peripheral intravenous catheter insertion characteristics were collected at a large quaternary paediatric hospital in Queensland, Australia. Inpatients aged 0 to ≤ 18 years requiring a peripheral intravenous catheter or who had one inserted in the last 24 h, were eligible. Proportionate stratified random sampling was used. Generalised linear regression with modified Poisson regression assessed associations between patient variables (e.g., age) and first-time insertion success, along with technique (e.g., inserting clinician) and technology (e.g., ultrasound) variables. Models were adjusted for confounding variables identified through direct acyclic graphs.
199 children required 250 peripheral intravenous catheters (July 2022–September 2023). In the adjusted model, each year of age increase and every 5-kg increase in weight were associated with higher first-time insertion success. Children with a history of prematurity had an increased risk of first-time insertion failure. Vascular access specialists were more likely to succeed on the first attempt, as was ultrasound-guidance when adjusted for difficult intravenous access risk.
We identified techniques (expert clinicians) and technologies (ultrasound guidance) that improve first-time insertion success in paediatric patients.
A multi-faceted approach combining technique (clinician), technology (ultrasound guidance), and standardised policy can improve first-time peripheral intravenous catheter insertion. These strategies minimise patient discomfort, trauma, and emotional distress, enhancing the overall healthcare experience for children and their families.
This study emphasises the need to standardise healthcare policies and training, incorporating clinician expertise and ultrasound guidance to improve first-time insertion success, particularly for high-risk patients.
The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE).
No Patient or Public Contribution.
Australia New Zealand Clinical Trials Registry, ACTRN12622000034730
To address the gap in existing postpartum care literature by gaining an in-depth understanding of Australian child and family health nurses' experiences of providing postpartum contraceptive care.
A qualitative exploratory study design, using semi-structured interviews.
Convenience and snowballing sampling methods were employed to recruit child and family health nurses currently practising in Australia. Semi-structured interviews were conducted with 15 nurses in July 2023, and data were analysed using reflexive thematic analysis as outlined by Braun and Clarke. The consolidated criteria for Reporting Qualitative research checklist were used to support the research process.
Despite their frequent contact with postpartum women and acknowledging the importance of postpartum contraceptive care, most participants did not commonly discuss contraception or family planning with mothers and did not feel it was part of their role to do so. Participants cited role ambiguity, limited knowledge of postpartum contraception, lack of clinical practice guidance, time constraints, and competing priorities as contributing to inconsistencies in postpartum contraceptive care provision.
This study highlights critical gaps in the provision of postpartum contraceptive care by child and family health nurses in Australia and underscores the need for systemic changes to promote postpartum contraceptive care as a key component of routine maternal health services.
This study provides actionable evidence for improving the delivery of postpartum contraceptive care, ensuring women are provided with accurate information about their options, and supporting contraceptive uptake to reduce the incidence of short interpregnancy intervals.
Our findings provide practical guidance relevant for healthcare policy and practice, emphasising the need to enhance child and family health nurses training in reproductive health, develop clear clinical practice guidelines, and address systemic barriers such as time constraints to improve the provision of postpartum contraceptive care and support women's reproductive health needs.
Standards for reporting qualitative research (SRQR).
No patient or public contribution.
To assess the acceptability and perceived feasibility of integrating a co-designed nurse-led model of contraception and medication abortion care within rural and regional general practices.
Qualitative exploratory design utilising Sidani and Braden's indicators of acceptability and feasibility.
We conducted semi-structured interviews with 12 practice nurses, 8 general practitioners and 3 practice managers who currently or previously worked in rural, regional or remote general practice. Participants were recruited purposively through social media, partner organisation newsletters and snowballing. During the interview, participants were presented with an overview of the co-designed model of care and asked specific questions to gain feedback on its acceptability and perceived feasibility. Data were analysed in NVivo using template analysis and iterative categorisation. Findings were mapped according to Sidani and Braden's indicators of acceptability and feasibility.
Three overarching themes were identified: nurses are acceptable providers, factors influencing the feasibility of the model and factors supporting greater feasibility of the model. Participants found the nurse-led model acceptable, describing nurses as suitable and sometimes preferred providers of long-acting reversible contraception and abortion care in rural and regional settings. They also perceived the model as feasible, citing similarities to existing care processes such as infant immunisations and chronic disease management, contributing to its feasibility. However, contextual factors such as the need to adapt the model to each clinic and patient's unique needs, foster strong general practitioner–practice nurse professional relationships and ensure that staff have shared values and adequate training for contraception and abortion provision were described as critical for feasibility.
Overall, participants found the nurse-led model of care to be acceptable and feasible for implementation in rural and regional general practices. This perception carries important implications for policy and practice, highlighting the need for supportive policies to enhance the effectiveness of such models across Australian general practice.
Our findings emphasise the need for initiatives aimed at addressing inadequate funding for nurse-led care, improving documentation of this care, enhancing understanding among general practitioners and nurses regarding the scope of practice for practice nurses, and overcoming training barriers specific to rural areas. These measures are essential for enabling nurse-led models of contraception and medication abortion to function effectively in practice.
This paper is reported according to the consolidated criteria for reporting qualitative research (COREQ) guidelines.
Two consumer representatives contributed to the development of the co-design methodology as members of the ORIENT Intervention Advisory Group Governance Committee.
FreshRSS 