Conectar
Suicide is a significant public health issue worldwide. Many deaths by suicide occur in moments of crisis. Therefore, interventions which support individuals to manage moments of acute distress are needed. Safety Planning Interventions (SPI) are a group of brief interventions which aim to reduce imminent risk of suicide through the collaborative creation of a written set of coping strategies a person can use when suicidal ideation and/or urges occur. A number of studies, including systematic reviews, have supported the efficacy of SPIs in reducing suicidal behaviour, and sometimes ideation. However, there is notable heterogeneity in SPI effectiveness research. Our review aims to synthesise and critically examine the methodological characteristics of research on SPI effectiveness and to provide recommendations for the reporting of future research.
A predetermined search strategy will be used to search six electronic databases. Eligible studies will examine the effectiveness of SPIs for suicidality in adults aged 18+. There will be no restrictions to inclusion based on study design, study setting and participant characteristics. Two independent reviewers will perform study selection, data extraction and quality assessment. Disagreements between reviewers will be resolved by a third reviewer. Data gathered will include study design, participant characteristics, study setting, type of SPI delivered, theoretical approach used to guide research, outcomes measured and results reported. A narrative synthesis of the methodological characteristics of the included studies will be provided. Recommendations for the development and reporting of future research will be provided. Reporting of the review will be informed by Preferred Reporting Items for Systematic Review and Meta-Analysis guidance.
Ethical approval is not required as no original data will be collected. Findings will be disseminated through peer-reviewed publications and conference presentations.
This protocol has been registered on Prospero (registration ID CRD42025641027).
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.
FreshRSS 