Machine learning and SHAP interpretation to identify high-level compassion fatigue among operating room nurses: a multicenter cross-sectional study
AI Summary
High prevalence: 31.8% severe compassion fatigue among 1024 OR nurses; secondary traumatic stress most prevalent symptom (95.4%).
Random forest model achieved highest test AUC 0.851; XGBoost next best AUC 0.824, outperforming decision tree, logistic regression, and SVM.
SHAP analyses identified depression, anxiety, mental health training, sleep quality, and length of service as top contributors, enhancing model interpretability for targeted interventions.
BMC Nurs. 2026 May 8. doi: 10.1186/s12912-026-04728-3. Online ahead of print.
ABSTRACT
BACKGROUND: Operating room nurses (ORNs) are at high risk for compassion fatigue (CF), which significantly impairs individuals’ well-being, undermines the stability of the nursing workforce, and jeopardizes patients’ safety. The study aimed to analyze the prevalence and symptom characteristics of CF among ORNs, construct and compare predictive models using machine learning, and determine the relative contribution of distinct features to the models.
METHODS: This is a multi-center cross-sectional study. The questionnaires used in the study included a sociodemographic questionnaire, the Professional Quality of Life Scale (ProQoL), the Patient Health Questionnaire-9 (PHQ-9), the Generalized Anxiety Disorder 7-item Scale (GAD-7), and the Pittsburgh Sleep Quality Index (PSQI). LASSO regression was used to select critical variables, and predictive models such as decision tree, logistic regression, random forest, SVM, and XGBoost were constructed and compared. SHapley Additive exPlanation (SHAP) were drawn to show the contribution of each feature to the models. SPSS version 26.0 and R software version 4.4.0 were used for statistical analyses.
RESULTS: In this study, a total of 1024 ORNs from 20 cities across China were recruited. According to ProQoL, 326 (31.8%) reported severe CF, 311 (30.4%) moderate CF, and the remaining 387 (37.8%) no or mild CF. Among the three dimensions, the incidence of secondary traumatic stress was most common (95.4%), followed by low compassion satisfaction (61.3%) and burnout (35.0%). In five machine learning-based predictive models, the RF model stood out with the highest AUC at 0.851 (95%CI: 0.795-0.907) in testing set. Following closely, the XGBoost model showed favorable efficacy with the AUC at 0.824 (95%CI: 0.769-0.879) in testing set, outperforming the remaining algorithms. The results of the two SHAP plots (RF and XGBoost) were consistent: depression, anxiety, self-mental health training, sleep quality, and length of service emerged as the five most significant contributors to the models.
CONCLUSION: This study identified severe CF among ORNs, and the most serious symptom was secondary traumatic stress. The RF model exhibited the best performance in identifying high-level CF among ORNs, and SHAP improved the interpretability of the model. The findings of this study could help medical managers and researchers better understand CF and provide timely interventions for ORNs.
Schizophr Bull. 2026 Apr 10;52(3):sbag064. doi: 10.1093/schbul/sbag064.ABSTRACTBACKGROUND AND HYPOTHESIS: Individuals with schizophrenia report that time can feel discontinuous. Difficulties in benefiting from the passage of...
Schizophr Bull. 2026 Apr 10;52(3):sbag068. doi: 10.1093/schbul/sbag068.ABSTRACTSTUDY DESIGN: In this secondary analysis of a randomized controlled trial, individuals aged 18-65 with a psychotic disorder and...
Schizophr Bull. 2026 Apr 10;52(3):sbag048. doi: 10.1093/schbul/sbag048.ABSTRACTBACKGROUND: According to predictive processing models, hallucinations can arise from over-weighting of prior expectations relative to sensory input. Individuals...
Schizophr Bull. 2026 Apr 10;52(3):sbag062. doi: 10.1093/schbul/sbag062.ABSTRACTBACKGROUND AND HYPOTHESIS: Persistent negative symptoms (PNS) often emerge early in the course of schizophrenia spectrum disorders, significantly impair...
Schizophr Bull. 2026 Apr 10;52(3):sbag067. doi: 10.1093/schbul/sbag067.ABSTRACTBACKGROUND: People with severe mental illness (SMI) are at an increased risk of infection mortality compared to the general...
Schizophr Bull. 2026 Apr 10;52(3):sbag049. doi: 10.1093/schbul/sbag049.ABSTRACTBACKGROUND AND HYPOTHESIS: The early phase of psychosis is critical for interventions to modify long-term outcomes. It is unclear...
