Background and objective: Delirium is the most common neuropsychological complication among older adults admitted to the intensive care unit (ICU) and is often associated with a poor prognosis. This study aimed to construct and validate an interpretable machine learning (ML) for early delirium prediction in older ICU patients.Methods: This was a retrospective observational cohort study and patient data were extracted from the Medical Information Mart for Intensive Care-IV database. Feature variables associated with delirium, including predisposing factors, disease-related factors, and iatrogenic and environmental factors, were selected using least absolute shrinkage and selection operator regression, and prediction models were built using logistic regression, decision trees, support vector machines, extreme gradient boosting (XGBoost), k-nearest neighbors and naive Bayes methods. Multiple metrics were used for evaluation of performance of the models, including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, recall, F1 score, calibration plot, and decision curve analysis. SHapley Additive exPlanations (SHAP) were used to improve the interpretability of the final model.Results: Nine thousand seven hundred forty-eight adults aged 65 years or older were included for analysis. Twenty-six features were selected to construct ML prediction models. Among the models compared, the XGBoost model demonstrated the best performance including the highest AUC (0.836), accuracy (0.765), sensitivity (0.713), recall (0.713), and F1 score (0.725) in the training set. It also exhibited excellent discrimination with AUC of 0.810, good calibration, and had the highest net benefit in the validation cohort. The SHAP summary analysis showed that Glasgow Coma Scale, mechanical ventilation, and sedation were the top three risk features for outcome prediction. The SHAP dependency plot and SHAP force analysis interpreted the model at both the factor level and individual level, respectively.Conclusion: ML is a reliable tool for predicting the risk of critical delirium in elderly patients. By combining XGBoost and SHAP, it can provide clear explanations for personalized risk prediction and more intuitive understanding of the effect of key features in the model. The establishment of such a model would facilitate the early risk assessment and prompt intervention for delirium.

Background: Delirium is a common and serious complication among patients in the Intensive Care Unit (ICU). Nurses have an essential role in dealing with delirium in critical illness. However, understanding of ICU nurses’ knowledge, attitude, and practice (KAP)on delirium is limited, and large-scale survey lacking.Objectives: To explore the status and related factors of KAP of delirium among critical care nurses in China.Methods: From February to May 2019, a cross-sectional survey was conducted among 3,199 intensive care nurses from 160 hospitals across China using a convenience sampling approach. An online questionnaire was designed and distributed to evaluate the KAP of nurses. Univariate and multivariate linear regression analyses were used to assess the factors that influenced ICU nurses’ KAP.Results: A total of 3,199 valid questionnaires were collected. Overall, the scores of ICU nurses’ knowledge, attitude, and practice regarding delirium assessment were 38.00 (33.00, 44.00), 23.00 (19.00, 26.00), and 16.00 (12.00, 19.00), respectively. Among the respondents, the proportions of individuals providing positive responses regarding their knowledge, attitude, and practice scores were 48.59%, 58.27%, and 40.52%, respectively. The attitude scores of the nurses were significantly related to knowledge scores (p < 0.001). Moreover, the scores for nurses’ practice show a significant correlation with their knowledge scores (p < 0.001) and attitudes scores (p < 0.001). Multivariate linear regression analysis showed a higher level of education (P = 0.037), surgical ICU (P = 0.02), private hospital (P < 0.001), clinical position (P = 0.007), shorter working hours (P < 0.001), primary professional title (P < 0.001), and previous experience in delirium nursing (P < 0.001)and training (P < 0.001)were related to higher practice scores.Conclusion: The knowledge of delirium among ICU nurses is at a moderate level. While these nurses exhibit a positive attitude toward this issue, their actual practices tend to reflect a relatively negative approach. Managers and nursing researchers should develop and offer standardized training for critical care nurses to improve their KAP toward delirium in critically ill patients.

Background: Work withdrawal behavior adversely affects both individual nurses' career development and team performance. However, the current status of work withdrawal behavior among nurses in China and its relationship with perceived stress and work-life balance has received limited attention. Objective: This study aims to examine the current status of work withdrawal behavior among nurses in Chinese hospitals and to analyze its associations with perceived stress and work-life balance. Methods: A cross-sectional survey was conducted from February to March 2025 using convenience sampling to recruit 2,707 nurses from 203 primary, secondary, and tertiary hospitals across 27 provinces in China. Validated scales were used to assess nurses' work withdrawal behavior, perceived stress, and work-life balance. Univariate analysis and multiple linear regression analysis were conducted to examine factors associated with work withdrawal behavior. Results: Among 2,594 valid questionnaires (response rate: 95.8%), the mean Work Withdrawal Behavior Scale score was 19.14 ( SD = 6.90). Multiple linear regression revealed that male gender, older age, working in intensive care units or emergency departments, lower monthly income, longer overtime hours, higher perceived stress, and poorer work-life balance were significantly associated with increased work withdrawal behaviors (all p < 0.05). Among these, perceived stress (β = 0.291) and work-life balance (β = −0.201) were the strongest predictors. Conclusion: Work withdrawal behaviors are observable among Chinese nurses, with psychological withdrawal aspects showing relatively higher manifestation. Among the range of associated factors, increased perceived stress and poorer work-life balance were the most salient. Hospitals should therefore implement adequate organizational support, regular psychological screenings, and counseling services to alleviate stress and improve work-life balance, thereby reducing work withdrawal behaviors.

Background: The Braden Skin Score (BSS), a tool for assessing pressure ulcers, is increasingly recognized for its prognostic value in various disorders. However, its link to critical delirium in surgical patients remains understudied. This study aimed to explore the association between BSS upon admission and the risk of delirium in SICU patients.Methods: This retrospective observational cohort study used data from the Medical Information Mart for Intensive Care (MIMIC)-IV database. The primary outcome was incidence of delirium. Feature importance of BSS was initially assessed using a machine learning algorithm, while restricted cubic spline (RCS) models and multivariable logistic analysis evaluated the relationship between BSS and delirium. Additionally, Kaplan–Meier analysis and mediation analysis were conducted to explore interactions among BSS, delirium, and short-term mortality.Results: A total of 4,899 patients were included in the study, among whom 1,491 were diagnosed with delirium. The Boruta algorithm identified BSS as a significant predictor of delirium occurrence. RCS models demonstrated a non-linear positive relationship between BSS and delirium. Based on RCS curves, the optimal threshold for BSS was established at 16, thereby categorizing participants into two groups: those with BSS < 16 and those with BSS ≥ 16. Multivariable logistic regression analysis revealed that lower BSS was positively correlated with an increased risk of delirium. These findings exhibited robust consistency across subgroup analyses and sensitivity analyses. Furthermore, patients in lower BSS groups had a higher 90-day mortality, with delirium mediating an indirect effect on this outcome.Conclusion: The low BSS was independently associated with an increased risk of delirium in critically ill surgical patients. Patients exhibiting a BSS below 16 demonstrated heightened susceptibility to the onset of delirium, thereby necessitating vigilant monitoring and timely intervention. Larger prospective studies are needed to confirm these findings.

Background: The working environment of ICU nurses, which is high-intensity and fast-paced, contributes to elevated levels of perceived stress, which may consequently lead to work withdrawal behavior. Although work-life balance is regarded as a critical resource in coping with perceived stress, its mediating mechanism between perceived stress and work withdrawal behavior has not yet been fully elucidated. Objective: This study aims to examine the relationships between perceived stress, work-life balance, and work withdrawal behavior among ICU nurses in China. Methods: This cross-sectional study was conducted between September and October 2025. A total of 1,279 ICU nurses were enrolled from 58 hospitals across 16 Chinese provinces using convenience and snowball sampling. Data were collected employing validated scales: the Work-Life Balance Scale (WLBS), the Perceived Stress Scale (PSS), and the Work Withdrawal Behavior Scale (WWBS). Structural equation modeling (SEM) was applied to examine the relationships among variables, and the bootstrap method was utilized to test the mediating effects. Results: The questionnaire response rate was 91.35% (1,279/1400). Path analysis confirmed that perceived stress negatively influenced work-life balance ( β = −0.234, p < 0.001) and positively influenced work withdrawal behavior ( β = 0.207, p < 0.001). Work-life balance also showed a significant negative effect on withdrawal behavior ( β = −0.439, p < 0.001). The mediation analysis indicated that work-life balance played a significant mediating role between perceived stress and work withdrawal behavior, with the indirect effect accounting for 33.23% of the total effect. Conclusion: The results indicate a significant association between perceived stress and work withdrawal behavior, with work-life balance playing a crucial mediating role in this relationship. These findings highlight the potential of work-life balance-focused interventions to alleviate stress, reduce withdrawal, and improve occupational health outcomes for ICU nurses.