ABSTRACT
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.
ABSTRACT
Background: Mental health literacy (MHL) is crucial to address issues related to mental illness. Nurses' MHL is even more important because they are expected to deal with both the physical and psychological consequences of mental disorders. Objective: This study investigated the level, discrepancy, and characteristics of MHL among Chinese nurses from both public general and psychiatric hospitals; identified influential factors; and explored the relationship between MHL and mental health status. Methods: Using a stratified cluster sampling method to select participants, a cross-sectional survey was conducted to describe the MHL of 777 nurses from 13 general and 12 psychiatric hospitals using the Chinese version of the Mental Health Literacy Scale, Patient Health Questionnaire-2, Generalized Anxiety Disorder-2, and a demographic questionnaire. A multiple regression analysis was used to determine the factors influencing MHL among the nurses recruited. Results: The participants' total score on the Chinese version of the Mental Health Literacy Scale was 93.25 (SD = 10.52). Multiple regression analysis revealed that nurses who worked in psychiatric or higher-level hospitals, with higher professional titles or higher education had higher levels of overall MHL and core MHL, while those working in general hospitals, with shorter work duration, or who were unmarried had higher social acceptance of patients. Nurses' MHL was closely correlated with their mental health status. Conclusion: The overall and core MHL of Chinese nurses were at a moderate level, with social acceptance remaining at a relatively low level. There is an urgent need for MHL promotion programs to improve the MHL of clinical nurses. The focus must be given to overall MHL, especially core MHL, for non-psychiatric nurses to enhance their competence in mental health promotion and identification; more emphasis should be placed on the social acceptance of patients with mental illnesses for psychiatric nurses to improve their provision of professional services. Better MHL would be a formula for improving nurses' own mental health and their mental health service competence.
