Conectar
To estimate the longitudinal predictive relationships between anxiety, depression and post-traumatic stress disorder symptoms in nurses exposed to horizontal violence and identify the most influential symptom using cross-lagged panel network analysis.
A longitudinal cross-lagged panel network analysis study.
Data were obtained from a short longitudinal survey conducted at four tertiary hospitals in Shandong Province, China. Two follow-up surveys spaced 7 weeks apart were conducted on 298 nurses with horizontal violence exposure using the General Information Scale, the Negative Acts Questionnaire, the seven-item Generalised Anxiety Disorder scale, the nine-item Patient Health Questionnaire and the four-item SPAN. Unique longitudinal relationships between symptoms were estimated using cross-lagged panel network analysis.
The results showed that the out-expected influence of A2 (Uncontrollable worry) and P2 (Physiological arousal) was highest and they were the most predictive symptoms in the network. The bridge out-expected influence of A2 (Uncontrollable worry) was also highest and it was the key bridge symptom within the network.
A2 (Uncontrollable worry) and P2 (Physiological arousal) were the top risk factors contributing to mental health deterioration in nurses with horizontal violence exposure.
This study precisely identified the predictive mechanisms and core symptoms among psychological symptoms in nurses exposed to horizontal violence, which is expected to play a significant role in improving the mental health of this group. The results showed that “Uncontrollable worry” and “Physiological arousal” were the core symptoms with the strongest predictive effects on other symptoms. Additionally, “Uncontrollable worry” was also the bridge symptom driving the mutual transmission and development of anxiety, depression and post-traumatic stress disorder. Nursing managers should prioritise “Uncontrollable worry” and “Physiological arousal” as intervention targets, optimising mental health interventions to effectively enhance the psychological well-being of nurses exposed to horizontal violence.
No patient or public contribution.
To develop and validate a machine learning-based risk prediction model for delirium in older inpatients.
A prospective cohort study.
A prospective cohort study was conducted. Eighteen clinical features were prospectively collected from electronic medical records during hospitalisation to inform the model. Four machine learning algorithms were employed to develop and validate risk prediction models. The performance of all models in the training and test sets was evaluated using a combination of the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, Brier score, and other metrics before selecting the best model for SHAP interpretation.
A total of 973 older inpatient data were utilised for model construction and validation. The AUC of four machine learning models in the training and test sets ranged from 0.869 to 0.992; the accuracy ranged from 0.931 to 0.962; and the sensitivity ranged from 0.564 to 0.997. Compared to other models, the Random Forest model exhibited the best overall performance with an AUC of 0.908 (95% CI, 0.848, 0.968), an accuracy of 0.935, a sensitivity of 0.992, and a Brier score of 0.053.
The machine learning model we developed and validated for predicting delirium in older inpatients demonstrated excellent predictive performance. This model has the potential to assist healthcare professionals in early diagnosis and support informed clinical decision-making.
By identifying patients at risk of delirium early, healthcare professionals can implement preventive measures and timely interventions, potentially reducing the incidence and severity of delirium. The model's ability to support informed clinical decision-making can lead to more personalised and effective care strategies, ultimately benefiting both patients and healthcare providers.
This study was reported in accordance with the TRIPOD statement.
No patient or public contribution.
FreshRSS 