Cross-Combination Analyses of Random Forest Feature Selection and Decision Tree Model for Predicting Intraoperative Hypothermia in Total Joint Arthroplasty.

BACKGROUND: In total joint arthroplasty patients, intraoperative hypothermia (IOH) is associated with perioperative complications and an increased economic burden. Previous models have some limitations and mainly focus on regression modeling. Random forest (RF) algorithms and decision tree modeling are effective for eliminating irrelevant features and making predictions that aid in accelerating modeling and reducing application difficulty. METHODS: We conducted this prospective observational study using convenience sampling and collected data from 327 total joint arthroplasty patients in a tertiary hospital from March 4, 2023, to September 11, 2023. Of those, 229 patients were assigned to the training and 98 to the testing sets. The Chi-square, Mann-Whitney U, and t-tests were used for baseline analyses. The feature variables selection used the RF algorithms, and the decision tree model was trained on 299 examples and validated on 98. The sensitivity, specificity, recall, F1 score, and area under the curve were used to test the model's performance. RESULTS: The RF algorithms identified the preheating time, the volume of flushing fluids, the intraoperative infusion volume, the anesthesia time, the surgical time, and the core temperature after intubation as risk factors for IOH. The decision tree was grown to 5 levels with 9 terminal nodes. The overall incidence of IOH was 42.13%. The sensitivity, specificity, recall, F1 score, and area under the curve were 0.651, 0.907, 0.916, 0.761, and 0.810, respectively. The model indicated strong internal consistency and predictive ability. CONCLUSIONS: The preheating time, the volume of flushing fluids, the intraoperative infusion volume, the anesthesia time, the surgical time, and the core temperature after intubation could accurately predict IOH in total joint arthroplasty patients. By monitoring these factors, the clinical staff could achieve early detection and intervention of IOH in total joint arthroplasty patients.

Resilience, organizational support, and innovative behavior on nurses' work engagement: a moderated mediation analysis.

Objectives: To investigate the status of nurses' work engagement and the relationship among resilience, organizational support, and innovative behaviors. Methods: In this cross-sectional study, we investigated 496 nurses in Hunan, China, from July 2022 to December 2022. A descriptive statistical approach, Pearson's correlation analysis and Hayes' PROCESS Macro Models 4 and 14 were used to analyze the available data. Results: The level of work engagement among nurses was found to be moderate. Resilience positively predicted work engagement among nurses. Organizational support played a partially mediating role in the association between resilience and work engagement. Furthermore, innovative behavior played a moderating role in the association between adaptive resilience and work engagement. Conclusion: Based on the results, greater attention needs to be paid to nurses' work engagement. A high level of resilience, organizational support, and innovative behavior may increase work engagement among nurses. Nursing leaders can take measures to increase work engagement among nurses by improving nurses' resilience and organizational support, and cultivating innovative behavior.

Diabetes distress as mediators of loneliness and health promotion behaviour: a cross-sectional study.

OBJECTIVES: The purpose of this study was to explore whether diabetes distress mediated the relationship between loneliness and health promotion in older adults with diabetes. DESIGN: A cross-sectional study. SETTING: The study was conducted at three tertiary hospitals in Changsha, Hunan Province, China. PARTICIPANTS: The sample included 140 patients with diabetes (65 years and older, mean age 72.6 years, SD=4.6). METHODS: We employed path models to analyse data on diabetes distress, loneliness and health promotion behaviours. We collected diabetes distress, loneliness and health promotion behaviour with self-reported questionnaires including the Diabetes Distress Scale, the University of California at Los Angeles (UCLA) Loneliness Scale and the Elderly Health Promotion Scale from January 2022 to October 2022. Mediation analysis was performed by SPSS V.26.0's PROCESS macro. RESULT: The findings of this study indicated diabetes distress acted as a mediator between loneliness and health promotion behaviour. According to bootstrapping results, the total effect of loneliness on health promotion behaviour was significantly negative (ß=-0.312, p=0.006). Loneliness significantly and negatively correlated with diabetes distress (ß=-0.043, p<0.001), while diabetes distress significantly and negatively correlated with health promotion behaviours (ß=-2.724, p=0.008). Both the indirect effect and the direct effect of loneliness on health promotion behaviour were significant. CONCLUSION: Our study illustrated that loneliness was negatively associated with health promotion behaviours, and diabetes distress acted as a mediator in this relationship. It is suggested that healthcare providers should prioritise the identification and management of diabetes distress in older patients with diabetes who experience loneliness to improve health promotion behaviours and optimise disease management outcomes.