Search

Abstract Purpose To analyze the key factors influencing the psychological resilience of intensive care unit (ICU) nurses during the COVID-19 pandemic and put forward suggestions promoting resilience based on key improvement factors and clinical experience. Methods Data were collected from 35 ICU nurses in a hospital in Zhejiang Province, China, through a questionnaire survey conducted between January and February 2023. The Decision-Making Trial and Evaluation Laboratory (DEMATEL) method was then used to construct and visualize the relationship structure between the factors. The DEMATEL-based Analytical Network Process (DANP) was applied to determine the influential weights of all factors. Finally, the key improvement factors were identified using importance-performance analysis (IPA). Results Based on the cause-effect impact network diagram (CEIND), it was concluded that (C 11), (C 22), and (C 32) are the key factors that promote the improvement of psychological resilience among ICU nurses. Additionally, these factors were the key factors that influence psychological resilience. The confidence levels of these results and the gap were 99.6% and 0.4%, respectively, which exceed the threshold value of 95%, indicating good stability. Finally, for the case hospitals, (C 13) was identified as the key improvement factor. Conclusions Hospital administrators should support ICU nurses in enhancing their psychological resilience during major epidemics by: (i) Providing training on comprehensive protective measures and nursing skills; (ii) Effectively managing the human resources of nurses in the hospital to reduce their workload; (iii) Increasing social and organizational support for nurses to alleviate anxiety caused by large-scale public health events and improve their psychological resilience.

Abstract Purpose To identify the key risk factors for venous thromboembolism (VTE) in urological inpatients based on the Caprini scale using an interpretable machine learning method. Methods VTE risk data of urological inpatients were obtained based on the Caprini scale in the case hospital. Based on the data, the Boruta method was used to further select the key variables from the 37 variables in the Caprini scale. Furthermore, decision rules corresponding to each risk level were generated using the rough set (RS) method. Finally, random forest (RF), support vector machine (SVM), and backpropagation artificial neural network (BPANN) were used to verify the data accuracy and were compared with the RS method. Results Following the screening, the key risk factors for VTE in urology were “(C 1) Age,” “(C 2) Minor Surgery planned,” “(C 3) Obesity (BMI > 25),” “(C 8) Varicose veins,” “(C 9) Sepsis ( 45 min),” “(C 19) Laparoscopic surgery (> 45 min),” “(C 20) Patient confined to bed (> 72 h),” “(C18) Malignancy (present or previous),” “(C 23) Central venous access,” “(C 31) History of DVT/PE,” “(C 32) Other congenital or acquired thrombophilia,” and “(C 34) Stroke ( 45 minutes),” and “(C 21) Malignancy (present or previous)” were the main factors influencing mid- and high-risk levels, and some suggestions on VTE prevention were indicated based on these three factors. The average accuracies of the RS, RF, SVM, and BPANN models were 79.5%, 87.9%, 92.6%, and 97.2%, respectively. In addition, BPANN had the highest accuracy, recall, F1-score, and precision. Conclusions The RS model achieved poorer accuracy than the other three common machine learning models. However, the RS model provides strong interpretability and allows for the identification of high-risk factors and decision rules influencing high-risk assessments of VTE in urology. This transparency is very important for clinicians in the risk assessment process.