Background: Appropriate allocation of nursing staff is key to ensuring efficient nursing in hospitals, and is significantly correlated with patient safety, nursing quality, and nurse job satisfaction. However, there are few studies on nursing workforce allocation in the isolation wards of COVID-19 designated hospitals globally. This study aims to better understand the nursing workforce allocation in the isolation wards of COVID-19 designated hospitals in China, and provide a theoretical basis for efficiently deploying first-line nurses in China and across the world in the future. Methods: An online survey was conducted among the head nurses (n = 229) and nurses (n = 1378) in the isolation wards of 117 hospitals (selected by stratified sampling), using a self-reported human resource allocation questionnaire. Results: The average bed-to-nurse ratios of different isolation wards were different (Z = 36.742, P = 0.000). The bed-to-nurse ratios of the ICU, suspected COVID-19 cases ward, and confirmed COVID-19 cases ward, were 1:1.88, 1:0.56, and 1:0.45, respectively. The nurse work hours per shift in different isolation wards were also different (Z = 8.468, P = 0.014), with the specific values of the ICU, suspected COVID-19 cases ward, and confirmed COVID-19 cases ward, being 5, 6, and 6 h, respectively. A correlation analysis showed that the average work hours per shift was proportional to the overtime work of nurses (r_s = 0.146), the proportion of nurse practitioners was proportional to the overall utilization rate of nursing human resources in the wards (r_s = 0.136), and the proportion of nurses with college degrees was proportional to teamwork (r_s = 0.142). The proportion of nurses above grade 10 was inversely proportional to teamwork and psychological problems (r_s = 0.135, r_s = 0.203). The results of multiple stepwise regression analyses showed that the work hours of nurses per shift was the main factor affecting nurse satisfaction and that the proportion of nurses and the work hours of nurses per shift were both independent factors affecting the length of stay (LOS) of patients. Conclusion: Hospitals in China have made good nursing workforce allocations during the COVID-19 pandemic, but there are certain shortcomings. Therefore, scientific and efficient nursing workforce allocation practice plans should be established to improve the ability of hospitals to deal with public health emergencies and are urgent problems that need to be addressed soon.

Background/Objectives: The accurate prediction of postprocedural mortality is critical for clinical decision-making; however, research on mortality risk models for patients undergoing mechanical thrombectomy remains limited. This study aimed to develop and validate machine learning models for predicting 90-day post-mechanical thrombectomy mortality. Methods: A retrospective-prospective cohort study involving 699 retrospective patients (January 2019–December 2022) and 274 prospective patients (January 2023–June 2024) from a single institution in Sichuan was conducted. The primary outcome was all-cause mortality within 90 days, ascertained via telephone follow-up. Predictors were identified using univariate analysis and LASSO regression. Eight predictive models were developed and evaluated using existing machine learning methods via 10-fold cross-validation. Model performance was assessed through discrimination, calibration, decision curve analysis, and interpretability via Shapley additive explanations. Results: The final dataset included 593 patients in the modeling set and 247 in the validation set. The 90-day mortality rates were 25.6% and 32.0%, respectively. Key predictors included age, hyperlipidemia, atrial fibrillation, pre-stroke statin use, antiplatelet/anticoagulant therapy within 48 h of onset, dysphagia, D-dimer levels, and activities of daily living scores. Logistic regression demonstrated superior performance in the modeling cohort (AUC = 0.87), whereas the multilayer perceptron model exhibited the greatest efficacy in the validation cohort (AUC = 0.77). Conclusions: Machine learning algorithms can accurately predict 90-day mortality among patients undergoing mechanical thrombectomy. The multilayer perceptron model demonstrated robust validation performance and offers a potential tool for personalized risk assessment and optimization of clinical decision-making.