A three-domain perspective on teacher-student relationship and bullying victimization in Chinese schools: a serial mediation.

Elective unilateral lower extremity joint replacement surgery, as an important means of treating advanced joint diseases, has been widely applied in clinical practice, significantly improving the joint function and quality of life of patients (). However, the postoperative rehabilitation process of patients is complex and varies among individuals, and the level of discharge readiness is directly related to the postoperative recovery effect and the risk of readmission (). With the intensification of the aging population trend and the continuous increase in the number of patients undergoing elective lower extremity joint replacement surgery, how to effectively assess and enhance the discharge readiness level of patients has become an urgent issue to be addressed in the current clinical nursing and rehabilitation fields (, ). Current research mainly focuses on the impact of postoperative physiological indicators and clinical pathological factors on patient recovery, while the role of psychosocial factors in patients’ discharge readiness and rehabilitation has increasingly drawn attention. Numerous studies have revealed that patients’ psychological states, such as kinesiophobia, anxiety and depression, as well as non-clinical factors like social support systems and economic conditions, significantly affect the smoothness of postoperative recovery and patients’ self-management abilities (, ). Moreover, patients with lower socioeconomic status often face insufficient access to medical resources and weak family support, which frequently leads to inadequate discharge preparation and increases the risk of postoperative adverse events. These findings suggest that relying solely on traditional clinical indicators is insufficient to comprehensively reflect patients’ discharge readiness, and integrating psychosocial factors is of great significance for constructing a precise risk assessment system (, ). Although the above studies have provided a theoretical basis for understanding patients’ discharge readiness, there is still a lack of systematic integration of clinical and psychosocial multi-dimensional factors to establish a predictive model for poor discharge readiness in the specific population of patients undergoing lower extremity joint replacement surgery (). Most current risk assessment tools focus on a single dimension, making it difficult to capture the complex interactions among multiple factors, and lack the development and validation of models based on modern data analysis techniques such as machine learning (). Therefore, how to utilize multivariate statistics and machine learning methods to construct efficient, accurate, and clinically interpretable predictive models for discharge readiness risk has become a hot and difficult issue in clinical research (, ). To address the aforementioned deficiencies, this study adopted a retrospective observational cohort design to systematically collect clinical indicators, psychological status, and socio-economic background information of patients undergoing elective unilateral lower extremity joint replacement surgery. By integrating Elastic Net, logistic regression, and XGBoost algorithms, variable selection and model construction were carried out. This approach can effectively handle multicollinearity, variable selection, and nonlinear relationships, thereby enhancing the predictive performance and generalization ability of the model. The aim of this study is to develop a risk prediction tool for poor discharge readiness based on the combination of clinical and psychosocial factors, providing a scientific basis for the early identification of high-risk patients and the formulation of personalized intervention plans in clinical practice (, ).