Objective To explore, identify, and develop novel blood-based indicators using machine learning algorithms for accurate preoperative assessment and effective prediction of postoperative complication risks in patients with rheumatoid arthritis (RA) undergoing total knee arthroplasty (TKA). Methods A retrospective cohort study was conducted including RA patients who underwent unilateral TKA between January 2019 and December 2024. Inpatient and 30-day postoperative outpatient follow-up data were collected. Six machine learning algorithms, including decision tree, random forest, logistic regression, support vector machine, extreme gradient boosting, and light gradient boosting machine, were used to construct predictive models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), F1-score, accuracy, precision, and recall. SHapley Additive exPlanations (SHAP) values were employed to interpret and rank the importance of individual variables. Results According to the inclusion criteria, a total of 1 548 patients were enrolled. Ultimately, 18 preoperative indicators were identified as effective predictive features, and 8 postoperative complications were defined as prediction labels for inclusion in the study. Within 30 days after surgery, 453 patients (29.2%) developed one or more complications. Considering overall accuracy, precision, recall, and F1-score, the random forest model [AUC=0.930, 95%CI (0.910, 0.950)] and the extreme gradient boosting model [AUC=0.909, 95%CI (0.880, 0.938)] demonstrated the best predictive performance. SHAP analysis revealed that anti-cyclic citrullinated peptide antibody, C-reactive protein, rheumatoid factor, interleukin-6, body mass index, age, and smoking status made significant contributions to the overall prediction of postoperative complications. Conclusion Machine learning-based models enable accurate prediction of postoperative complication risks among RA patients undergoing TKA. Inflammatory and immune-related blood biomarkers, such as anti-cyclic citrullinated peptide antibody, C-reactive protein, and rheumatoid factor, interleukin-6, play key predictive roles, highlighting their potential value in perioperative risk stratification and individualized management.
Objective To investigate the effect of preoperative lower-limb muscle strength on perioperative blood loss, postoperative pain, and functional recovery in patients undergoing total knee arthroplasty (TKA).Methods A retrospective analysis was conducted on the clinical data of 380 patients who underwent TKA and met the selection criteria between February 2023 and December 2024. Based on the gender-specific median of standardized preoperative lower-limb extensor isokinetic muscle strength (IMS), the patients were divided into a low-extensor strength group and a high-extensor strength group, with 190 cases in each group. The following data of the two groups were collected and compared, including age, gender, body mass index, comorbidities, surgical side, length of hospital stay, Kellgren-Lawrence grade, perioperative parameters [including hematocrit (Hct) and hemoglobin (Hb) levels within 1 week preoperatively and 2-3 days postoperatively, with the calculation of Hct loss and Hb loss (the difference between the pre- and post-operative measurements), and whether intraoperative allogeneic blood transfusion was performed], preoperative knee flexion and extension IMS, 5-time sit-to-stand (5-STS) test within 2 weeks preoperatively, as well as visual analogue scale (VAS) score for pain and active range of motion (AROM) within 2 weeks preoperatively and 1 day postoperatively. Pearson correlation analysis was used to analyze the correlation between preoperative lower-limb extensor IMS and TBL. Through multiple linear regression analysis, the effect of IMS on TBL was further explored after adjusting for confounding factors such as age, body mass index, hypertension, diabetes mellitus, coronary atherosclerotic heart disease, and chronic obstructive pulmonary disease. Results There was no significant difference between the two groups in age, gender, body mass index, surgical side, Kellgren-Lawrence grade, comorbidities, length of hospital stay, preoperative Hct and Hb levels, intraoperative allogeneic blood transfusion rate, and changes in VAS scores (P>0.05). The high-extensor strength group was superior to the low-extensor strength group in preoperative VAS scores, AROM, 5-STS, as well as postoperative Hct and Hb loss, and the changes of AROM and TBL were less than those in the low-extensor strength group, with all differences being significant (P<0.05). Pearson correlation analysis showed a negative correlation between preoperative lower-limb extensor IMS and TBL (r=–0.460, P=0.043). Multiple linear regression analysis showed that after adjustment, a lower TBL was associated with a higher preoperative lower-limb extensor IMS. Specifically, for every 1 N·m increase in preoperative lower-limb extensor IMS, TBL decreased by 9.973 mL. TBL was not significantly affected by other factors such as age, body mass index, and comorbidities. Conclusion Higher preoperative lower-limb muscle strength is associated with reduced intraoperative blood loss during TKA and improved postoperative pain relief and functional recovery. These findings highlight the critical role of preoperative muscle strength management, providing scientific evidence for designing standardized postoperative rehabilitation protocols and offering guidance for optimizing surgical timing to maximize recovery outcomes.
