Predictive Model for Early Prognosis After Total Knee Arthroplasty Based on Multidimensional Indicators

Objective To comprehensively evaluate the significance of multidimensional perioperative indicators for the prognosis following total knee arthroplasty (TKA), construct and validate a nomogram model for predicting optimal early knee joint function recovery at 2 weeks post-TKA, and provide evidence-based support for clinical precise intervention, thereby accelerating patients' rehabilitation process and improving the quality of prognosis. Methods A total of 297 patients with end-stage knee osteoarthritis (KOA) who underwent TKA were retrospectively enrolled and divided into a training set (n = 247) and a validation set (n = 50) at a ratio of 5:1. Multidimensional data, including demographic characteristics, surgical indicators, imaging parameters, hematological results, and scale scores, were systematically collected preoperatively and perioperatively. The minimum clinically important difference (MCID) of the Knee Society Score (KSS) functional score was calculated using the anchor-based method and defined as the primary outcome variable. Variables were initially screened via Bootstrap-LASSO regression, and a nomogram model was constructed by integrating multivariate Logistic regression to identify independent risk factors affecting prognosis. The model performance was evaluated in terms of discrimination, calibration, and clinical utility through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA), respectively. Results The MCID of the KSS functional score at 2 weeks post-TKA was determined to be 8.2. Multivariate Logistic regression analysis revealed that preoperative KSS functional score (OR = 0.944, 95% CI: 0.922–0.965, P < 0.001), SF-36 role-emotional score (OR = 0.989, 95% CI: 0.982–0.996, P = 0.003), and duration of pain (OR = 0.426, 95% CI: 0.209–0.847, P = 0.017) were protective factors; whereas preoperative uric acid level (OR = 1.005, 95% CI: 1.001–1.010, P = 0.031) and tourniquet application time (OR = 2.068, 95% CI: 1.042–4.206, P = 0.041) were independent risk factors. The area under the ROC curve (AUC) of the nomogram model was 0.81 (95% CI: 0.75–0.87) in the training set and 0.75 (95% CI: 0.55–0.95) in the validation set. The Hosmer-Lemeshow goodness-of-fit test yielded P-values > 0.05 in both sets, with Brier scores ≤ 0.171. The decision curve analysis demonstrated that the net benefit of the nomogram was superior to the extreme strategies of "Treat all" or "Treat none". Conclusion The nomogram constructed based on 5 independent factors effectively predicts the early rehabilitation outcome after TKA with favorable performance. It facilitates the early identification of high-risk patients and the implementation of targeted interventions in clinical practice, providing a valuable reference for the development of individualized perioperative rehabilitation strategies.