Objective To investigate the effects of rivaroxaban anticoagulant therapy on lower deep venous thrombosis (DVT) after artificial knee arthroplasty. Methods One hundred and forty-four patients who received artificial knee replacement in the Zhujiang Hospital of Southern Medical University from June 2020 to June 2022 were retrospectively analyzed. All the patients received rivaroxaban anticoagulant treatment after surgery. Among them, the patients who started anticoagulant therapy at platelets > 100×10⁹/L were included in the observation group (n=76), and the patients who started anticoagulant at platelets > 300×10⁹/L were included in the control group (n=68). The propensity score matching was used to adjust the balance, and each group included 56 patients. The changes of coagulation markers [D-dimer and plasma viscosity (PV)] before and after operation were compared between the two groups. The survival curve was drawn by Kaplan-Meier method to analyze the occurrence of DVT in the two groups within 30 days after operation. According to the presence or absence of lower limb DVT events after knee arthroplasty, the patients were divided into DVT group (n=36) and non-DVT group (n=76). Logistic regression model was used to analyze the independent correlation between platelet level before anticoagulant therapy and postoperative DVT. Multivariate logistic regression analysis was used to analyze the risk factors of DVT after knee arthroplasty. The nomogram was established by R software and verified 1000 times by Bootstrap method. The area under ROC curve (AUC) and calibration curve were used to evaluate the discrimination and accuracy. Results After matching, the baseline characteristics of the observation group and the control group were balanced (P>0.05). Univariate analysis showed that compared with non-DVT group, BMI and the proportion of bilateral knee arthroplasty, intraoperative blood loss ≥400 ml, general anesthesia, use of bone cement, and triacylglycerol ≥1.7 mmol/L, and the levels of D-dimer and platelet increased, prothrombin time (PT) shortened, and activated partial thromboplastin time (APTT) extended in the DVT group (P<0.05). After adjusting the confounding factors of age, sex, BMI, triglyceride, D-dimer, PT and APTT, the platelet level before anticoagulant therapy was still an independent risk factor for postoperative DVT (OR=3.858, 95%CI 1.849-6.054), and there was a significant difference in platelet trend test from low to high quintile (P_trend<0.001). The results of multivariate logistic regression analysis showed that BMI ≥25 kg/m², bilateral knee arthroplasty, general anesthesia, D-dimer ≥190 μg, platelet ≥300×10⁹/L were risk factors for DVT after knee arthroplasty (OR>1, P<0.05), while not using bone cement and PT ≥12 s were protective factors (OR<1, P<0.05). Before and after the verification of the nomogram, the AUC was 0.851(95%CI 0.773-0.912) and 0.813 (95%CI 0.736-0.894), and the average absolute error of the calibration curve was 0.015. Conclusion The application of rivaroxaban anticoagulation therapy can quickly improve the coagulation function of patients with platelet > 100×10⁹/L after artificial knee replacement surgery and reduce the incidence of DVT.