Abstract: Objective To investigate the influencing factors for anthracycline⁃induced cardiotoxicity (AIC) in patients with soft tissue sarcoma (STS), and to develop and validate a predictive model. Methods The methodology involved a retrospective analysis of  clinical data from STS patients who received anthracycline treatment at Xijing Hospital from January 2013 to December 2023. Key variables were identified using Lasso regression analysis. And predictive factors were determined through Logistic regression to construct a Nomogram prediction model. Internal validation was performed using the Bootstrap test with 1，000 resamples. The model's discrimination was assessed via the area under the curve (AUC) of receiver operating characteristic, calibration was evaluated using calibration curves, and clinical applicability was assessed through decision curve analysis. Results A total of 153 patients was included, among whom 16 (10.5%) experienced AIC. Based on the results of Lasso⁃Logistic regression analysis, and considering sample size and statistical significance, age (OR=5.96, 95%CI:1.55-22.93), triglyceride (OR=3.02, 95%CI:1.47-6.12), and combined dexrazoxane (OR=0.10, 95%CI:0.02-0.46) were identified as significant predictive variables. The Nomogram prediction model developed using these variables demonstrated an AUC of 0.859, indicating robust discrimination, calibration, and clinical applicability. Conclusions This study developed a Nomogram prediction model for AIC in STS patients based on the variables of age, triglyceride, and combined dexrazoxane. The model exhibits strong  predictive performance, providing a potential tool for identifying the risk of AIC in STS patients.

Key words: Soft tissue sarcoma, Anthracyclines, Cardiotoxicity, Influencing factor, Prediction model