关键词: 恶性淋巴瘤, 贫血, LASSO分析, 危险因素, 列线图

Abstract: Objective To construct and validate a nomogram for predicting the risk of anemia in patients with malignant lymphoma. Methods A total of 132 patients with malignant lymphoma who were admitted to our hospital for diagnosis and treatment from January 2016 to July 2021 were enrolled. LASSO analysis and Logistic regression analysis were used to screen independent risk factors,and R（R3.5.3） software to establish a nomogram model for predicting the risk of anemia in patients with malignant lymphoma. Results 46（34.85%）patients developed anemia. The LASSO analysis and Logistic regression analysis showed that age ≥60 years,gender,radiotherapy,serum albumin concentration <35 g/L, smoking and drinking were independent risk factors （P<0.05）. Accordingly,anomogram model was established based on these 6 independent predictors. The C-index was 0.862 （95%CI：0.829~0.895）,and the calibration curve was basically consistent with the ideal curve. The AUC was 0.845（95%CI：0.819~0.871）,and the decision curve showed that when the threshold probability was in the range of 3% to 100%,and there was a higher net benefit value. Conclusion The nomogram presents accurate and applicable prediction for the anemia risk in malignant lymphoma patients.

Key words: Malignant lymphoma, Anemia, LASSO analysis, Risk factors, Nomogram