Objective To analyze the risk factors for anemia in patients with multiple myeloma,construct a nomo-gram prediction model based on this,and evaluate its predictive value.Method The clinical data of 130 multiple myelo-ma patients were collected,and divided into anemia group(n=56)and non-anemia group(n=74)based on whether ane-mia occurred.The influencing factors of anemia in patients with multiple myeloma were analyzed by using multivariate Logistic regression,and a nomogram prediction model was constructed to predict the risk of anemia in patients with multi-ple myeloma according to the influencing factors.The receiver operating characteristic(ROC)curve was drawn,the area under the curve(AUC)was calculated,and the predictive value of nomogram prediction model for risk of anemia in mul-tiple myeloma patients was evaluated.The reliability and accuracy of the nomogram prediction model were evaluated by calibration curve,and the clinical application value of the nomogram prediction model was evaluated by decision curve analysis(DCA).Result Multivariate Logistic regression showed that decreased platelet count,increased proportion of bone marrow plasma cells,increased blood creatinine levels,and increased interleukin-6(IL-6)were independent risk fac-tors for anemia in patients with multiple myeloma(P＜0.05).Based on this,a nomogram prediction model was construct-ed.ROC curve showed that the AUC of the nomogram prediction model for predicting the risk of anemia in multiple my-eloma patients was 0.951,indicating a high predictive value.The calibration curve showed that the C-index of the nomo-gram prediction model for predicting the risk of anemia in multiple myeloma patients was 0.778(95％CI:0.741-0.815),indicating that the observed values of the nomogram prediction model had good agreement with the actual observed re-sults for predicting the risk of anemia.The DCA curve showed that the prediction model had clinical significance in pre-dicting the risk of anemia in patients with multiple myeloma,with a high clinical net benefit.Conclusion The risk of anemia in patients with multiple myeloma is closely related to decrease in platelet count,increase in the proportion of bone marrow plasma cells,and increase in blood creatinine levels and IL-6.The nomogram prediction model constructed based on these risk factors has high accuracy in predicting the risk of anemia in patients with multiple myeloma.
维普
万方数据