目的 探讨乳腺癌化疗患者骨髓抑制风险因素，构建风险预测模型。方法 采用便利抽样法，选取2022年3-10月十堰市某三级甲等医院270例乳腺癌患者，其中2022年3-7月的189例作为建模组，2022年8-10月的81例作为验证组。采用受试者特征曲线（receiver operating characteristic curve，ROC）下面积（area under the curve，AUC）和Hosmer-Lemeshow 拟合优度检验模型的预测效果，绘制模型列线图。结果 建模组和验证组骨髓抑制发生率分别为66.14%和80.25%。患者手术、化疗前白细胞、血红蛋白与血小板水平是骨髓抑制的独立影响因素（均P＜0.05）。建模组和验证组的AUC分别为0.767和0.755。结论 本研究构建的风险预测模型可预测乳腺癌化疗患者骨髓抑制风险，可为医护人员早期制订干预措施提供参考。

Objective To explore the risk factors of myelosuppression in breast cancer chemotherapy patients and to construct a risk prediction model.Methods A convenience sampling method was used to select 270 breast cancer patients from March to October 2022 in a tertiary A hospital in Shiyan,with 189 patients from March to July 2022 as the modeling group and 81 patients from August to October 2022 as the validation group.The predictive effect of the model was tested by the area under the receiver operating characteristic curve (ROC) and the Hosmer-Lemeshow goodness of fit test.The model nomogram was drawn.Results The incidence of myelosuppression was 66.14% and 80.25% in the modeling and validation groups,respectively.The surgery,pre-chemotherapy leukocyte,hemoglobin and platelet levels were independent influencing factors(P＜0.05).The AUC of the modeling and validation groups were 0.767and 0.755,respectively.Conclusions The risk prediction model constructed in this study can predict the risk of myelosuppression in breast cancer chemotherapy patients,which can provide a reference for healthcare professionals to develop interventions at an early stage.

R473.6

十堰市太和医院基金项目（2022JJXM122）；湖北省教育厅哲学社会科学项目（21D074）