目的：筛选糖尿病性黄斑水肿(DME)患者疾病进展风险的预测因素，建立联合预测模型并分析其预测效能。

方法：回顾性研究，选取2021年7月至2024年10月在我院治疗的240例DME患者为研究对象，根据黄斑中心厚度(CMT)及是否累及中心凹将患者分为低风险组102例与高风险组138例。收集患者的基本资料和糖脂代谢指标、肝肾功能指标等相关检查数据，将单因素分析有差异的指标(P<0.05)纳入多因素分析，筛选出DME患者疾病进展的影响因素，并构建预测模型。用受试者工作特征曲线下面积对预测模型的拟合效果进行评估，通过灵敏度、特异度和约登指数对预测模型进行验证。

结果：两组患者一般资料比较具有可比性，血压比较无差异(均P>0.05)。单因素分析显示，高风险组基线、3、6 mo的糖化血红蛋白(HbA1c)、空腹血糖(FBG)、晚期糖基化终末产物(AGEs)、总胆固醇(TC)、低密度脂蛋白胆固醇(LDL-C)、甘油三酯(TG)、血肌酐(Scr)、尿酸(UA)及3、6 mo胱抑素C(Cys-C)均高于低风险组(均P<0.01)； 高风险组的基线、3、6 mo肾小球滤过率(eGFR)、总胆红素(TBIL)及3、6 mo高密度脂蛋白胆固醇(HDL-C)均低于低风险组(P<0.05)； 回归分析显示基线HbA1c、3 mo FBG、3 mo AGEs、基线LDL-C、3 mo TG、3 mo eGFR、基线TBIL、6 mo TBIL是DME患者疾病进展风险的影响因素。联合构建的预测模型曲线下面积为0.909(95%CI：0.872-0.945)，敏感度79.00%、特异度94.10%。

结论：HbA1c、FBG、AGEs、LDL-C、TG、eGFR、TBIL是DME患者疾病进展风险的影响因素，联合构建预测模型可为预测DME患者疾病进展风险提供参考。

METHODS:A retrospective selection was made of 240 patients with DME who were treated in our hospital from July 2021 to October 2024 as the research subjects. The patients were divided into a low-risk group(n=102)and a high-risk group(n=138)based on the central macular thickness(CMT)and whether the fovea was accumulated. The basic information of the patients and relevant examination data such as glycolipid metabolism indicators and liver and kidney function indicators were collected. The indicators with differences in the univariate analysis(P<0.05)were included in the multivariate analysis to screen out the independent influencing factors of disease progression in DME patients and construct a predictive model. The fitting effect of the prediction model was evaluated by the area under the receiver operating characteristic curve, and the prediction model was verified by sensitivity, specificity and Youden index.

RESULTS: The general data of the two groups of patients are comparable, and there was no statistically significant difference in blood pressure between the two groups of patients(both P>0.05). Univariate analysis showed that the glycated hemoglobin(HbA1c), fasting blood glucose(FBG), advanced glycation end products(AGEs), total cholesterol(TC), low-density lipoprotein cholesterol(LDL-C), triglycerides(TG), serum creatinine(Scr), uric acid(UA), and cystatin C(Cys-C)at 3 and 6 mo in the high-risk group at baseline, 3 and 6 mo were higher than those in the low-risk group(all P<0.01). The baseline, 3 and 6 mo estimated glomerular filtration rate(eGFR), total bilirubin(TBIL), and 3 and 6 mo high-density lipoprotein cholesterol(HDL-C)in the high-risk group were all lower than those in the low-risk group(P<0.05). Regression analysis showed that baseline HbA1c, 3 mo FBG, 3 mo AGEs, baseline LDL-C, 3 mo TG, 3 mo eGFR, baseline TBIL, and 6 mo TBIL were risk factors for disease progression in DME patients. The area under curve(AUC)of the combined prediction model was 0.909(95%CI: 0.872-0.945), with a sensitivity of 79.00% and a specificity of 94.10%.

CONCLUSION: HbA1c, FBG, AGEs, LDL-C, TG, eGFR and TBIL are risk factors for the risk of disease progression in patients with DME. The combined prediction model can provide a reference for predicting the risk of disease progression in patients with DME.