基于动态血糖监测系统探讨七点末梢血糖谱对1型糖尿病夜间低血糖的评估价值

Value of daily capillary blood glucose profiles in assessing nocturnal hypoglycemia of type 1 diabetes mellitus based on continuous blood glucose monitoring system

目的应用动态血糖监测系统(CGMS)评估1型糖尿病(T1DM)患者夜间低血糖的发生情况及影响因素,探讨七点末梢血糖谱对T1DM患者夜间低血糖的评估价值。方法纳入2013年5月至2018年8月在南京鼓楼医院住院的T1DM患者137例,在患者治疗方案基本稳定后给予CGM,同步监测三餐前后及睡前的末梢血糖,观察低血糖的发生特点。再根据CGM期间低血糖发生情况分为无低血糖组和夜间低血糖组,比较两组的一般特征、实验室指标及CGM参数变化。为进一步确立末梢血糖与夜间低血糖发生相关的最佳切点值,对空腹、晚餐后、睡前血糖及评估模型BGn进行了受试者操作特征(ROC)曲线分析,计算曲线下面积(AUC)。夜间发生低血糖的危险因素采用Logistic回归分析。结果(1)在接受CGMS监测的137例T1DM患者中,共发生低血糖事件179次,其中发生夜间低血糖患者31例,共50次(27.9%);(2)Logistic回归分析显示,糖化血红蛋白(HbA1c)、糖化白蛋白、平均血糖(MBG)与夜间低血糖的发生呈独立负相关(OR=0.784、0.021、0.751,P<0.05),血糖水平标准差(SD)、低血糖指数(LBGI)呈独立正相关(OR=1.641、3.004,P<0.05);(3)七点末梢血糖谱中的空腹、晚餐后及睡前血糖与夜间发生低血糖呈独立负相关(OR=0.257、0.685、0.708,P<0.05),应用ROC分析相应切点值,空腹血糖(FPG)为5.8mmol/L(特异度90%,敏感度80%,AUC0.91)、晚餐后血糖为8.2mmol/L(特异度76%,敏感度57%,AUC0.72)、睡前血糖为6.7mmol/L(特异度90%,敏感度64%,AUC0.80);(4)基于七点末梢血糖谱中的基础血糖变异度,建立夜间低血糖的评测模型BGn=睡前血糖×(1-SDSM/MBGSM),BGn为5.2mmol/L时,特异度达93%,AUC为0.81。结论T1DM患者夜间低血糖发生率高,应设定个体化血糖控制目标,FPG<5.8mmol/L、睡前血糖<6.7mmol/L或BGn模型<5.2mmol/L均提示夜间发生低血糖的危险增加。

Objective To investigate the incidence and risk factors of nocturnal hypoglycemia in type 1 diabetes mellitus (T1DM), and to explore whether nocturnal hypoglycemia can be evaluated by daily capillary blood glucose profiles. Methods A total of 137 T1DM patients hospitalized in Nanjing Drum Tower Hospital between May 2013 and August 2018 were recruited and received continuous glucose monitoring (CGM) for 3 consecutive days during stable therapy period, meanwhile capillary blood glucose measurements (before and after 3 meals as well as at bedtime) were recorded. From data of CGM, the patients were divided into nocturnal hypoglycemia group and non-hypoglycemia group. The demographics, laboratory measurements and dynamic blood glucose parameters were compared between these two groups. Receiver operating characteristic curve (ROC) was used to analyze the optimal cut-off points of fasting blood glucose, postprandial blood glucose, bedtime blood glucose and BGn was used to predict nocturnal hypoglycemia. Multiple regression analysis was used to evaluate the risk factors of nocturnal hypoglycemia. Results (1) Totally, 179 hypoglycemic profiles monitored by CGM were recorded in 137 patients with T1DM, including 50 nocturnal hypoglycemic episodes occurred in 31 patients (27.9%).(2) Logistic regression analysis indicated that glycated hemoglobin A1c (HbA1c), glycated albumin and mean blood glucose were independent negatively correlated with nocturnal hypoglycemia (OR=0.784, 0.021, 0.751, P<0.05), while standard deviation of blood glucose and low blood glucose index were independent positively correlated with nocturnal hypoglycemia (OR=1.641, 3.004, P<0.05).(3) Of the daily capillary blood glucose profiles, levels of fasting blood glucose, blood glucose after dinner and blood glucose at bedtime were independently negative correlated with nocturnal hypoglycemia (OR=0.257, 0.685, 0.708, P<0.05). The cut-off values for prediction of nocturnal hypoglycemia were as follows: levels of fasting glucose was 5.8 mmol/L [sensitivity 80%, specificity 90%, area under curvel (AUC) 0.91], levels of blood glucose after dinner was 8.2 mmol/L (sensitivity 57%, specificity 76%, AUC 0.72), levels of blood glucose at bedtime was 6.7 mmol/L (sensitivity 64%, specificity 90%, AUC 0.80).(4) Based on the capillary blood glucose profiles before meals and at bedtime, a model was established for the prediction of nocturnal hypoglycemia: BGn=bedtime blood glucose ×(1-SDSM/MBGSM). When BGn was 5.2 mmol/L, the specificity increased to 93% and AUC was 0.81. Conclusion Nocturnal hypoglycemia is common in patients with T1DM, and individualized blood glucose control targets should be set. Potential increased risk factors of nocturnal hypoglycemia were as follows: the levels of fasting blood glucose in the morning is below 5.8 mmol/L, the levels of blood glucose at bedtime is below 6.7 mmol/L or the model of BGn is below 5.2 mmol/L.