Department of Internal Medicine and Center for Value-Based Care Research, Cleveland Clinic Community Care, Cleveland Clinic, United States of America; Department of Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic, United States of America.
Department of Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic, United States of America.
J Diabetes Complications. 2020 Jan;34(1):107490. doi: 10.1016/j.jdiacomp.2019.107490. Epub 2019 Nov 12.
BACKGROUND/AIM: Episodes of non-severe hypoglycemia can be captured through diagnoses documented in the electronic medical record. We aimed to create a clinically useful prediction model for a severe hypoglycemia event, requiring an emergency department visit or hospitalization, in patients with Type 2 diabetes with a history of non-severe hypoglycemia.
Using electronic medical record data from 50,439 patients with Type 2 diabetes in one health system, number of severe hypoglycemia events and associated patient characteristics from 2006 to 2015 were previously defined. Using the landmarking method, a dynamic prediction model was built using the subset of 1876 patients who had a documented non-severe hypoglycemia diagnosis code, using logistic regression to obtain landmark-specific odds of severe hypoglycemia in this group. For model performance, the bootstrap procedure was employed for internal validation and area under the curve (AUC) and index of prediction accuracy (IPA) were calculated.
Glycosylated hemoglobin (HbA1c) less than 7% (53 mmol/mol) was associated with increased odds ratio (OR) of severe hypoglycemia at 3 months (OR 1.92 95% Confidence Interval (CI) 1.19-3.10 at HbA1c 5% (31 mmol/mol) and OR 1.21, CI 1.03-1.41 at HbA1c 6%(42 mmol/mol).) History of non-severe hypoglycemia within the past 3 months increased odds for severe hypoglycemia (OR 2.58 95% CI 1.80-3.70) as did Black race, insulin use with the past 3 months, and comorbidities. Metformin and sulfonlylurea use in the past 3 months, increasing age and body mass index had lower odds of a future severe hypoglycemia event. For the prediction model for 3 month risk of severe hypoglycemia, the AUC was 0.890 (CI 0.843-0.907) and the IPA was 10.8% (CI 4.4% - 12.4%).
In patients with a documented diagnosis of non-severe hypoglycemia, a dynamic prediction model identifies patients with Type 2 diabetes with 3-month increased risk of severe hypoglycemia, allowing for preventive efforts, such as medication changes, at the point of care.
背景/目的：通过电子病历中记录的诊断，可以捕捉到非严重低血糖发作。我们旨在为有非严重低血糖病史的 2 型糖尿病患者创建一个用于预测严重低血糖事件（需要急诊或住院治疗）的临床有用的预测模型。
利用来自一个医疗系统的 50439 例 2 型糖尿病患者的电子病历数据，根据 2006 年至 2015 年的严重低血糖事件和相关患者特征，对先前定义的严重低血糖事件进行定义。使用 landmarking 方法，使用 1876 例有记录的非严重低血糖诊断代码的患者子集，使用逻辑回归获得该组中严重低血糖的 landmark 特异性比值比。对于模型性能，采用自举程序进行内部验证，并计算曲线下面积（AUC）和预测准确性指数（IPA）。
糖化血红蛋白（HbA1c）<7%（53mmol/mol）与 3 个月时严重低血糖的比值比（OR）升高相关（HbA1c 5%（31mmol/mol）时 OR 1.92，95%置信区间（CI）1.19-3.10，HbA1c 6%（42mmol/mol）时 OR 1.21，CI 1.03-1.41）。过去 3 个月内有非严重低血糖病史会增加严重低血糖的几率（OR 2.58，95%CI 1.80-3.70），黑种人、过去 3 个月内使用胰岛素以及合并症也是如此。过去 3 个月内使用二甲双胍和磺酰脲类药物、年龄增长和体重指数增加与未来严重低血糖事件的几率降低相关。对于 3 个月内严重低血糖风险的预测模型，AUC 为 0.890（CI 0.843-0.907），IPA 为 10.8%（CI 4.4%-12.4%）。
在有非严重低血糖诊断记录的患者中，动态预测模型可识别出 2 型糖尿病患者在 3 个月内严重低血糖风险增加，从而可以在护理点进行药物改变等预防措施。
