McCoy Rozalina G, Ngufor Che, Van Houten Holly K, Caffo Brian, Shah Nilay D
Departments of *Medicine, Division of Primary Care Internal Medicine †Health Sciences Research, Division of Health Care Policy & Research, Mayo Clinic ‡Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery §Department of Health Sciences Research, Division of Biomedical Statistics & Informatics, Mayo Clinic, Rochester, MN ∥Department of Biostatistics, Johns Hopkins University, Baltimore, MD ¶OptumLabs, Cambridge, MA.
Med Care. 2017 Nov;55(11):956-964. doi: 10.1097/MLR.0000000000000807.
Individualized diabetes management would benefit from prospectively identifying well-controlled patients at risk of losing glycemic control.
To identify patterns of hemoglobin A1c (HbA1c) change among patients with stable controlled diabetes.
Cohort study using OptumLabs Data Warehouse, 2001-2013. We develop and apply a machine learning framework that uses a Bayesian estimation of the mixture of generalized linear mixed effect models to discover glycemic trajectories, and a random forest feature contribution method to identify patient characteristics predictive of their future glycemic trajectories.
The study cohort consisted of 27,005 US adults with type 2 diabetes, age 18 years and older, and stable index HbA1c <7.0%.
HbA1c values during 24 months of observation.
We compared models with k=1, 2, 3, 4, 5 trajectories and baseline variables including patient age, sex, race/ethnicity, comorbidities, medications, and HbA1c. The k=3 model had the best fit, reflecting 3 distinct trajectories of glycemic change: (T1) rapidly deteriorating HbA1c among 302 (1.1%) youngest (mean, 55.2 y) patients with lowest mean baseline HbA1c, 6.05%; (T2) gradually deteriorating HbA1c among 902 (3.3%) patients (mean, 56.5 y) with highest mean baseline HbA1c, 6.53%; and (T3) stable glycemic control among 25,800 (95.5%) oldest (mean, 58.5 y) patients with mean baseline HbA1c 6.21%. After 24 months, HbA1c rose to 8.75% in T1 and 8.40% in T2, but remained stable at 6.56% in T3.
Patients with controlled type 2 diabetes follow 3 distinct trajectories of glycemic control. This novel application of advanced analytic methods can facilitate individualized and population diabetes care by proactively identifying high risk patients.
前瞻性地识别有血糖控制丧失风险的血糖控制良好的患者，将有助于实现个性化糖尿病管理。
确定血糖稳定控制的糖尿病患者糖化血红蛋白（HbA1c）变化模式。
使用OptumLabs数据仓库进行队列研究，时间跨度为2001年至2013年。我们开发并应用了一个机器学习框架，该框架使用广义线性混合效应模型混合的贝叶斯估计来发现血糖轨迹，并使用随机森林特征贡献方法来识别预测患者未来血糖轨迹的患者特征。
研究队列包括27,005名美国2型糖尿病成年人，年龄在18岁及以上，且索引糖化血红蛋白（HbA1c）稳定<7.0%。
观察24个月期间的HbA1c值。
我们比较了具有1、2、3、4、5条轨迹的模型以及包括患者年龄、性别、种族/民族、合并症、药物治疗和HbA1c在内的基线变量。k = 3的模型拟合度最佳，反映了3种不同的血糖变化轨迹：（T1）302名（1.1%）最年轻（平均年龄55.2岁）、平均基线HbA1c最低（6.05%）的患者中HbA1c迅速恶化；（T2）902名（3.3%）平均基线HbA1c最高（6.53%）、平均年龄56.5岁的患者中HbA1c逐渐恶化；（T3）25,800名（95.5%）年龄最大（平均年龄58.5岁）、平均基线HbA1c为6.21%的患者血糖控制稳定。24个月后，T1组的HbA1c升至8.75%，T2组升至8.40%，而T3组保持稳定，为6.56%。
血糖控制良好的2型糖尿病患者遵循3种不同的血糖控制轨迹。这种先进分析方法的新应用可以通过主动识别高危患者来促进个性化和群体糖尿病护理。
