Eli Lilly and Company, Indianapolis, IN, USA.
Optum Labs, Minneapolis, MN, USA.
J Diabetes Sci Technol. 2023 Nov;17(6):1573-1579. doi: 10.1177/19322968221098057. Epub 2022 May 20.
The aim of this study was to develop a predictive model to classify people with type 2 diabetes (T2D) into expected levels of success upon bolus insulin initiation.
Machine learning methods were applied to a large nationally representative insurance claims database from the United States (dNHI database; data from 2007 to 2017). We trained boosted decision tree ensembles (XGBoost) to assign people into Class 0 (never meeting HbA1c goal), Class 1 (meeting but not maintaining HbA1c goal), or Class 2 (meeting and maintaining HbA1c goal) based on the demographic and clinical data available prior to initiating bolus insulin. The primary objective of the study was to develop a model capable of determining at an individual level, whether people with T2D are likely to achieve and maintain HbA1c goals. HbA1c goal was defined at <8.0% or reduction of baseline HbA1c by >1.0%.
Of 15 331 people with T2D (mean age, 53.0 years; SD, 8.7), 7800 (50.9%) people met HbA1c goal but failed to maintain that goal (Class 1), 4510 (29.4%) never attained this goal (Class 0), and 3021 (19.7%) people met and maintained this goal (Class 2). Overall, the model's receiver operating characteristic (ROC) was 0.79 with greater performance on predicting those in Class 2 (ROC = 0.92) than those in Classes 0 and 1 (ROC = 0.71 and 0.62, respectively). The model achieved high area under the precision-recall curves for the individual classes (Class 0, 0.46; Class 1, 0.58; Class 2, 0.71).
Predictive modeling using routine health care data reasonably accurately classified patients initiating bolus insulin who would achieve and maintain HbA1c goals, but less so for differentiation between patients who never met and who did not maintain goals. Prior HbA1c was a major contributing parameter for the predictions.
本研究旨在开发一种预测模型，以将 2 型糖尿病（T2D）患者分为起始胰岛素冲击治疗后预期达标水平。
应用机器学习方法对来自美国的大型全国性保险理赔数据库（dNHI 数据库；数据来自 2007 年至 2017 年）进行分析。我们利用提升决策树集合（XGBoost）对人群进行分类，0 类（从未达到 HbA1c 目标）、1 类（达到但未维持 HbA1c 目标）或 2 类（达到并维持 HbA1c 目标），分类依据是起始胰岛素冲击治疗前的人口统计学和临床数据。研究的主要目的是开发一种能够确定个体患者是否可能达到和维持 HbA1c 目标的模型。HbA1c 目标定义为＜8.0%或较基线 HbA1c 降低＞1.0%。
在 15331 例 T2D 患者中（平均年龄 53.0 岁，标准差 8.7），7800 例（50.9%）患者达到 HbA1c 目标但未能维持（1 类），4510 例（29.4%）从未达到此目标（0 类），3021 例（19.7%）患者达到并维持此目标（2 类）。总体而言，模型的受试者工作特征曲线（ROC）为 0.79，对预测 2 类患者（ROC=0.92）的性能优于预测 0 类和 1 类患者（ROC=0.71 和 0.62）。模型在预测个体患者类别时，精准度-召回曲线下面积较高（0 类，0.46；1 类，0.58；2 类，0.71）。
利用常规医疗保健数据进行预测建模可以合理准确地对起始胰岛素冲击治疗的患者进行分类，以评估其是否能达到和维持 HbA1c 目标，但对区分从未达标和未能维持目标的患者的预测效果较差。既往 HbA1c 是预测的主要影响因素。
