Division of Nephrology, Department of Medicine, Joan C Edwards School of Medicine, Marshall University, Huntington, West Virginia, USA.
Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, Maryland, USA.
J Clin Hypertens (Greenwich). 2021 Dec;23(12):2137-2145. doi: 10.1111/jch.14397. Epub 2021 Nov 30.
Albuminuria and estimated glomerular filtration rate (e-GFR) are early markers of renal disease and cardiovascular outcomes in persons with diabetes. Although body composition has been shown to predict systolic blood pressure, its application in predicting albuminuria is unknown. In this study, we have used machine learning methods to assess the risk of albuminuria in persons with diabetes using body composition and other determinants of metabolic health. This study is a comparative analysis of the different methods to predict albuminuria in persons with diabetes mellitus who are older than 40 years of age, using the LOOK AHEAD study cohort-baseline characteristics. Age, different metrics of body composition, duration of diabetes, hemoglobin A1c, serum creatinine, serum triglycerides, serum cholesterol, serum HDL, serum LDL, maximum exercise capacity, systolic blood pressure, diastolic blood pressure, and the ankle-brachial index are used as predictors of albuminuria. We used Area under the curve (AUC) as a metric to compare the classification results of different algorithms, and we show that AUC for the different models are as follows: Random forest classifier-0.65, gradient boost classifier-0.61, logistic regression-0.66, support vector classifier -0.61, multilayer perceptron -0.67, and stacking classifier-0.62. We used the Random forest model to show that the duration of diabetes, A1C, serum triglycerides, SBP, Maximum exercise Capacity, serum creatinine, subtotal lean mass, DBP, and subtotal fat mass are important features for the classification of albuminuria. In summary, when applied to metabolic imaging (using DXA), machine learning techniques offer unique insights into the risk factors that determine the development of albuminuria in diabetes.
尿白蛋白和估计肾小球滤过率 (e-GFR) 是糖尿病患者肾脏疾病和心血管结局的早期标志物。尽管身体成分已被证明可预测收缩压，但它在预测尿白蛋白方面的应用尚不清楚。在这项研究中，我们使用机器学习方法评估了使用身体成分和代谢健康的其他决定因素预测糖尿病患者尿白蛋白的风险。这是对年龄大于 40 岁的糖尿病患者使用 LOOK AHEAD 研究队列基线特征预测尿白蛋白的不同方法的比较分析。年龄、身体成分的不同指标、糖尿病病程、糖化血红蛋白、血清肌酐、血清甘油三酯、血清胆固醇、血清高密度脂蛋白、血清低密度脂蛋白、最大运动能力、收缩压、舒张压和踝臂指数用作尿白蛋白的预测因子。我们使用曲线下面积 (AUC) 作为衡量不同算法分类结果的指标，结果表明不同模型的 AUC 如下：随机森林分类器为 0.65、梯度提升分类器为 0.61、逻辑回归为 0.66、支持向量机分类器为 0.61、多层感知机为 0.67、堆叠分类器为 0.62。我们使用随机森林模型表明，糖尿病病程、A1C、血清甘油三酯、SBP、最大运动能力、血清肌酐、总瘦体重、DBP 和总脂肪量是尿白蛋白分类的重要特征。总之，当应用于代谢成像（使用 DXA）时，机器学习技术为确定糖尿病患者尿白蛋白发展的危险因素提供了独特的见解。
