Prediction of Incident Diabetes in the Jackson Heart Study Using High-Dimensional Machine Learning.
Prediction of Incident Diabetes in the Jackson Heart Study Using High-Dimensional Machine Learning.
复制标题
DOI：
10.1371/journal.pone.0163942
复制
发表时间：
2016
期刊：
影响因子：
3.7
通讯作者：
Bertoni AG
中科院分区：
文献类型：
--
作者：
Casanova R;Saldana S;Simpson SL;Lacy ME;Subauste AR;Blackshear C;Wagenknecht L;Bertoni AG
预测糖尿病发病率的统计模型通常基于有限的变量。在这里，我们追求两个主要目标：1）研究机器学习方法（如随机森林（RF））在由大量观察数据定义的高维环境中检测糖尿病事件的相对性能，以及2）发现糖尿病的潜在预测因素。杰克逊心脏研究收集了5,301名非裔美国人的基线和两次随访数据。我们排除了那些基线糖尿病患者和没有随访的人，留下3，633人进行分析。在平均8年的随访中，584名参与者患上了糖尿病。完整RF模型评价了93个变量，包括人口统计学、人体测量学、血液生物标志物、病史和超声心动图数据。我们还使用变量重要性的RF指标，根据变量对糖尿病预测的贡献对变量进行排名。我们基于逻辑回归和RF实现了其他模型，其中预先选择了特征。RF全模型性能与那些更简约的模型相似（AUC = 0.82）。根据RF排名靠前的变量包括血红蛋白A1 C、空腹血糖、腰围、脂联素、C反应蛋白、甘油三酯、瘦素、左心室质量、高密度脂蛋白胆固醇和醛固酮。这项工作显示了RF在处理高维数据时用于糖尿病预测的潜力。
Statistical models to predict incident diabetes are often based on limited variables. Here we pursued two main goals: 1) investigate the relative performance of a machine learning method such as Random Forests (RF) for detecting incident diabetes in a high-dimensional setting defined by a large set of observational data, and 2) uncover potential predictors of diabetes. The Jackson Heart Study collected data at baseline and in two follow-up visits from 5,301 African Americans. We excluded those with baseline diabetes and no follow-up, leaving 3,633 individuals for analyses. Over a mean 8-year follow-up, 584 participants developed diabetes. The full RF model evaluated 93 variables including demographic, anthropometric, blood biomarker, medical history, and echocardiogram data. We also used RF metrics of variable importance to rank variables according to their contribution to diabetes prediction. We implemented other models based on logistic regression and RF where features were preselected. The RF full model performance was similar (AUC = 0.82) to those more parsimonious models. The top-ranked variables according to RF included hemoglobin A1C, fasting plasma glucose, waist circumference, adiponectin, c-reactive protein, triglycerides, leptin, left ventricular mass, high-density lipoprotein cholesterol, and aldosterone. This work shows the potential of RF for incident diabetes prediction while dealing with high-dimensional data.
登录
查看更多内容
影响因子：
2.9
作者：
Farran B;Channanath AM;Behbehani K;Thanaraj TA
通讯作者：
Thanaraj TA
影响因子：
16.2
作者：
Effoe VS;Correa A;Chen H;Lacy ME;Bertoni AG
通讯作者：
Bertoni AG
影响因子：
3.7
作者：
Casanova R;Saldana S;Chew EY;Danis RP;Greven CM;Ambrosius WT
通讯作者：
Ambrosius WT
影响因子：
168.9
作者：
Ferrannini, Ele;Cushman, William C.
通讯作者：
Cushman, William C.
影响因子：
3.7
作者：
Casanova R;Hsu FC;Sink KM;Rapp SR;Williamson JD;Resnick SM;Espeland MA;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative