Department of Radiology, University Hospital, LMU Munich, Munich, Germany.
Dresden International University, Division of Health Care Sciences, Center for Clinical Research and Management Education, Dresden, Germany.
Sci Rep. 2020 May 20;10(1):8363. doi: 10.1038/s41598-020-65040-x.
To identify the most important factors that impact brain volume, while accounting for potential collinearity, we used a data-driven machine-learning approach. Gray Matter Volume (GMV) was derived from magnetic resonance imaging (3T, FLAIR) and adjusted for intracranial volume (ICV). 93 potential determinants of GMV from the categories sociodemographics, anthropometric measurements, cardio-metabolic variables, lifestyle factors, medication, sleep, and nutrition were obtained from 293 participants from a population-based cohort from Southern Germany. Elastic net regression was used to identify the most important determinants of ICV-adjusted GMV. The four variables age (selected in each of the 1000 splits), glomerular filtration rate (794 splits), diabetes (323 splits) and diabetes duration (122 splits) were identified to be most relevant predictors of GMV adjusted for intracranial volume. The elastic net model showed better performance compared to a constant linear regression (mean squared error = 1.10 vs. 1.59, p < 0.001). These findings are relevant for preventive and therapeutic considerations and for neuroimaging studies, as they suggest to take information on metabolic status and renal function into account as potential confounders.
为了确定影响脑容量的最重要因素，同时考虑到潜在的共线性，我们使用了一种数据驱动的机器学习方法。脑灰质体积（GMV）源自磁共振成像（3T，FLAIR），并根据颅内体积（ICV）进行了调整。从社会人口统计学、人体测量学测量、心血管代谢变量、生活方式因素、药物、睡眠和营养等类别中获得了来自德国南部一个基于人群的队列的 293 名参与者的 93 个 GMV 的潜在决定因素。弹性网络回归用于确定 ICV 调整后 GMV 的最重要决定因素。四个变量（在每个 1000 个分割中选择一个），肾小球滤过率（794 个分割）、糖尿病（323 个分割）和糖尿病持续时间（122 个分割）被确定为与颅内体积调整后的 GMV 最相关的预测因子。弹性网络模型的表现优于常数线性回归（均方误差=1.10 与 1.59，p<0.001）。这些发现与预防和治疗考虑以及神经影像学研究有关，因为它们表明需要考虑代谢状态和肾功能信息作为潜在的混杂因素。
