Wang Kesheng, Theeke Laurie A, Liao Christopher, Wang Nianyang, Lu Yongke, Xiao Danqing, Xu Chun
School of Nursing, Health Sciences Center, West Virginia University, Morgantown, WV 26506, USA.
School of Nursing, The George Washington University, Ashburn, VA 20147, USA.
J Neurol Sci. 2023 Oct 15;453:120812. doi: 10.1016/j.jns.2023.120812. Epub 2023 Sep 22.
Metabolic biomarkers can potentially inform disease progression in Alzheimer's disease (AD). The purpose of this study is to identify and describe a new set of diagnostic biomarkers for developing deep learning (DL) tools to predict AD using Ultra Performance Liquid Chromatography Mass Spectrometry (UPLC-MS/MS)-based metabolomics data.
A total of 177 individuals, including 78 with AD and 99 with cognitive normal (CN), were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort along with 150 metabolomic biomarkers. We performed feature selection using the Least Absolute Shrinkage and Selection Operator (LASSO). The H2O DL function was used to build multilayer feedforward neural networks to predict AD.
The LASSO selected 21 metabolic biomarkers. To develop DL models, the 21 biomarkers identified by LASSO were imported into the H2O package. The data was split into 70% for training and 30% for validation. The best DL model with two layers and 18 neurons achieved an accuracy of 0.881, F1-score of 0.892, and AUC of 0.873. Several metabolomic biomarkers involved in glucose and lipid metabolism, in particular bile acid metabolites, were associated with APOE-ε4 allele and clinical biomarkers (Aβ42, tTau, pTau), cognitive assessments [the Alzheimer's Disease Assessment Scale-cognitive subscale 13 (ADAS13), the Mini-Mental State Examination (MMSE)], and hippocampus volume.
This study identified a new set of diagnostic metabolomic biomarkers for developing DL tools to predict AD. These biomarkers may help with early diagnosis, prognostic risk stratification, and/or early treatment interventions for patients at risk for AD.
代谢生物标志物可能为阿尔茨海默病（AD）的疾病进展提供信息。本研究的目的是识别并描述一组新的诊断生物标志物，用于开发深度学习（DL）工具，以利用基于超高效液相色谱质谱联用（UPLC-MS/MS）的代谢组学数据预测AD。
从阿尔茨海默病神经成像倡议（ADNI）队列中选取了177名个体，包括78名AD患者和99名认知正常（CN）者，以及150种代谢组学生物标志物。我们使用最小绝对收缩和选择算子（LASSO）进行特征选择。使用H2O DL函数构建多层前馈神经网络来预测AD。
LASSO选择了21种代谢生物标志物。为了开发DL模型，将LASSO识别出的21种生物标志物导入H2O软件包。数据分为70%用于训练，30%用于验证。具有两层和18个神经元的最佳DL模型的准确率为0.881，F1分数为0.892，曲线下面积（AUC）为0.873。几种参与葡萄糖和脂质代谢的代谢组学生物标志物，特别是胆汁酸代谢物，与APOE-ε4等位基因和临床生物标志物（Aβ42、总tau蛋白、磷酸化tau蛋白）、认知评估[阿尔茨海默病评估量表认知子量表13（ADAS13）、简易精神状态检查表（MMSE）]以及海马体积相关。
本研究识别出一组新的诊断代谢组学生物标志物，用于开发预测AD的DL工具。这些生物标志物可能有助于对AD风险患者进行早期诊断、预后风险分层和/或早期治疗干预。
