MDD ATR dataset

While functional near-infrared spectroscopy (fNIRS) had previously been suggested for major depressive disorder (MDD) diagnosis, the clinical application to predict antidepressant treatment response (ATR) is still unclear. To address this, the aim of the current study is to investigate MDD ATR using fNIRS and micro-ribonucleic acids (miRNAs). Our proposed algorithm includes a custom inter-subject variability reduction based on the Principal Component Analysis (PCA). The entire algorithm achieved a better performance through the Gaussian support vector machine (SVM), with 82.70% accuracy, 78.44% sensitivity, 86.15% precision, and 91.02% specificity, respectively, when compared with conventional approaches. The actual effect in feature space of the mentioned proposal is also visualized via 2-dimensional t-distributed stochastic embeddings (t-SNE) to support the claim that the fusion of fNIRS and miRNA with custom inter-subject variability removal helps differentiate various categories of MDD ATRs. 

尽管此前已有研究将功能近红外光谱（functional near-infrared spectroscopy, fNIRS）应用于重度抑郁症（major depressive disorder, MDD）的诊断，但将其用于临床预测抗抑郁治疗应答（antidepressant treatment response, ATR）的相关研究仍不明朗。为解决这一问题，本研究旨在借助功能近红外光谱与微核糖核酸（micro-ribonucleic acids, miRNAs）探究重度抑郁症的抗抑郁治疗应答情况。本研究提出的算法包含一种基于主成分分析（Principal Component Analysis, PCA）的自定义受试者间变异性降低方法。相较于传统方法，采用高斯支持向量机（Gaussian support vector machine, SVM）的完整算法实现了更优性能，其准确率达82.70%、灵敏度78.44%、精确率86.15%、特异度91.02%。此外，本研究还通过二维t分布随机邻域嵌入（2-dimensional t-distributed stochastic embeddings, t-SNE）对所提方法在特征空间中的实际作用效果进行可视化展示，以佐证“融合功能近红外光谱与微核糖核酸数据，并结合自定义受试者间变异性去除步骤，有助于区分不同类别的重度抑郁症抗抑郁治疗应答”这一结论。

搜集汇总

背景与挑战

背景概述

该数据集专注于研究重度抑郁症（MDD）的抗抑郁治疗反应（ATR），使用功能近红外光谱（fNIRS）和微核糖核酸（miRNAs）作为数据源，旨在通过机器学习算法预测治疗响应。数据集包含.mat格式的文件，属于生物医学和健康科学领域，其特点在于结合多模态生物数据并采用主成分分析（PCA）减少受试者间变异性，以提高分类准确性。