Functional near-infrared spectroscopy (fNIRS) and its interaction with machine learning (ML) is a popular research topic for the diagnostic classification of clinical disorders due to the lack of robust and objective biomarkers. This review provides an overview of research on psychiatric diseases by using fNIRS and ML. Article search was carried out and 45 studies were evaluated by considering their sample sizes, used features, ML methodology, and reported accuracy. To our best knowledge, this is the first review that reports diagnostic ML applications using fNIRS. We found that there has been an increasing trend to perform ML applications on fNIRS-based biomarker research since 2010. The most studied populations are schizophrenia (n = 12), attention deficit and hyperactivity disorder (n = 7), and autism spectrum disorder (n = 6) are the most studied populations. There is a significant negative correlation between sample size (>21) and accuracy values. Support vector machine (SVM) and deep learning (DL) approaches were the most popular classifier approaches (SVM = 20) (DL = 10). Eight of these studies recruited a number of participants more than 100 for classification. Concentration changes in oxy-hemoglobin (ΔHbO) based features were used more than concentration changes in deoxy-hemoglobin (ΔHb) based ones and the most popular ΔHbO-based features were mean ΔHbO (n = 11) and ΔHbO-based functional connections (n = 11). Using ML on fNIRS data might be a promising approach to reveal specific biomarkers for diagnostic classification.

中文翻译：

---

使用功能性近红外光谱对临床人群进行诊断机器学习应用：综述

由于缺乏可靠且客观的生物标志物，功能性近红外光谱（fNIRS）及其与机器学习（ML）的相互作用是临床疾病诊断分类的热门研究课题。本综述概述了使用 fNIRS 和 ML 对精神疾病进行的研究。我们进行了文章搜索，并根据样本量、使用的特征、ML 方法和报告的准确性对 45 项研究进行了评估。据我们所知，这是第一篇使用 fNIRS 报告诊断 ML 应用的综述。我们发现，自 2010 年以来，在基于 fNIRS 的生物标志物研究中进行机器学习应用的趋势不断增加。研究最多的人群是精神分裂症患者（n= 12），注意力缺陷和多动症（n= 7) 和自闭症谱系障碍 (n= 6) 是研究最多的人群。样本量 (>21) 和准确度值之间存在显着的负相关。支持向量机 (SVM) 和深度学习 (DL) 方法是最流行的分类器方法 (SVM = 20) (DL = 10)。其中八项研究招募了超过 100 名参与者进行分类。基于氧合血红蛋白 (ΔHbO) 的浓度变化的特征比基于脱氧血红蛋白 (ΔHb) 的浓度变化的特征使用得更多，并且最流行的基于 ΔHbO 的特征是平均 ΔHbO (n= 11) 和基于 ΔHbO 的功能连接 (n= 11）。在 fNIRS 数据上使用机器学习可能是揭示诊断分类的特定生物标志物的一种有前途的方法。