Refined prefrontal working memory network as a neuromarker for Alzheimer’s disease

Abstract

Detecting Alzheimer’s disease (AD) is an important step in preventing pathological brain damage. Working memory (WM)-related network modulation can be a pathological feature of AD, but is usually modulated by untargeted cognitive processes and individual variance, resulting in the concealment of this key information. Therefore, in this study, we comprehensively investigated a new neuromarker, named “refined network,” in a prefrontal cortex (PFC) that revealed the pathological features of AD. A refined network was acquired by removing unnecessary variance from the WM-related network. By using a functional near-infrared spectroscopy (fNIRS) device, we evaluated the reliability of the refined network, which was identified from the three groups classified by AD progression: healthy people (N=31), mild cognitive impairment (N=11), and patients with AD (N=18). As a result, we identified edges with significant correlations between cognitive functions and groups in the dorsolateral PFC. Moreover, the refined network achieved a significantly correlating metric with neuropsychological test scores, and a remarkable three-class classification accuracy (95.0%). These results implicate the refined PFC WM-related network as a powerful neuromarker for AD screening.

Diagnostic Machine Learning Applications on Clinical Populations using Functional Near Infrared Spectroscopy: A Review

“…94.4 % accuracy was found to classify AD. Another study that tried to classify AD, MCI and HC subjects was conducted by Kim and colleagues (E. Kim et al, 2021). In this study, 60 participants (18 AD, 11 MCI and 31 HC) were recruited and PFC based FC of ΔHbO values were used as input of artificial neural network (ANN) classifier to classify disease state highest accuracy was found as 93.7%.…”

“…Another study that tried to classify AD, MCI and HC subjects was conducted by Kim and colleagues (E. Kim et al, 2021). In this study 60 participants( 18 AD, 11 MCI and 31 HC) attended fNIRS recording sessions during two different working memory tasks including Delayed Match-To-Sample (DMTS) task and Digit Span Test (DST).…”

“…Another study that tried to classify AD, MCI and HC subjects was conducted by Kim and colleagues (E. Kim et al, 2021).…”

Hotspots and trends in fNIRS disease research: A bibliometric analysis

“…(4) In terms of disease diagnosis and identification, Zhu et al studied the brain function of autistic patients during related tasks through fNIRS (Zhu et al, 2015;Li and Yu, 2016;Vo et al, 2021); Li et al found that the HbO concentration in the region of interest changed sharply as the disease severity progressed from mild cognitive impairment to moderate/severe dementia (Li et al, 2018;Nakamura et al, 2021) specific brain regions in patients with schizophrenia and their clinical symptoms and functional results (Chou et al, 2020), facilitating clinical differentiation of schizophrenia, depression and bipolar disorder (Kumar et al, 2017). ( 5) fNIRS is also of great significance in the early diagnosis of AD (Perpetuini et al, 2019), since it can distinguish AD from normal aging based on functional connectivity (Tang and Chan, 2018), and can be used for AD screening with the help of refined PFC working memoryrelated networks (Kim et al, 2021). fNIRS revealed different patterns of activation in the frontoparietal cortex between AD and behavioral-subtype frontotemporal dementia (Metzger et al, 2016b), and showed more severe disruption of connectivity and frontal oxygenation changes in AD patients than in patients with mild cognitive impairment patients (Yeung and Chan, 2020), which can facilitate AD diagnosis and identification of disease progression.…”

Screening for Alzheimer's disease using prefrontal resting-state functional near-infrared spectroscopy

“…In the classification study, it was shown that there were significant correlations between cognitive functions and DLPFC in these patient groups (Yang and Hong, 2021 ). Properties of the functional connectivity network showed significant correlations with neuropsychological test scores and derived features achieved a high three-class classification accuracy (95.0%) (Kim et al, 2021 ). Another study used fNIRS and deep learning to distinguish not only between healthy and Alzheimer's afflicted subjects but also subjects with asymptomatic AD and dementia due to AD.…”