Abstract
ObjectiveIndividuals with subjective cognitive decline (SCD) or amnestic mild cognitive impairment (aMCI) represent important targets for the early detection and intervention of Alzheimer’s disease (AD). In this study, we employed a multi-kernel support vector machine (SVM) to examine whether white matter (WM) structural networks can be used for screening SCD and aMCI.MethodsA total of 138 right-handed participants [51 normal controls (NC), 36 SCD, 51 aMCI] underwent MRI brain scans. For each participant, three types of WM networks with different edge weights were constructed with diffusion MRI data: fiber number-weighted networks, mean fractional anisotropy-weighted networks, and mean diffusivity (MD)-weighted networks. By employing a multiple-kernel SVM, we seek to integrate information from three weighted networks to improve classification performance. The accuracy of classification between each pair of groups was evaluated via leave-one-out cross-validation.ResultsFor the discrimination between SCD and NC, an area under the curve (AUC) value of 0.89 was obtained, with an accuracy of 83.9%. Further analysis revealed that the methods using three types of WM networks outperformed other methods using single WM network. Moreover, we found that most of discriminative features were from MD-weighted networks, which distributed among frontal lobes. Similar classification performance was also reported in the differentiation between subjects with aMCI and NCs (accuracy = 83.3%). Between SCD and aMCI, an AUC value of 0.72 was obtained, with an accuracy of 72.4%, sensitivity of 74.5% and specificity of 69.4%. The highest accuracy was achieved with features only selected from MD-weighted networks.ConclusionWhite matter structural network features help machine learning algorithms accurately identify individuals with SCD and aMCI from NCs. Our findings have significant implications for the development of potential brain imaging markers for the early detection of AD.
Highlights
Subjective cognitive decline (SCD) refers to self-perceived cognitive decline relative to a previously normal status, without impaired performance on standardized neuropsychological tests (Jessen et al, 2014; Molinuevo et al, 2017)
Examination (MMSE), Montreal Cognitive Assessment (MoCA), Auditory Verbal Learning Test (AVLT); (c) a Clinical Dementia Rating (CDR) score of 0.5; (d) did not fulfill the criteria for dementia according to the Diagnostic and Statistical Manual of Mental Disorders, fourth edition, revised (DSM-IV); and (e) hippocampal atrophy observed by structural MRI
The proposed multiple kernel SVM-based multi-weight network approach achieved a classification accuracy of 83.9%, with a sensitivity of 77.8% and a specificity of 88.2% in the discrimination between normal controls (NCs) subjects and SCD subjects
Summary
Subjective cognitive decline (SCD) refers to self-perceived cognitive decline relative to a previously normal status, without impaired performance on standardized neuropsychological tests (Jessen et al, 2014; Molinuevo et al, 2017). Using DTI measures, previous studies observed WM abnormalities in SCD subjects compared with the normal control (NC) group (Selnes et al, 2012; Li et al, 2016). Such alterations may predict medial temporal lobe atrophy and dementia (Selnes et al, 2013). Previous studies suggested that patients with SCD and MCI exhibit global disruption of brain connectivity and topologic alterations of the whole-brain connectome rather than in a single isolated region (Shu et al, 2012, 2018). The topographical metrics of patients with SCD and MCI correlating with impaired cognitive performance suggest their potential use as biomarkers for the early detection of cognitive impairment in elderly individuals
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
