AUTHOR=Xu Xiaowen , Chen Peiying , Xiang Yongsheng , Xie Zhongfeng , Yu Qiang , Zhou Xiang , Wang Peijun 

TITLE=Altered pattern analysis and identification of subjective cognitive decline based on morphological brain network

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 14 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2022.965923

DOI=10.3389/fnagi.2022.965923

ISSN=1663-4365

ABSTRACT=Subjective cognitive decline (SCD) is considered as the first stage of Alzheimer’s Disease with subtle cognitive decline. Accurate diagnosis and pathological mechanism exploration of SCD is of great value for targeted AD prevention. However, there is little knowledge on the specific altered morphological network patterns in SCD individuals. In this present study, 36 SCD cases and 34 paired-matched normal control (NC) were recruited. The Jensen-Shannon distance-based similarity (JSS) method was implemented to construct and derive the attributes of multiple brain connectomes (i.e., morphological brain connections, and global and nodal graph metrics) of individual morphological brain networks. The t-test was used to discriminate between the selected nodal graph metrics, while the Leave-One-Out Cross-Validation (LOOCV) was used to obtain consensus connections. Comparisons were performed to explore the altered patterns of connectome features. Further, the multiple kernel support vector machine (MK-SVM) was used for combining brain connectomes and differentiating SCD from NCs. We found that the consensus connections and the nodal graph metrics with the most discriminative ability were mostly found in the frontal, limbic and parietal lobes, corresponding to the default mode network (DMN) and fronto-parietal task control (FTC) network. Altered pattern analysis demonstrated that SCD cases had a tendency for modularity as well as local efficiency enhancement. In addition, using the MK-SVM to combine the features of multiple brain connectomes was associated with optimal classification performance (AUC:0.9510, sensitivity:97.22%, specificity:85.29% and accuracy:91.43%). Therefore, our study highlighted the combination of multiple connectome attributes based on morphological brain networks offered a valuable method for distinguishing SCD individuals from NCs. Meanwhile, the altered patterns of multi-dimensional connectome attributes provided a promising approach for insight into the neuroimaging mechanism and early intervention of SCD subjects.