AUTHOR=Feng Qi , Wang Luoyu , Tang Xue , Ge Xiuhong , Hu Hanjun , Liao Zhengluan , Ding Zhongxiang 

TITLE=Machine learning classifiers and associations of cognitive performance with hippocampal subfields in amnestic mild cognitive impairment

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 15 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2023.1273658

DOI=10.3389/fnagi.2023.1273658

ISSN=1663-4365

ABSTRACT=Neuroimaging studies have shown that the demonstrated alterations in hippocampal volume of hippocampus and hippocampal subfields changes in theamong individuals with amnestic mild cognitive impairment (aMCI) population.). However, there are relatively few studiesresearch on using hippocampal subfield volume modeling used to distinguishdifferentiate aMCI from normal2 This is a provisional file, not the final typeset article controls (NCs),) is limited, and the relationship between hippocampal volume and overall cognitive scorescores remains to be clarifiedunclear.For this target, we recruitedWe enrolled 50 subjects with aMCI and 44 NCs. First, for this study. Initially, a univariate general linear model was usedemployed to analyze the volume differences in the volumes of hippocampal subfield. Thensubfields. Subsequently, two groupssets of four dimensionality reduction methods and four machine learning methodstechniques were used for distinguishingapplied to distinguish aMCI and NCfrom NCs based on the hippocampal subfields volumesubfield volumes. Finally, we assessed the correlation between the relative volumevolumes of hippocampal subfields and cognitive test variables (Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment Scale (MoCA)) was analyzed respectively. ).The Significant volume differences were observed in several hippocampal subfields, notably in the left hippocampus. Specifically, the volumes of the hippocampal tail, subiculum, CA1, presubiculum, molecular layer, GC-ML-DG, CA3, CA4, and fimbria werediffered significantly different between the two groups, especially in the left hippocampus. . The highest area under the curve (AUC) value in thevalues for left and right hippocampal machine learning classifiers waswere 0.678 and 0.701, respectively. The volume Moreover, the volumes of the left subiculum, left molecular layer, right subiculum, right CA1, right molecular layer, right GC-ML-DG, and right CA4 wasexhibited the strongest and most strongly and actively correlatedconsistent correlations with MoCA scores.The Hippocampal subfield volume may serve as a predictive marker for aMCI. These findings underscore the sensitivity of hippocampal subfield may be a predictor of aMCI. The results suggest that the volume of hippocampal subfield plays a sensitive role into overall cognitive performance.