Assessing Cognitive Features of Dementia Progression for Different Dementia Levels using Feature Selection

Author:

Thabtah Fadi1,Peebles David2

Affiliation:

1. ASD Tests

2. University of Huddersfield

Abstract

AbstractPurposeDementia is a condition with symptoms of memory decline, cognitive impairment, and difficulties in language and problem-solving, among others. Early screening of dementia conditions such as Alzheimer’s disease (AD) is fundamental for quick intervention, and disease management. Currently used neuropsychological assessments are either time-consuming, invasive require scarce resources, and often not cost effective. Therefore, identifying cognitive features for different dementia sub-groups during the condition’s progression is crucial. This study uses a cost-effective data driven approach to determine whether neuropsychological items change from one stage of dementia to another.MethodsUsing real cases and controls from the Alzheimer’s Disease Neuroimaging Initiative data repository (ADNI) who undertook the Alzheimer’s Disease Assessment Scale-Cognitive 13 (ADAS-Cog), we conducted a feature-feature assessment to derive influential cognitive features for specific dementia groups from baseline diagnosis up to 36 months.ResultsThe results reveal non-overlapping features (‘command’, ‘naming of objects’, and ‘ideational praxis’) from participants who had a baseline diagnosis of Cognitively Normal (CN) and progressed to AD. In addition, overlapping of cognitive elements was observed for Mild Cognitive Impairment (MCI) subjects who advanced to AD.ConclusionThis study revealed influential cognitive subsets that are uniquely associated with certain dementia stages. The overlapping of features in groups that remained in mild cognitive impairment or progressed to light dementia argues against separating these groups on these features. Other features (e.g., ‘spoken language’ and ‘word recognition’ in the ‘Cog-MCI-AD’ sub-group) showed much less correlation, indicating that these should be investigated further when assessing patients with MCI.

Publisher

Research Square Platform LLC

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3