Insights into the Heterogeneity of Cognitive Aging: A Comparative Analysis of Two Data-Driven Clustering Algorithms.

IF 4.8 2区医学 Q1 GERIATRICS & GERONTOLOGY

Journals of Gerontology Series B-Psychological Sciences and Social Sciences Pub Date : 2025-02-13 DOI:10.1093/geronb/gbaf022

Truc Nguyen, Yu-Ling Chang

{"title":"Insights into the Heterogeneity of Cognitive Aging: A Comparative Analysis of Two Data-Driven Clustering Algorithms.","authors":"Truc Nguyen, Yu-Ling Chang","doi":"10.1093/geronb/gbaf022","DOIUrl":null,"url":null,"abstract":"Objectives: Cognitive aging entails diverse patterns of cognitive profiles, brain imaging, and biomarkers. Yet, few studies have explored the performance of multiple clustering algorithms on a single dataset. Here, we employ data-driven methods to analyze neuropsychological performance in older individuals with normal cognition (NC) and mild cognitive impairment (MCI).Methods: A total of 311 older adults without dementia completed a comprehensive assessment, consisting of 17 cognitive tests and a memory complaint questionnaire. We utilized two clustering algorithms: nonnegative matrix factorization (NMF) and model-based clustering (MBC). Cluster characteristics were examined in demographic, clinical, and brain morphometric data.Results: Both NMF and MBC uncovered two- and three-cluster solutions, with satisfactory data fit. The two-cluster profiles encompassed a cognitively intact (CI) group and a cognitively suboptimal (CS) group, distinguished by cognitive performance. The three-cluster solutions included CI-memory proficient, CI-nonmemory proficient, and CS groups. Remarkably, patterns of cognitive heterogeneity and their association with demographic and neuroimaging variables were highly comparable across NMF and MBC. Phenotypic homogeneity improved after identifying participants with consistent and mismatched memberships from the two algorithms.Discussion: The results indicate that two distinct data-driven algorithms, with different heuristics, generated comparable patterns regarding cognitive heterogeneity within NC and MCI. These findings may inform future subtyping studies in cognitive aging, where replication of stratifications found across different methods is strongly recommended.","PeriodicalId":56111,"journal":{"name":"Journals of Gerontology Series B-Psychological Sciences and Social Sciences","volume":" ","pages":""},"PeriodicalIF":4.8000,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journals of Gerontology Series B-Psychological Sciences and Social Sciences","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/geronb/gbaf022","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GERIATRICS & GERONTOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Objectives: Cognitive aging entails diverse patterns of cognitive profiles, brain imaging, and biomarkers. Yet, few studies have explored the performance of multiple clustering algorithms on a single dataset. Here, we employ data-driven methods to analyze neuropsychological performance in older individuals with normal cognition (NC) and mild cognitive impairment (MCI).

Methods: A total of 311 older adults without dementia completed a comprehensive assessment, consisting of 17 cognitive tests and a memory complaint questionnaire. We utilized two clustering algorithms: nonnegative matrix factorization (NMF) and model-based clustering (MBC). Cluster characteristics were examined in demographic, clinical, and brain morphometric data.

Results: Both NMF and MBC uncovered two- and three-cluster solutions, with satisfactory data fit. The two-cluster profiles encompassed a cognitively intact (CI) group and a cognitively suboptimal (CS) group, distinguished by cognitive performance. The three-cluster solutions included CI-memory proficient, CI-nonmemory proficient, and CS groups. Remarkably, patterns of cognitive heterogeneity and their association with demographic and neuroimaging variables were highly comparable across NMF and MBC. Phenotypic homogeneity improved after identifying participants with consistent and mismatched memberships from the two algorithms.

Discussion: The results indicate that two distinct data-driven algorithms, with different heuristics, generated comparable patterns regarding cognitive heterogeneity within NC and MCI. These findings may inform future subtyping studies in cognitive aging, where replication of stratifications found across different methods is strongly recommended.

查看原文本刊更多论文

洞察认知老化的异质性：两种数据驱动聚类算法的比较分析。

目的：认知衰老涉及认知谱、脑成像和生物标志物的多种模式。然而，很少有研究探讨多个聚类算法在单个数据集上的性能。在这里，我们采用数据驱动的方法来分析具有正常认知（NC）和轻度认知障碍（MCI）的老年人的神经心理学表现。方法：311名无痴呆的老年人完成了一项综合评估，包括17项认知测试和一份记忆抱怨问卷。我们使用了两种聚类算法：非负矩阵分解（NMF）和基于模型的聚类（MBC）。在人口统计学、临床和脑形态计量学数据中检查聚类特征。结果：NMF和MBC都得到了二聚类和三聚类的解，数据拟合满意。两组概况包括认知完整（CI）组和认知次优（CS）组，以认知表现区分。三组解决方案包括ci -内存精通组、ci -非内存精通组和CS组。值得注意的是，认知异质性模式及其与人口统计学和神经影像学变量的关联在NMF和MBC之间具有高度可比性。从两种算法中识别出具有一致和不匹配成员的参与者后，表型同质性得到改善。讨论：结果表明，两种不同的数据驱动算法，具有不同的启发式，在NC和MCI中产生了关于认知异质性的可比较模式。这些发现可能为未来的认知衰老亚型研究提供信息，在这些研究中，强烈推荐通过不同方法发现的分层复制。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journals of Gerontology Series B-Psychological Sciences and Social Sciences 医学-老年医学

CiteScore

11.60

自引率

8.10%

发文量

178

审稿时长

6-12 weeks

期刊介绍： The Journal of Gerontology: Psychological Sciences publishes articles on development in adulthood and old age that advance the psychological science of aging processes and outcomes. Articles have clear implications for theoretical or methodological innovation in the psychology of aging or contribute significantly to the empirical understanding of psychological processes and aging. Areas of interest include, but are not limited to, attitudes, clinical applications, cognition, education, emotion, health, human factors, interpersonal relations, neuropsychology, perception, personality, physiological psychology, social psychology, and sensation.