Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Predicting CDR status over 36 months with a recall-based digital cognitive biomarker

Bruno, D, Jauregi Zinkunegi, A, Bock, JR and ADNI, (2024) Predicting CDR status over 36 months with a recall-based digital cognitive biomarker. Alzheimer's & Dementia: The Journal of the Alzheimer's Association. ISSN 1552-5260

[img]
Preview
Text
Predicting CDR status over 36 months with a recall-based digital cognitive biomarker.pdf - Published Version
Available under License Creative Commons Attribution.

Download (356kB) | Preview

Abstract

INTRODUCTION: Word-list recall tests are routinely employed for cognitive assessment. Process scoring and latent modeling of these tests have shown potential to enhance accuracy without requiring test redesign. We examined whether a set of process-based digital cognitive biomarkers (DCBs) at baseline predicted Clinical Dementia Rating (CDR) longitudinally, and how they compared to standard metrics. METHODS: Secondary data analyses were carried out with ADNI data. DCBs were derived from ADAS-Cog Word Recall test data. Participants were 330 (baseline mean age=71.4, SD=7.2). We conducted Bayesian and frequentist regression analyses using CDR at 36 months as outcome, controlled for demographics and genetic risk, and used ADAS-Cog traditional scores and DCBs as predictors. RESULTS: Across tests, the best predictor of CDR score at 36 months appeared to be M, a DCB reflecting recall ability. This metric outperformed traditional ADAS-Cog scores. Diagnostic results suggest that M may be particularly useful to identify true negatives, i.e., individuals who are unlikely to decline over the follow-up period. DISCUSSION: These results indicate that M, derived from word-list tests such as ADAS-Cog, may outperform some of the traditional metrics used for the purpose of identifying individuals who are at greater risk of disease progression. More research is needed, however, to determine these metrics’ applicability and sensitivity with other word-list tests and across diverse populations.

Item Type: Article
Uncontrolled Keywords: 1103 Clinical Sciences; 1109 Neurosciences; Geriatrics
Subjects: B Philosophy. Psychology. Religion > BF Psychology
Divisions: Psychology (from Sep 2019)
Publisher: Wiley
SWORD Depositor: A Symplectic
Date Deposited: 29 Jul 2024 15:41
Last Modified: 24 Sep 2024 10:30
DOI or ID number: 10.1002/alz.14213
URI: https://researchonline.ljmu.ac.uk/id/eprint/23811
View Item View Item