Automated detection of mild cognitive impairment and dementia from voice recordings: A natural language processing approach.

Alzheimers Dement

Department of Electrical & Computer Engineering, Division of Systems Engineering, and Department of Biomedical Engineering, Boston University, Boston, Massachusetts, USA.

Published: March 2023

Introduction: Automated computational assessment of neuropsychological tests would enable widespread, cost-effective screening for dementia.

Methods: A novel natural language processing approach is developed and validated to identify different stages of dementia based on automated transcription of digital voice recordings of subjects' neuropsychological tests conducted by the Framingham Heart Study (n = 1084). Transcribed sentences from the test were encoded into quantitative data and several models were trained and tested using these data and the participants' demographic characteristics.

Results: Average area under the curve (AUC) on the held-out test data reached 92.6%, 88.0%, and 74.4% for differentiating Normal cognition from Dementia, Normal or Mild Cognitive Impairment (MCI) from Dementia, and Normal from MCI, respectively.

Discussion: The proposed approach offers a fully automated identification of MCI and dementia based on a recorded neuropsychological test, providing an opportunity to develop a remote screening tool that could be adapted easily to any language.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10148688PMC
http://dx.doi.org/10.1002/alz.12721DOI Listing

Publication Analysis

Top Keywords

mild cognitive
8
cognitive impairment
8
voice recordings
8
natural language
8
language processing
8
processing approach
8
neuropsychological tests
8
dementia based
8
dementia normal
8
mci dementia
8

Similar Publications

Background: Rimegepant, a novel oral calcitonin gene-related peptide receptor antagonist, has been recently approved for the acute migraine treatment. While its efficacy was confirmed in randomized clinical trials, no data is available regarding real-life effectiveness and tolerability. GAINER, a prospective, multicentric study, aimed to evaluate rimegepant effectiveness and tolerability in the real-world setting.

View Article and Find Full Text PDF

Objective: The Clarity AD phase III trial showed that lecanemab reduced amyloid markers in early Alzheimer's disease (AD) and resulted in less decline on measures of cognition and function than placebo. Herein, we aimed to characterize amyloid-β (Aβ) protofibril (PF) captured by lecanemab in human cerebrospinal fluid (CSF) from living participants with different stages in AD, which enable an enhanced understanding of the dynamic changes of lecanemab-associated Aβ-PF (Lec-PF) in vivo.

Methods: We newly developed a unique and highly sensitive immunoassay method using lecanemab that selectively captures Lec-PF.

View Article and Find Full Text PDF

Background: White matter hyperintensities (WMH) have been implicated in the pathogenesis of neuropsychiatric symptoms of dementia but the functional significance of WMH in specific white matter (WM) tracts is unclear. We investigate whether WMH burden within major WM fibre classes and individual WM tracts are differentially associated with different neuropsychiatric syndromes in a large multicentre study.

Method: Neuroimaging and neuropsychiatric data of seven memory clinic cohorts through the Meta VCI Map consortium were harmonised.

View Article and Find Full Text PDF

Objective: Older adults have an increased risk of developing persistent cognitive complaints after mild traumatic brain injury (mTBI). Yet, studies exploring which factors protect older adults with mTBI from developing such complaints are rare. It has been suggested that one such factor may be cognitive reserve (CR), but it is unknown how CR influences cognition in this patient category.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!