Detection of Cognitive Impairment through Spontaneous Speech Acoustic Markers Using Transformer‐based Machine Learning Approach.

Background: The increasing prevalence of cognitive impairment and dementia threatens global health, necessitating the development of accessible tools for detection of cognitive impairment. This study explores using a transformer‐based approach to detect cognitive impairment using acoustic markers of spontaneous speech.

Method: Recordings of unstructured interviews from baseline visits were obtained from participants of The 90+ Study, a longitudinal study of individuals older than 90 years.

Transformer‐based Deep Learning Architecture Improves Detection of Associations between Spontaneous Speech Language Markers and Cognition.

Background: Spontaneous speech is easily obtainable and has the potential to become an accessible and low‐cost marker for cognitive function. The time‐consuming and labor‐intensive nature of speech analysis has been a major obstacle to utilizing this promising tool. This study uses a novel transformer‐based methodology to explore associations between spontaneous speech language features and global cognition.

The potential of plasma TDP‐43 as a biomarker for limbic predominant age related TDP‐43 encephalopathy.

Background: Despite recent advances in biomarkers discovery for neurodegenerative diseases, there are currently no in vivo biomarkers for limbic‐predominant age‐related TDP‐43 encephalopathy (LATE‐NC). A few studies have suggested that plasma TDP‐43 can be an in vivo marker of frontotemporal dementia due to TDP‐43 pathology and amyotrophic lateral sclerosis. In this pilot study, we aimed to assess plasma TDP‐43 concentrations as a biomarker in individuals with autopsy confirmed LATE‐NC.

Characterizing Limbic-Predominant Age-Related TDP-43 Encephalopathy Without Alzheimer's Disease and Lewy Body Dementia in the Oldest Old: A Case Series.

Background: Limbic-predominant age-related TDP-43 encephalopathy neuropathologic change (LATE-NC) is a clinicopathological construct proposed to facilitate studying TDP-43 pathology in older individuals.

Objective: Our aim was to describe clinical and cognitive characteristics of LATE-NC without Alzheimer's disease neuropathologic change (ADNC) and Lewy body (LB) and to compare this with ADNC and primary age related tauopathy (PART).

Methods: In 364 autopsies of the oldest old of The 90+ Study, we identified those with LATE-NC without ADNC and LB.