Allostatic Load as a Short-Term Prognostic and Predictive Marker.

It would be highly valuable to possess a tool for evaluating disease progression and identifying patients at risk of experiencing a more severe clinical course and potentially worse outcomes. The concept of allostatic load, which represents the overall strain on the body from repeated stress responses, has been recognized as a precursor to the development of chronic illnesses. It functions as a cumulative measure of the body's capacity to adapt to stress.

Biomarkers.

Background: Beyond dementia syndromes, cognitive symptoms are highly prevalent in Parkinson's disease (PD), often manifesting as mild cognitive impairment (MCI). Yet, their detection and characterization remain suboptimal because standard approaches rely on subjective impressions derived from lengthy, univariate tests. Here we introduce a novel approach to detect cognitive symptom severity and identify MCI in PD using fully automated word property analyses on brief verbal fluency tasks.

Biomarkers.

Background: Dementia impacts the way individuals perceive and describe everyday events. Alzheimer's disease (AD) notably affects processing of entities manifested by nouns, while behavioral variant frontotemporal dementia (bvFTD) often presents a detached, third-person perspective. Yet, the potential of natural language processing tools (NLP) to detect these variations in spontaneous speech remains explored.

Biomarkers.

Background: Digital health research on Alzheimer's disease (AD) points to automated speech and language analysis (ASLA) as a globally scalable approach for diagnosis and monitoring. However, most studies target uninterpretable features in Anglophone samples, casting doubts on the approach's clinical utility and cross-linguistic validity. The present study was designed to tackle both issues.

Biomarkers.

Background: Verbal fluency tasks are routinely employed in screening for mild cognitive impairment (MCI). Yet, traditional outcome measures focus on the number of valid responses, failing to reveal which specific semantic memory dimensions may be altered and limiting analyses to univariate methods. Building on recent findings on Alzheimer's disease, we employed automated methods to establish which linguistic and speech timing features better discriminate MCI patients from healthy controls (HCs), including machine learning analyses, comparisons with standard neuropsychological tests, and brain-behavior correlations.