Search

Background: Advancement in screening tools accessible to the general population for the early detection of Alzheimer's disease (AD) and prediction of its progression is essential for achieving timely therapeutic interventions and conducting decentralized clinical trials. This study delves into the application of Machine Learning (ML) techniques by leveraging paralinguistic features extracted directly from a brief spontaneous speech (SS) protocol. We aimed to explore the capability of ML techniques to discriminate between different degrees of cognitive impairment based on SS. Furthermore, for the first time, this study investigates the relationship between paralinguistic features from SS and cognitive function within the AD spectrum. Methods: Physical-acoustic features were extracted from voice recordings of patients evaluated in a memory unit who underwent a SS protocol. We implemented several ML models evaluated via cross-validation to identify individuals without cognitive impairment (subjective cognitive decline, SCD), with mild cognitive impairment (MCI), and with dementia due to AD (ADD). In addition, we established models capable of predicting cognitive domain performance based on a comprehensive neuropsychological battery from Fundació Ace (NBACE) using SS-derived information. Results: The results of this study showed that, based on a paralinguistic analysis of sound, it is possible to identify individuals with ADD (F1 = 0.92) and MCI (F1 = 0.84). Furthermore, our models, based on physical acoustic information, exhibited correlations greater than 0.5 for predicting the cognitive domains of attention, memory, executive functions, language, and visuospatial ability. Conclusions: In this study, we show the potential of a brief and cost-effective SS protocol in distinguishing between different degrees of cognitive impairment and forecasting performance in cognitive domains commonly affected within the AD spectrum. Our results demonstrate a high correspondence with protocols traditionally used to assess cognitive function. Overall, it opens up novel prospects for developing screening tools and remote disease monitoring. [ABSTRACT FROM AUTHOR]

Background: Alzheimer's disease (AD) diagnosis relies on clinical symptoms complemented with biological biomarkers, the Amyloid Tau Neurodegeneration (ATN) framework. Small non-coding RNA (sncRNA) in the blood have emerged as potential predictors of AD. We identified sncRNA signatures specific to ATN and AD, and evaluated both their contribution to improving AD conversion prediction beyond ATN alone. Methods: This nested case–control study was conducted within the ACE cohort and included MCI patients matched by sex. Patients free of type 2 diabetes underwent cerebrospinal fluid (CSF) and plasma collection and were followed-up for a median of 2.45-years. Plasma sncRNAs were profiled using small RNA-sequencing. Conditional logistic and Cox regression analyses with elastic net penalties were performed to identify sncRNA signatures for A+(T|N)+ and AD. Weighted scores were computed using cross-validation, and the association of these scores with AD risk was assessed using multivariable Cox regression models. Gene ontology (GO) and Kyoto encyclopaedia of genes and genomes (KEGG) enrichment analysis of the identified signatures were performed. Results: The study sample consisted of 192 patients, including 96 A+(T|N)+ and 96 A-T-N- patients. We constructed a classification model based on a 6-miRNAs signature for ATN. The model could classify MCI patients into A-T-N- and A+(T|N)+ groups with an area under the curve of 0.7335 (95% CI, 0.7327 to 0.7342). However, the addition of the model to conventional risk factors did not improve the prediction of AD beyond the conventional model plus ATN status (C-statistic: 0.805 [95% CI, 0.758 to 0.852] compared to 0.829 [95% CI, 0.786, 0.872]). The AD-related 15-sncRNAs signature exhibited better predictive performance than the conventional model plus ATN status (C-statistic: 0.849 [95% CI, 0.808 to 0.890]). When ATN was included in this model, the prediction further improved to 0.875 (95% CI, 0.840 to 0.910). The miRNA-target interaction network and functional analysis, including GO and KEGG pathway enrichment analysis, suggested that the miRNAs in both signatures are involved in neuronal pathways associated with AD. Conclusions: The AD-related sncRNA signature holds promise in predicting AD conversion, providing insights into early AD development and potential targets for prevention. [ABSTRACT FROM AUTHOR]