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: The FACEmemory® online platform comprises a complex memory test and sociodemographic, medical, and family questions. This is the first study of a completely self-administered memory test with voice recognition, pre-tested in a memory clinic, sensitive to Alzheimer's disease, using information and communication technologies, and offered freely worldwide. Objective: To investigate the demographic and clinical variables associated with the total FACEmemory score, and to identify distinct patterns of memory performance on FACEmemory. Methods: Data from the first 3,000 subjects who completed the FACEmemory test were analyzed. Descriptive analyses were applied to demographic, FACEmemory, and medical and family variables; t-test and chi-square analyses were used to compare participants with preserved versus impaired performance on FACEmemory (cut-off = 32); multiple linear regression was used to identify variables that modulate FACEmemory performance; and machine learning techniques were applied to identify different memory patterns. Results: Participants had a mean age of 50.57 years and 13.65 years of schooling; 64.07% were women, and 82.10% reported memory complaints with worries. The group with impaired FACEmemory performance (20.40%) was older, had less schooling, and had a higher prevalence of hypertension, diabetes, dyslipidemia, and family history of neurodegenerative disease than the group with preserved performance. Age, schooling, sex, country, and completion of the medical and family history questionnaire were associated with the FACEmemory score. Finally, machine learning techniques identified four patterns of FACEmemory performance: normal, dysexecutive, storage, and completely impaired. Conclusions: FACEmemory is a promising tool for assessing memory in people with subjective memory complaints and for raising awareness about cognitive decline in the community. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a neurodegenerative condition characterized by a gradual decline in cognitive functions. Currently, there are no effective treatments for AD, underscoring the importance of identifying individuals in the preclinical stages of mild cognitive impairment (MCI) to enable early interventions. Among the neuropathological events associated with the onset of the disease is the accumulation of amyloid protein in the brain, which correlates with decreased levels of Aβ42 peptide in the cerebrospinal fluid (CSF). Consequently, the development of non-invasive, low-cost, and easy-to-administer proxies for detecting Aβ42 positivity in CSF becomes particularly valuable. A promising approach to achieve this is spontaneous speech analysis, which combined with machine learning (ML) techniques, has proven highly useful in AD. In this study, we examined the relationship between amyloid status in CSF and acoustic features derived from the description of the Cookie Theft picture in MCI patients from a memory clinic. The cohort consisted of fifty-two patients with MCI (mean age 73 years, 65% female, and 57% positive amyloid status). Eighty-eight acoustic parameters were extracted from voice recordings using the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS), and several ML models were used to classify the amyloid status. Furthermore, interpretability techniques were employed to examine the influence of input variables on the determination of amyloid-positive status. The best model, based on acoustic variables, achieved an accuracy of 75% with an area under the curve (AUC) of 0.79 in the prediction of amyloid status evaluated by bootstrapping and Leave-One-Out Cross Validation (LOOCV), outperforming conventional neuropsychological tests (AUC = 0.66). Our results showed that the automated analysis of voice recordings derived from spontaneous speech tests offers valuable insights into AD biomarkers during the preclinical stages. These findings introduce novel possibilities for the use of digital biomarkers to identify subjects at high risk of developing AD. [ABSTRACT FROM AUTHOR]

The HapHop-Physio exer-learning game is a cognitive rehabilitation solution for children with learning disorders to train memory and attention functions. Therefore, HapHop-Physio must be assessed as an appropriate tool developed to support the enhancement of essential cognitive skills. In this paper, we aim to establish the validity of HapHop-Physio in a healthcare setting with children receiving training with this tool. HapHop-Physio was developed through interaction between clinical experts, one graphic designer, and game developers. Following an assessment framework for serious games in healthcare, the game's rationale, functionality, validity, and data safety are described. Particularly, the validity was assessed with experts through a case study conducted in three phases with 12 children diagnosed with Specific Learning Disorders. The baseline of the cognitive profile of the children was obtained and trained with HapHop-Physio. General trends and findings were obtained through an exploratory analysis of the gathered results from the phases. The validity aspects were achieved through continuous feedback from the experts, allowing to improve the game in five features: game structure, scoring system, avatars, login system, and clinicians' dashboard. The application of the assessment framework in HapHop-Physio guarantees end users that the game is safe and effective enough to be used for supporting memory and attention training. One relevant finding from the case study was that cognitive performance improved in 11 out of 12 children at the end of the training. The positive outcomes of this assessment indicate the game's appropriateness for a healthcare setting. However, the improvement in cognitive performance cannot be associated with HapHop-Physio in this case study. Consequently, it needs to be evaluated in a controlled experiment (including a control group) to ensure that it leads to cognitive rehabilitation in reality. [ABSTRACT FROM AUTHOR]

Background: Computerized neuropsychological tests for early detection of Alzheimer's disease (AD) have attracted increasing interest. Memory for faces and proper names is a complex task because its association is arbitrary. It implicates associative occipito-temporal cerebral regions, which are disrupted in AD. The short form of the Face-Name Associative Memory Exam (FNAME-12), developed to detect preclinical and prodromal AD, asks individuals to learn the names and occupations associated with 12 faces. The current work advances this field by using voice recognition and touchscreen response format. The purpose of this study is to create the first self-administered episodic memory test, FACEmemory®, by adapting the FNAME-12 for tablet use with voice recognition, touchscreen answers, and automatic scoring. The test was minimally supervised by a psychologist to avoid technological problems during execution and scored manually to assess the reliability of the automatic scoring. The aims of the present study were (1) to determine whether FACEmemory® is a sensitive tool for the detection of cognitive impairment, (2) to examine whether performances on FACEmemory® are correlated with those on the S-FNAME (paper-and-pencil version with 16 images), and (3) to determine whether performances on FACEmemory® are related to AD biomarkers in the cerebrospinal fluid (CSF) (Aβ42, p-tau, and Aβ42/p-tau ratio). Methods: FACEmemory® was completed by 154 cognitively healthy (CH) individuals and 122 subjects with mild cognitive impairment, of whom 61 were non-amnestic (naMCI) and 61 amnestic (aMCI). A subsample of 65 individuals completed the S-FNAME, and 65 subjects received lumbar punctures. Results: Performance on FACEmemory® was progressively worse from CH to the naMCI and aMCI groups. A cutoff of 31.5 in total FACEmemory® obtained 80.5% and 80.3% sensitivity and specificity values, respectively, for discriminating between CH and aMCI. Automatically corrected FACEmemory® scores were highly correlated with the manually corrected ones. FACEmemory® scores and AD CSF biomarker levels were significantly correlated as well, mainly in the aMCI group. Conclusions: FACEmemory® may be a promising memory prescreening tool for detecting subtle memory deficits related to AD. Our findings suggest FACEmemory® performance provides a useful gradation of impairment from normal aging to aMCI, and it is related to CSF AD biomarkers. [ABSTRACT FROM AUTHOR]

Individuals with subjective cognitive decline (SCD) have the perception of memory problems without showing impairment on standardized cognitive tests. SCD has been associated with an increased risk of developing Alzheimer's disease (AD). Neuroticism and openness personality dimensions have also been associated with SCD and AD. From the aforementioned, we aimed to ascertain whether the dimensions and traits defined by the Zuckerman-Kuhlman Personality Questionnaire (ZKPQ) differentiate between individuals with SCD and the general population (GP). A total of 187 participants with SCD and mild affective symptomatology recruited from the Fundació ACE Health Brain Initiative (FACEHBI) project completed the ZKPQ. Each SCD participant was matched by sex and age to an individual from the GP. Both samples included 71 men and 116 women with a mean age of 65.9 years. Results indicated that the SCD group scored significantly lower in Neuroticism-Anxiety and Activity than the GP group. Only Activity remained statistically significant in a multivariate analysis. These findings suggest that individuals with SCD have a low energy level and a dislike for an active and busy life. From the obtained results and knowing additional physical activities may delay the conversion from normal aging to cognitive impairment, we encourage promoting this lifestyle in daily routine. The assessment of personality may result in an SCD plus feature, which may serve as an upgrading strategy for future research. [ABSTRACT FROM AUTHOR]

Background: To determine whether performance on the Latin American Spanish version of the Face-Name Associative Memory Exam (LAS-FNAME) can differentiate between cognitively intact carriers of an autosomal dominant Alzheimer's disease mutation (E280A) in Presenilin-1, who are genetically determined to develop early-onset dementia, from matched non-carriers. We also sought to examine whether LAS-FNAME performance is associated with amyloid-β and regional tau burden in mutation carriers. Methods: A total of 35 cognitively intact mutation carriers (age range 26–41), 19 symptomatic carriers, and 48 matched non-carriers (age range 27–44) completed a neuropsychological assessment including the LAS-FNAME. A subset of participants (31 carriers [12 symptomatic] and 35 non-carriers) traveled from Colombia to Boston to undergo positron emission tomography (PET) using Pittsburgh compound B to measure mean cortical amyloid-β and flortaucipir for regional tau. ANOVA analyses and Spearman correlations were used to examine group differences and relationships among LAS-FNAME performance and amyloid-β and tau accumulation. Results: Compared to non-carriers, cognitively intact mutation carriers had lower scores on the LAS-FNAME Total Scores (p =.040). Across all carriers (including symptomatic carriers), higher levels of amyloid-β (r = −.436, p =.018) and regional tau in the entorhinal (r = −.394, p =.031) and inferior temporal cortex (r = −.563, p =.001) were associated with lower LAS-FNAME Total Scores. Conclusions: Performance on the LAS-FNAME differentiated between cognitively intact mutation carriers from non-carriers and was associated with greater amyloid and tau burden when examining all carriers. Findings suggest that the LAS-FNAME is sensitive to early clinical and pathological changes and can potentially help track disease progression in Spanish-speaking individuals. [ABSTRACT FROM AUTHOR]