Unveiling the sound of the cognitive status: Machine Learning-based speech analysis in the Alzheimer's disease spectrum.

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.

Genome-wide association study and polygenic risk scores of retinal thickness across the cognitive continuum: data from the NORFACE cohort.

BACKGROUND: Several studies have reported a relationship between retinal thickness and dementia. Therefore, optical coherence tomography (OCT) has been proposed as an early diagnosis method for Alzheimer's disease (AD). In this study, we performed a genome-wide association study (GWAS) aimed at identifying genes associated with retinal nerve fiber layer (RNFL) and ganglion cell inner plexiform layer (GCIPL) thickness assessed by OCT and exploring the relationships between the spectrum of cognitive decline (including AD and non-AD cases) and retinal thickness. METHODS: RNFL and GCIPL thickness at the macula were determined using two different OCT devices (Triton and Maestro). These determinations were tested for association with common single nucleotide polymorphism (SNPs) using adjusted linear regression models and combined using meta-analysis methods. Polygenic risk scores (PRSs) for retinal thickness and AD were generated. RESULTS: Several genetic loci affecting retinal thickness were identified across the genome in accordance with previous reports. The genetic overlap between retinal thickness and dementia, however, was weak and limited to the GCIPL layer; only those observable with all-type dementia cases were considered. CONCLUSIONS: Our study does not support the existence of a genetic link between dementia and retinal thickness.

Focusing on Earlier Management of Alzheimer Disease: Expert Opinion Based on a Modified Nominal Group Technique.

BACKGROUND: Despite the number of people living with Alzheimer disease (AD), awareness of the early stages of this condition, including mild cognitive impairment due to AD-which poses management challenges-continues to be low. To identify areas for improvement in early AD management, dementia specialists convened in a virtual roundtable meeting. METHODOLOGY: A modified version of the nominal group technique was followed to prioritize specific topics and allow experts to provide their opinions. The overarching topics prioritized and discussed were (1) education and support for primary care physicians on cognitive assessment, detection of mild cognitive impairment, and patient monitoring; (2) nonpharmacological interventions; (3) and the introduction of disease-modifying therapies. CONCLUSIONS: Consensus was achieved regarding the need for educating primary care physicians on identifying people with cognitive impairment and for better diagnostic tools for its detection and early management. Management of mild cognitive impairment due to AD should encompass an adequate follow-up schedule aiming to maintain function for as long as possible, and primary care physicians and patients should be aware of the benefits of nonpharmacological interventions.

Macular vessel density in the superficial plexus is not a proxy of cerebrovascular damage in non-demented individuals: data from the NORFACE cohort.

INTRODUCTION: Optical coherence tomography angiography (OCT-A) is a novel tool that allows the detection of retinal vascular changes. We investigated the association of macular vessel density (VD) in the superficial plexus assessed by OCT-A with measures of cerebrovascular pathology and atrophy quantified by brain magnetic resonance imaging (MRI) in non-demented individuals. METHODS: Clinical, demographical, OCT-A, and brain MRI data from non-demented research participants were included. We analyzed the association of regional macular VD with brain vascular burden using the Fazekas scale assessed in a logistic regression analysis, and the volume of white matter hyperintensities (WMH) assessed in a multiple linear regression analysis. We also explored the associations of macular VD with hippocampal volume, ventricle volume and Alzheimer disease cortical signature (ADCS) thickness assessed in multiple linear regression analyses. All analyses were adjusted for age, sex, syndromic diagnosis and cardiovascular variables. RESULTS: The study cohort comprised 188 participants: 89 with subjective cognitive decline and 99 with mild cognitive impairment. No significant association of regional macular VD with the Fazekas categories (all, p > 0.111) and WMH volume (all, p > 0.051) were detected. VD in the nasal quadrant was associated to hippocampal volume (p = 0.007), but no other associations of macular VD with brain atrophy measures were detected (all, p > 0.05). DISCUSSION: Retinal vascular measures were not a proxy of cerebrovascular damage in non-demented individuals, while VD in the nasal quadrant was associated with hippocampal atrophy independently of the amyloid status.

FACEmemory®, an Innovative Online Platform for Episodic Memory Pre-Screening: Findings from the First 3,000 Participants.

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.

Harnessing acoustic speech parameters to decipher amyloid status in individuals with mild cognitive impairment.

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 Aß42 peptide in the cerebrospinal fluid (CSF). Consequently, the development of non-invasive, low-cost, and easy-to-administer proxies for detecting Aß42 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.

Automated Classification of Cognitive Decline and Probable Alzheimer's Dementia Across Multiple Speech and Language Domains.

BACKGROUND: Decline in language has emerged as a new potential biomarker for the early detection of Alzheimer's disease (AD). It remains unclear how sensitive language measures are across different tasks, language domains, and languages, and to what extent changes can be reliably detected in early stages such as subjective cognitive decline (SCD) and mild cognitive impairment (MCI). METHOD: Using a scene construction task for speech elicitation in a new Spanish/Catalan speaking cohort (N = 119), we automatically extracted features across seven domains, three acoustic (spectral, cepstral, and voice quality), one prosodic, and three from text (morpholexical, semantic, and syntactic). They were forwarded to a random forest classifier to evaluate the discriminability of participants with probable AD dementia, amnestic and nonamnestic MCI, SCD, and cognitively healthy controls. Repeated-measures analyses of variance and paired-samples Wilcoxon signed-ranks test were used to assess whether and how performance differs significantly across groups and linguistic domains. RESULTS: The performance scores of the machine learning classifier were generally satisfactorily high, with the highest scores over .9. Model performance was significantly different for linguistic domains (p < .001), and speech versus text (p = .043), with speech features outperforming textual features, and voice quality performing best. High diagnostic classification accuracies were seen even within both cognitively healthy (controls vs. SCD) and MCI (amnestic and nonamnestic) groups. CONCLUSION: Speech-based machine learning is powerful in detecting cognitive decline and probable AD dementia across a range of different feature domains, though important differences exist between these domains as well. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.23699733.

Cognitive and Motor Decline in Dementia with Lewy Bodies and Parkinson's Disease Dementia.

Background: There is a need to better understand the rate of cognitive and motor decline of Dementia with Lewy bodies (DLB) and Parkinson's disease Dementia (PDD). Objectives: To compare the rate of cognitive and motor decline in patients with DLB and PDD from the E-DLB Consortium and the Parkinson's Incidence Cohorts Collaboration (PICC) Cohorts. Methods: The annual change in MMSE and MDS-UPDRS part III was estimated using linear mixed regression models in patients with at least one follow-up (DLB n = 837 and PDD n = 157). Results: When adjusting for confounders, we found no difference in the annual change in MMSE between DLB and PDD (-1.8 [95% CI -2.3, -1.3] vs. -1.9 [95% CI -2.6, -1.2] [P = 0.74]). MDS-UPDRS part III showed nearly identical annual changes (DLB 4.8 [95% CI 2.1, 7.5]) (PDD 4.8 [95% CI 2.7, 6.9], [P = 0.98]). Conclusions: DLB and PDD showed similar rates of cognitive and motor decline. This is relevant for future clinical trial designs.

A randomized, open-label clinical trial in mild cognitive impairment with EGb 761 examining blood markers of inflammation and oxidative stress.

Although beta-amyloid (Aß) and phosphorylated tau remain the preferred targets for disease-modifying treatments (DMT) against Alzheimer's disease (AD), part of the pathophysiological mechanisms of cognitive impairment are related to neuroinflammation and oxidative stress. In mild cognitive impairment (MCI), a prodromal stage of AD and other neurodegenerative conditions, the joint appearance of inflammation, oxidative stress, and metabolic alterations are the common pathways of neurotoxicity and neurodegeneration. The standardized extract of Ginkgo biloba EGb 761 interferes with the pathogenic mechanisms involved in both the development of cognitive impairment due to AD and that of vascular origin. The primary objective of this study is to compare changes in the levels of blood markers of inflammation and oxidative stress after treatment with EGb 761 in a cohort of 100 patients with MCI. In addition, we aim to assess changes in these blood markers during an additional 12-month extension phase in which patients in the control group will also receive EGb 761 and patients in the active group will extend their treatment duration. Secondary objectives include comparing changes in neuropsychiatric and cognitive test scores between the baseline (v0) and 12-month visits (v2). This study is a Phase IV, single-center, randomized, open-label, parallel-group clinical trial consisting of the 12-month follow-up of a cohort of participants with MCI [Global Deterioration Scale (GDS) = 3] and an extension with an additional 12-month follow-up. During the first 12 months, participants will be randomized into two arms: in one arm, patients will receive 1 daily tablet of EGb 761 240 mg orally (study group, n = 50), while in the other arm, patients will not receive EGb 761 and will undergo the same assessments as the treated group (control group, n = 50). After the first 12 months of the study, patients in the EGb 761-treated group will continue treatment, and patients in the control group will be offered one EGb 761 240 mg tablet per day orally. All participants will be monitored for an additional 12 months. A battery of blood markers of inflammation and oxidative stress will be quantified at v0, v1, v2, v3, and v4. The Olink Proteomics panel of inflammation markers ( https://www.olink.com/products/inflammation/ ) will be used to evaluate 92 proteins associated with inflammatory diseases and related biological processes. The second panel measures 92 proteins involved in neurological processes. At v0, v2, and v4, neuropsychological and neurological evaluations will be conducted in addition to vital signs and anthropometric studies using a body composition monitor with bioimpedance technology (Tanita). Sixty percent of the 100 MCI patients recruited were women. The mean age was 73.1 years, and the mean time between symptom onset and MCI diagnosis was 2.9 years. The mean Mini-Mental State Examination (MMSE) score was 26.7. Depressive and anxiety disorders, as well as vascular risk factors, were the most frequent comorbidities among the cohort. The study is still ongoing, and results for the first year of treatment (v0, v1, v2) are expected by 2023. Individuals with MCI have an elevated risk of developing dementia. EGb 761 is used worldwide for the symptomatic treatment of cognitive disorders due to its neuroprotective effects. In experimental models and clinical observational studies, EGb 761 has shown strong antioxidant and anti-inflammatory activity. As a result, this study has been proposed to evaluate the antioxidant and anti-inflammatory effects on plasma markers and their potential clinical correlation with the progression of cognitive decline in patients with MCI.Trial registration: Registro Español de estudios clínicos (REec) number 2020-003776-41, ClinicalTrials.gov Identifier: NCT05594355.

Macular vessel density in the superficial plexus is not associated to cerebrospinal fluid core biomarkers for Alzheimer's disease in individuals with mild cognitive impairment: The NORFACE cohort.

Background: Optical coherence tomography angiography (OCT-A) is a novel method in the dementia field that allows the detection of retinal vascular changes. The comparison of OCT-A measures with established Alzheimer's disease (AD)-related biomarkers is essential to validate the former as a marker of cerebrovascular impairment in the AD continuum. We aimed to investigate the association of macular vessel density (VD) in the superficial plexus quantified by OCT-A with the AT(N) classification based on cerebrospinal fluid (CSF) Aß1-42, p181-tau and t-tau measurements in individuals with mild cognitive impairment (MCI). Materials and methods: Clinical, demographic, ophthalmological, OCT-A and CSF core biomarkers for AD data from the Neuro-ophthalmology Research at Fundació ACE (NORFACE) project were analyzed. Differences in macular VD in four quadrants (superior, nasal, inferior, and temporal) among three AT(N) groups [Normal, Alzheimer and Suspected non-Alzheimer pathology (SNAP)] were assessed in a multivariate regression model, adjusted for age, APOE ε4 status, hypertension, diabetes mellitus, dyslipidemia, heart disease, chronic obstructive pulmonary disease and smoking habit, using the Normal AT(N) group as the reference category. Results: The study cohort comprised 144 MCI participants: 66 Normal AT(N), 45 Alzheimer AT(N) and 33 SNAP AT(N). Regression analysis showed no significant association of the AT(N) groups with any of the regional macular VD measures (all, p > 0.16). The interaction between sex and AT(N) groups had no effect on differentiating VD. Lastly, CSF Aß1-42, p181-tau and t-tau measures were not correlated to VD (all r < 0.13; p > 0.13). Discussion: Our study showed that macular VD measures were not associated with the AT(N) classification based on CSF biomarkers in patients with MCI, and did not differ between AD and other underlying causes of cognitive decline in our cohort.

The Synergic Effect of AT(N) Profiles and Depression on the Risk of Conversion to Dementia in Patients with Mild Cognitive Impairment.

Few studies have addressed the impact of the association between Alzheimer's disease (AD) biomarkers and NPSs in the conversion to dementia in patients with mild cognitive impairment (MCI), and no studies have been conducted on the interaction effect of these two risk factors. AT(N) profiles were created using AD-core biomarkers quantified in cerebrospinal fluid (CSF) (normal, brain amyloidosis, suspected non-Alzheimer pathology (SNAP) and prodromal AD). NPSs were assessed using the Neuropsychiatric Inventory Questionnaire (NPI-Q). A total of 500 individuals with MCI were followed-up yearly in a memory unit. Cox regression analysis was used to determine risk of conversion, considering additive and multiplicative interactions between AT(N) profile and NPSs on the conversion to dementia. A total of 224 participants (44.8%) converted to dementia during the 2-year follow-up study. Pathologic AT(N) groups (brain amyloidosis, prodromal AD and SNAP) and the presence of depression and apathy were associated with a higher risk of conversion to dementia. The additive combination of the AT(N) profile with depression exacerbates the risk of conversion to dementia. A synergic effect of prodromal AD profile with depressive symptoms is evidenced, identifying the most exposed individuals to conversion among MCI patients.

Differences in macular vessel density in the superficial plexus across cognitive impairment: the NORFACE cohort.

Optical coherence tomography angiography (OCT-A) allows the detection of retinal vessel density (VD) loss, which is a reflection of brain vascular pathology. We aimed to investigate differences in macular VD in the superficial plexus in a large cohort of individuals cognitively unimpaired (CU), with mild cognitive impairment due to Alzheimer´s disease (MCI-AD), MCI due to cerebrovascular pathology (MCI-Va), probable Alzheimer´s disease dementia (ADD) and Vascular Dementia (VaD). Clinical, demographical, ophthalmological and OCT-A data from the Neuro-ophthalmology Research at Fundació ACE (NORFACE) project were analyzed. Differences of macular VD in four quadrants (superior, nasal, inferior and temporal) among the five diagnostic groups were assessed in a multivariate regression model, adjusted by age, sex, education, hypertension, diabetes mellitus, heart disease and stroke. The study cohort comprised 672 participants: 128 CU, 120 MCI-AD, 111 MCI-Va, 257 ADD and 56 VaD. Regression analysis showed a significantly higher VD in the temporal quadrant in MCI-AD compared to CU participants (49.05 ± 4.91 vs 47.27 ± 4.17, p = 0.02, d = 0.40), and a significantly lower VD in the inferior quadrant in MCI-Va compared to CU participants (48.70 ± 6.57 vs 51.27 ± 6.39, p = 0.02, d = 0.40). Individuals with heart disease presented significantly lower VD in the inferior quadrant than those without (p = 0.01). The interaction of sex and diagnosis had no effect in differentiating VD. Mini-Mental State Examination (MMSE) scores were not correlated to VD (all r < 0.16; p > 0.07). In conclusion, our study showed that the MCI-AD and MCI-Va groups had significant differences in macular VD in opposite directions in the temporal and inferior quadrants, respectively, compared to CU participants, suggesting that macular VD might be able to differentiate two pathogenic pathways (AD- and cerebrovascular-related) in early stages of cognitive decline.

Sex, Neuropsychiatric Profiles, and Caregiver Burden in Alzheimer's Disease Dementia: A Latent Class Analysis.

BACKGROUND: Neuropsychiatric symptoms (NPS) in Alzheimer's disease (AD) can be disruptive for patients and their families. OBJECTIVE: We aimed to classify patients based on NPS and to explore the relationship of these classes with sex and with caregiver burden. METHODS: The study cohort comprised individuals with AD dementia diagnosed at Ace Alzheimer Center in Barcelona, Spain, between 2011-2020. NPS were ascertained by using the Neuropsychiatric Inventory-Questionnaire. Latent class analysis was used to identify clusters of individuals sharing a similar NPS profile. We evaluated the caregiver burden using the Zarit Burden Interview. Multivariable regression models were used to obtain adjusted estimates of the association between sex, NPS classes, and caregiver burden. RESULTS: A total of 1,065 patients with AD dementia and their primary caregivers were included. We classified patients into five different classes according to their NPS profile: "Affective", "High-behavioral-disturbance", "Negative-affect", "Affective/deliriant", and "Apathy". We found that age, sex, and type of AD diagnosis differed greatly across classes. We found that patients from the "High-behavioral-disturbance" (OR = 2.56, 95% CI: 1.00-6.56), "Negative-affect" (OR = 2.72, 95% CI: 1.26-3.64), and "Affective/deliriant" (OR = 2.14, 95% CI: 1.26-3.64) classes were over two times more likely to have a female caregiver than those in "Apathy" class. These three classes were also the ones associated to the greatest caregiver burden in the adjusted analyses, which seems to explain the increased burden observed among female caregivers. CONCLUSION: Caregiver burden is highly dependent on the patient's NPS profiles. Female caregivers provide care to patients that pose a greater burden, which makes them more susceptible to become overwhelmed.

Symptomatic and Disease-Modifying Therapy Pipeline for Alzheimer's Disease: Towards a Personalized Polypharmacology Patient-Centered Approach.

Since 1906, when Dr. Alois Alzheimer first described in a patient "a peculiar severe disease process of the cerebral cortex", people suffering from this pathology have been waiting for a breakthrough therapy. Alzheimer's disease (AD) is an irreversible, progressive neurodegenerative brain disorder and the most common form of dementia in the elderly with a long presymptomatic phase. Worldwide, approximately 50 million people are living with dementia, with AD comprising 60-70% of cases. Pathologically, AD is characterized by the deposition of amyloid ß-peptide (Aß) in the neuropil (neuritic plaques) and blood vessels (amyloid angiopathy), and by the accumulation of hyperphosphorylated tau in neurons (neurofibrillary tangles) in the brain, with associated loss of synapses and neurons, together with glial activation, and neuroinflammation, resulting in cognitive deficits and eventually dementia. The current competitive landscape in AD consists of symptomatic treatments, of which there are currently six approved medications: three AChEIs (donepezil, rivastigmine, and galantamine), one NMDA-R antagonist (memantine), one combination therapy (memantine/donepezil), and GV-971 (sodium oligomannate, a mixture of oligosaccharides derived from algae) only approved in China. Improvements to the approved therapies, such as easier routes of administration and reduced dosing frequencies, along with the developments of new strategies and combined treatments are expected to occur within the next decade and will positively impact the way the disease is managed. Recently, Aducanumab, the first disease-modifying therapy (DMT) has been approved for AD, and several DMTs are in advanced stages of clinical development or regulatory review. Small molecules, mAbs, or multimodal strategies showing promise in animal studies have not confirmed that promise in the clinic (where small to moderate changes in clinical efficacy have been observed), and therefore, there is a significant unmet need for a better understanding of the AD pathogenesis and the exploration of alternative etiologies and therapeutic effective disease-modifying therapies strategies for AD. Therefore, a critical review of the disease-modifying therapy pipeline for Alzheimer's disease is needed.

Establishing In-House Cutoffs of CSF Alzheimer's Disease Biomarkers for the AT(N) Stratification of the Alzheimer Center Barcelona Cohort.

BACKGROUND: Clinical diagnosis of Alzheimer's disease (AD) increasingly incorporates CSF biomarkers. However, due to the intrinsic variability of the immunodetection techniques used to measure these biomarkers, establishing in-house cutoffs defining the positivity/negativity of CSF biomarkers is recommended. However, the cutoffs currently published are usually reported by using cross-sectional datasets, not providing evidence about its intrinsic prognostic value when applied to real-world memory clinic cases. METHODS: We quantified CSF Aß1-42, Aß1-40, t-Tau, and p181Tau with standard INNOTEST® ELISA and Lumipulse G® chemiluminescence enzyme immunoassay (CLEIA) performed on the automated Lumipulse G600II. Determination of cutoffs included patients clinically diagnosed with probable Alzheimer's disease (AD, n = 37) and subjective cognitive decline subjects (SCD, n = 45), cognitively stable for 3 years and with no evidence of brain amyloidosis in 18F-Florbetaben-labeled positron emission tomography (FBB-PET). To compare both methods, a subset of samples for Aß1-42 (n = 519), t-Tau (n = 399), p181Tau (n = 77), and Aß1-40 (n = 44) was analyzed. Kappa agreement of single biomarkers and Aß1-42/Aß1-40 was evaluated in an independent group of mild cognitive impairment (MCI) and dementia patients (n = 68). Next, established cutoffs were applied to a large real-world cohort of MCI subjects with follow-up data available (n = 647). RESULTS: Cutoff values of Aß1-42 and t-Tau were higher for CLEIA than for ELISA and similar for p181Tau. Spearman coefficients ranged between 0.81 for Aß1-40 and 0.96 for p181TAU. Passing-Bablok analysis showed a systematic and proportional difference for all biomarkers but only systematic for Aß1-40. Bland-Altman analysis showed an average difference between methods in favor of CLEIA. Kappa agreement for single biomarkers was good but lower for the Aß1-42/Aß1-40 ratio. Using the calculated cutoffs, we were able to stratify MCI subjects into four AT(N) categories. Kaplan-Meier analyses of AT(N) categories demonstrated gradual and differential dementia conversion rates (p = 9.815-27). Multivariate Cox proportional hazard models corroborated these findings, demonstrating that the proposed AT(N) classifier has prognostic value. AT(N) categories are only modestly influenced by other known factors associated with disease progression. CONCLUSIONS: We established CLEIA and ELISA internal cutoffs to discriminate AD patients from amyloid-negative SCD individuals. The results obtained by both methods are not interchangeable but show good agreement. CLEIA is a good and faster alternative to manual ELISA for providing AT(N) classification of our patients. AT(N) categories have an impact on disease progression. AT(N) classifiers increase the certainty of the MCI prognosis, which can be instrumental in managing real-world MCI subjects.

GA-MADRID: design and validation of a machine learning tool for the diagnosis of Alzheimer's disease and frontotemporal dementia using genetic algorithms.

Artificial Intelligence aids early diagnosis and development of new treatments, which is key to slow down the progress of the diseases, which to date have no cure. The patients' evaluation is carried out through diagnostic techniques such as clinical assessments neuroimaging techniques, which provide high-dimensionality data. In this work, a computational tool is presented that deals with the data provided by the clinical diagnostic techniques. This is a Python-based framework implemented with a modular design and fully extendable. It integrates (i) data processing and management of missing values and outliers; (ii) implementation of an evolutionary feature engineering approach, developed as a Python package, called PyWinEA using Mono-objective and Multi-objetive Genetic Algorithms (NSGAII); (iii) a module for designing predictive models based on a wide range of machine learning algorithms; (iv) a multiclass decision stage based on evolutionary grammars and Bayesian networks. Developed under the eXplainable Artificial Intelligence and open science perspective, this framework provides promising advances and opens the door to the understanding of neurodegenerative diseases from a data-centric point of view. In this work, we have successfully evaluated the potential of the framework for early and automated diagnosis with neuroimages and neurocognitive assessments from patients with Alzheimer's disease (AD) and frontotemporal dementia (FTD).

Identification of the main components of spontaneous speech in primary progressive aphasia and their neural underpinnings using multimodal MRI and FDG-PET imaging.

BACKGROUND: Primary progressive aphasia (PPA) is a clinical syndrome characterized by gradual loss of language skills. This study aimed to evaluate the diagnostic capacity of a connected speech task for the diagnosis of PPA and its variants, to determine the main components of spontaneous speech, and to examine their neural correlates. METHODS: A total of 118 participants (31 patients with nfvPPA, 11 with svPPA, 45 with lvPPA, and 31 healthy controls) were evaluated with the Cookie Theft picture description task and a comprehensive language assessment protocol. Patients also underwent 18F-fluorodeoxyglucose positron emission tomography and magnetic resonance imaging studies. Principal component analysis and machine learning were used to evaluate the main components of connected speech and the accuracy of connected speech parameters for diagnosing PPA. Voxel-based analyses were conducted to evaluate the correlation between spontaneous speech components and brain metabolism, brain volumes, and white matter microstructure. RESULTS: Discrimination between patients with PPA and controls was 91.67%, with 77.78% discrimination between PPA variants. Parameters related to speech rate and lexical variables were the most discriminative for classification. Three main components were identified: lexical features, fluency, and syntax. The lexical component was associated with ventrolateral frontal regions, while the fluency component was associated with the medial superior prefrontal cortex. Number of pauses was more related with the left parietotemporal region, while pauses duration with the bilateral frontal lobe. The lexical component was correlated with several tracts in the language network (left frontal aslant tract, left superior longitudinal fasciculus I, II, and III, left arcuate fasciculus, and left uncinate fasciculus), and fluency was linked to the frontal aslant tract. CONCLUSION: Spontaneous speech assessment is a useful, brief approach for the diagnosis of PPA and its variants. Neuroimaging correlates suggested a subspecialization within the left frontal lobe, with ventrolateral regions being more associated with lexical production and the medial superior prefrontal cortex with speech rate.

The Five-Point Test: Normative data for middle-aged and elderly Spaniards.

The Five-Point Test (5PT) is a neuropsychological tool for examining design or figural fluency. In this study, we aimed to provide normative data for the 5PT in Spain. Also, we aimed to compare the norms collected in our research with other normative studies from other populations to evaluate a potential cross-cultural application of 5PT. One hundred and ninety-two healthy subjects aged were enrolled. The mean age was 68.48 ± 9.68 years old (range 50-89), and mean years of education were 10.65 ± 5.22. There were 117 (60.9%) women. The overlapping interval strategy was used to maximize the sample size. Age- and education-adjusted scores were estimated using linear regression analysis. Intraclass correlation coefficient was used to calculate agreement with norms from other countries. Age and years of formal education showed moderate correlations with the scores, while the influence of sex was non-significant. Intraclass correlation coefficient (absolute agreement) between Spanish and German norms was 0.956 (95% confidence interval 0.906-0.978). Norms for unique designs at 1, 2, and 3 minutes are provided. Our study confirms the influence of age and education on design fluency and provides normative data for people older than 50 years old. We hypothesize that 5PT might be a useful test in cross-cultural settings.

Design and Verbal Fluency in Alzheimer's Disease and Frontotemporal Dementia: Clinical and Metabolic Correlates.

OBJECTIVE: Cognitive processes underlying verbal and design fluency, and their neural correlates in patients with Alzheimer's disease (AD) and behavioural variant Frontotemporal Dementia (bvFTD) remain unclear. We hypothesised that verbal and design fluency may be associated with distinct neuropsychological processes in AD and FTD, showing different patterns of impairment and neural basis. METHODS: We enrolled 142 participants including patients with AD (n = 80, mean age = 74.71), bvFTD (n = 34, mean age = 68.18), and healthy controls (HCs) (n = 28, mean age = 71.14), that underwent cognitive assessment and 18F-fluorodeoxyglucose positron emission tomography imaging. RESULTS: Semantic and phonemic fluency showed the largest effect sizes between groups, showing lower scores in bvFTD than AD and HCs, and lower scores in AD than HC. Both AD and bvFTD showed a lower number of unique designs in design fluency in comparison to HC. Semantic fluency was correlated with left frontotemporal lobe in AD, and with left frontal, caudate, and thalamus in bvFTD. Percentage of unique designs in design fluency was associated with the metabolism of the bilateral fronto-temporo-parietal cortex in AD, and the bilateral frontal cortex with right predominance in bvFTD. Repetitions in AD were correlated with bilateral frontal, temporal, and parietal lobes, and with left prefrontal cortex in bvFTD. CONCLUSIONS: Our findings demonstrate differential underlying cognitive processes in verbal and design fluency in AD and bvFTD. While memory and executive functioning associated with fronto-temporo-parietal regions were key in AD, attention and executive functions correlated with the frontal cortex and played a more significant role in bvFTD during fluency tasks.

Diagnosis of Alzheimer's disease and behavioural variant frontotemporal dementia with machine learning-aided neuropsychological assessment using feature engineering and genetic algorithms.

BACKGROUND: Neuropsychological assessment is considered a valid tool in the diagnosis of neurodegenerative disorders. However, there is an important overlap in cognitive profiles between Alzheimer's disease (AD) and behavioural variant frontotemporal dementia (bvFTD), and the usefulness in diagnosis is uncertain. We aimed to develop machine learning-based models for the diagnosis using cognitive tests. METHODS: Three hundred and twenty-nine participants (170 AD, 72 bvFTD, 87 healthy control [HC]) were enrolled. Evolutionary algorithms, inspired by the process of natural selection, were applied for both mono-objective and multi-objective classification and feature selection. Classical algorithms (NativeBayes, Support Vector Machines, among others) were also used, and a meta-model strategy. RESULTS: Accuracies for the diagnosis of AD, bvFTD and the differential diagnosis between them were higher than 84%. Algorithms were able to significantly reduce the number of tests and scores needed. Free and Cued Selective Reminding Test, verbal fluency and Addenbrooke's Cognitive Examination were amongst the most meaningful tests. CONCLUSIONS: Our study found high levels of accuracy for diagnosis using exclusively neuropsychological tests, which supports the usefulness of cognitive assessment in diagnosis. Machine learning may have a role in improving the interpretation and test selection.