Predicting changes in brain metabolism and progression from mild cognitive impairment to dementia using multitask Deep Learning models and explainable AI.

BACKGROUND: The prediction of Alzheimer's disease (AD) progression from its early stages is a research priority. In this context, the use of Artificial Intelligence (AI) in AD has experienced a notable surge in recent years. However, existing investigations predominantly concentrate on distinguishing clinical phenotypes through cross-sectional approaches. This study aims to investigate the potential of modeling additional dimensions of the disease, such as variations in brain metabolism assessed via [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET), and utilize this information to identify patients with mild cognitive impairment (MCI) who will progress to dementia (pMCI). METHODS: We analyzed data from 1,617 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had undergone at least one FDG-PET scan. We identified the brain regions with the most significant hypometabolism in AD and used Deep Learning (DL) models to predict future changes in brain metabolism. The best-performing model was then adapted under a multi-task learning framework to identify pMCI individuals. Finally, this model underwent further analysis using eXplainable AI (XAI) techniques. RESULTS: Our results confirm a strong association between hypometabolism, disease progression, and cognitive decline. Furthermore, we demonstrated that integrating data on changes in brain metabolism during training enhanced the models' ability to detect pMCI individuals (sensitivity=88.4%, specificity=86.9%). Lastly, the application of XAI techniques enabled us to delve into the brain regions with the most significant impact on model predictions, highlighting the importance of the hippocampus, cingulate cortex, and some subcortical structures. CONCLUSION: This study introduces a novel dimension to predictive modeling in AD, emphasizing the importance of projecting variations in brain metabolism under a multi-task learning paradigm.

Biomarkers of Alzheimer's disease and neurodegeneration in dried blood spots-A new collection method for remote settings.

BACKGROUND: We aimed to evaluate the precision of Alzheimer's disease (AD) and neurodegeneration biomarker measurements from venous dried plasma spots (DPSv enous) for the diagnosis and monitoring of neurodegenerative diseases in remote settings. METHODS: In a discovery (n = 154) and a validation cohort (n = 115), glial fibrillary acidic protein (GFAP); neurofilament light (NfL); amyloid beta (Aß) 40, Aß42; and phosphorylated tau (p-tau181 and p-tau217) were measured in paired DPSvenous and ethylenediaminetetraacetic acid plasma samples with single-molecule array. In the validation cohort, a subset of participants (n = 99) had cerebrospinal fluid (CSF) biomarkers. RESULTS: All DPSvenous and plasma analytes correlated significantly, except for Aß42. In the validation cohort, DPSvenous GFAP, NfL, p-tau181, and p-tau217 differed between CSF Aß-positive and -negative individuals and were associated with worsening cognition. DISCUSSION: Our data suggest that measuring blood biomarkers related to AD pathology and neurodegeneration from DPSvenous extends the utility of blood-based biomarkers to remote settings with simplified sampling conditions, storage, and logistics. HIGHLIGHTS: A wide array of biomarkers related to Alzheimer's disease (AD) and neurodegeneration were detectable in dried plasma spots (DPSvenous). DPSvenous biomarkers correlated with standard procedures and cognitive status. DPSvenous biomarkers had a good diagnostic accuracy discriminating amyloid status. Our findings show the potential interchangeability of DPSvenous and plasma sampling. DPSvenous may facilitate remote and temperature-independent sampling for AD biomarker measurement. Innovative tools for blood biomarker sampling may help recognizing the earliest changes of AD.

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.

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.

Genetic-based patient stratification in Alzheimer's disease.

Alzheimer's disease (AD) shows a high pathological and symptomatological heterogeneity. To study this heterogeneity, we have developed a patient stratification technique based on one of the most significant risk factors for the development of AD: genetics. We addressed this challenge by including network biology concepts, mapping genetic variants data into a brain-specific protein-protein interaction (PPI) network, and obtaining individualized PPI scores that we then used as input for a clustering technique. We then phenotyped each obtained cluster regarding genetics, sociodemographics, biomarkers, fluorodeoxyglucose-positron emission tomography (FDG-PET) imaging, and neurocognitive assessments. We found three clusters defined mainly by genetic variants found in MAPT, APP, and APOE, considering known variants associated with AD and other neurodegenerative disease genetic architectures. Profiling of these clusters revealed minimal variation in AD symptoms and pathology, suggesting different biological mechanisms may activate the neurodegeneration and pathobiological patterns behind AD and result in similar clinical and pathological presentations, even a shared disease diagnosis. Lastly, our research highlighted MAPT, APP, and APOE as key genes where these genetic distinctions manifest, suggesting them as potential targets for personalized drug development strategies to address each AD subgroup individually.

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.

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.

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.

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.

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.

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).

Genetic Algorithms for Optimized Diagnosis of Alzheimer's Disease and Frontotemporal Dementia Using Fluorodeoxyglucose Positron Emission Tomography Imaging.

Genetic algorithms have a proven capability to explore a large space of solutions, and deal with very large numbers of input features. We hypothesized that the application of these algorithms to 18F-Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) may help in diagnosis of Alzheimer's disease (AD) and Frontotemporal Dementia (FTD) by selecting the most meaningful features and automating diagnosis. We aimed to develop algorithms for the three main issues in the diagnosis: discrimination between patients with AD or FTD and healthy controls (HC), differential diagnosis between behavioral FTD (bvFTD) and AD, and differential diagnosis between primary progressive aphasia (PPA) variants. Genetic algorithms, customized with K-Nearest Neighbor and BayesNet Naives as the fitness function, were developed and compared with Principal Component Analysis (PCA). K-fold cross validation within the same sample and external validation with ADNI-3 samples were performed. External validation was performed for the algorithms distinguishing AD and HC. Our study supports the use of FDG-PET imaging, which allowed a very high accuracy rate for the diagnosis of AD, FTD, and related disorders. Genetic algorithms identified the most meaningful features with the minimum set of features, which may be relevant for automated assessment of brain FDG-PET images. Overall, our study contributes to the development of an automated, and optimized diagnosis of neurodegenerative disorders using brain metabolism.