Rey's Auditory Verbal Learning Test scores can be predicted from whole brain MRI in Alzheimer's disease

c-Triadem: A constrained, explainable deep learning model to identify novel biomarkers in Alzheimer's disease

Alzheimer's disease (AD) is a neurodegenerative disorder that requires early diagnosis for effective management. However, issues with currently available diagnostic biomarkers preclude early diagnosis, necessitating the development of alternative biomarkers and methods, such as blood-based diagnostics. We propose c-Triadem (constrained triple-input Alzheimer's disease model), a novel deep neural network to identify potential blood-based biomarkers for AD and predict mild cognitive impairment (MCI) and AD with high accuracy. The model utilizes genotyping data, gene expression data, and clinical information to predict the disease status of participants, i.e., cognitively normal (CN), MCI, or AD. The nodes of the neural network represent genes and their related pathways, and the edges represent known relationships among the genes and pathways. Simulated data validation further highlights the robustness of key features identified by SHapley Additive exPlanations (SHAP). We trained the model with blood genotyping data, microarray, and clinical features from the Alzheimer's Neuroimaging Disease Initiative (ADNI). We demonstrate that our model's performance is superior to previous models with an AUC of 97% and accuracy of 89%. We then identified the most influential genes and clinical features for prediction using SHapley Additive exPlanations (SHAP). Our SHAP analysis shows that CASP9, LCK, and SDC3 SNPs and PINK1, ATG5, and ubiquitin (UBB, UBC) expression have a higher impact on model performance. Our model has facilitated the identification of potential blood-based genetic markers of DNA damage response and mitophagy in affected regions of the brain. The model can be used for detection and biomarker identification in other related dementias.

Physical activity partially mediates the association between health literacy and mild cognitive impairment in older adults: cross-sectional evidence from Switzerland

Individuals' health literacy (HL) is positively associated with healthy behaviors and global cognitive functioning. Current evidence also suggests that physical activity may prevent or delay cognitive decline and dementia. This study examines the potential mediating role of physical activity in the association between HL and cognition in a population-based sample of adults aged 58+ in Switzerland. We used data from 1645 respondents to Wave 8 (2019/2020) of the Survey on Health, Ageing, and Retirement in Europe in Switzerland. HL was assessed using the HLS-EU-Q16 questionnaire. Mild cognitive impairment (MCI) was defined as a 1.5 SD below the mean of age- and education-specific global cognition score. The frequency of moderate and vigorous physical activity was self-reported. The associations were assessed using probit regression models, controlling for social, health, and regional characteristics. Structural equation modeling was used to test the mediation hypothesis. Higher HL was associated with a higher likelihood of being engaged in moderate (P < .001) and vigorous (P < .01) physical activity and with a lower likelihood of having MCI (P < .05). In addition, both moderate (P < .05) and vigorous (P < .01) physical activity were associated with a lower probability of having MCI. Mediation analysis indicated that the association between HL and MCI was partially mediated by both moderate (12.9%) and vigorous (6.7%) physical activity. Given that physical activity may partially mediate the association between HL and MCI, improving HL in older adults could potentially foster engagement in physical activity, which could, in turn, act as a protective factor against MCI.

Beat-to-beat blood pressure variability, hippocampal atrophy, and memory impairment in older adults

Visit-to-visit blood pressure variability (BPV) predicts age-related hippocampal atrophy, neurodegeneration, and memory decline in older adults. Beat-to-beat BPV may represent a more reliable and efficient tool for prospective risk assessment, but it is unknown whether beat-to-beat BPV is similarly associated with hippocampal neurodegeneration, or with plasma markers of neuroaxonal/neuroglial injury. Independently living older adults without a history of dementia, stroke, or other major neurological disorders were recruited from the community (N = 104; age = 69.5 ± 6.7 (range 55-89); 63% female). Participants underwent continuous blood pressure monitoring, brain MRI, venipuncture, and cognitive testing over two visits. Hippocampal volumes, plasma neurofilament light, and glial fibrillary acidic protein levels were assessed. Beat-to-beat BPV was quantified as systolic blood pressure average real variability during 7-min of supine continuous blood pressure monitoring. The cross-sectional relationship between beat-to-beat BPV and hippocampal volumes, cognitive domain measures, and plasma biomarkers was assessed using multiple linear regression with adjustment for demographic covariates, vascular risk factors, and average systolic blood pressure. Elevated beat-to-beat BPV was associated with decreased left hippocampal volume (P = .008), increased plasma concentration of glial fibrillary acidic protein (P = .006), and decreased memory composite score (P = .02), independent of age, sex, average systolic blood pressure, total intracranial volume, and vascular risk factor burden. In summary, beat-to-beat BPV is independently associated with decreased left hippocampal volume, increased neuroglial injury, and worse memory ability. Findings are consistent with prior studies examining visit-to-visit BPV and suggest beat-to-beat BPV may be a useful marker of hemodynamic brain injury in older adults.

Exploring individual differences in amygdala-mediated memory modulation

Amygdala activation by emotional arousal during memory formation can prioritize events for long-term memory. Building upon our prior demonstration that brief electrical stimulation to the human amygdala reliably improved long-term recognition memory for images of neutral objects without eliciting an emotional response, our study aims to explore and describe individual differences and stimulation-related factors in amygdala-mediated memory modulation. Thirty-one patients undergoing intracranial monitoring for intractable epilepsy were shown neutral object images paired with direct amygdala stimulation during encoding with recognition memory tested immediately and one day later. Adding to our prior sample, we found an overall memory enhancement effect without subjective emotional arousal at the one-day delay, but not at the immediate delay, for previously stimulated objects compared to not stimulated objects. Importantly, we observed a larger variation in performance across this larger sample than our initial sample, including some participants who showed a memory impairment for stimulated objects. Of the explored individual differences, the factor that most accounted for variability in memory modulation was each participant's pre-operative memory performance. Worse memory performance on standardized neuropsychological tests was associated with a stronger susceptibility to memory modulation in a positive or negative direction. Sex differences and the frequency of interictal epileptiform discharges (IEDs) during testing also accounted for some variance in amygdala-mediated memory modulation. Given the potential and challenges of this memory modulation approach, we discuss additional individual and stimulation factors that we hope will differentiate between memory enhancement and impairment to further optimize the potential of amygdala-mediated memory enhancement for therapeutic interventions.

Verbal Memory is Higher After Aerobic Exercise When Compared to Muscle Stretching

Acute exercise is linked to memory improvement. Several mediators may influence the effect of exercise such as the type of exercise (aerobic exercise, muscle stretching). Purpose: The primary aim was to analyze memory outcomes after a 20-min bout of aerobic exercise or muscle stretching. Methods: 42 healthy participants ages 18-35 were randomized to perform 20 min of either moderate-intensity aerobic exercise (AE) on a treadmill or muscle stretching exercise (SE). After exercise, memory was assessed using the Rey Auditory Verbal Learning Test (RAVLT). The relationship between exercise heart rate and memory outcomes were evaluated within each group. Results: Immediate learning as well as delayed recall was higher after AE compared to SE. Heart rate during exercise correlated with immediate learning in the AE group only. Conclusion: Acute exercise that elicits a heart rate response may be important for improving memory.

Stepwise identification of prodromal dementia: Testing a practical model for primary care

BACKGROUND

Prodromal dementia is largely underdiagnosed in primary care.

OBJECTIVE

To develop a clinical model for detecting prodromal dementia within the operative boundaries of primary care practice.

METHODS

The study employed the Functional Activities Questionnaire (FAQ) and Montreal Cognitive Assessment (MoCA) to evaluate a "functional-cognitive" step-down screening model, in which the MoCA is administered subsequent to reported symptoms on the FAQ. It classified participants from the Alzheimer's Disease Imaging Initiative to three diagnostic categories: (1) healthy cognition (n = 396), (2) mild cognitive impairment without conversion (n = 430), and (3) prodromal dementia assessed 24 months before diagnosis (n = 164).

RESULTS

Analyses indicated that the step-down model (Model 1) performed significantly better than an alternative model that applied the FAQ as a single measure (Model 2) and compared well with another model that administered both screening measures to all participants (Model 3). Gradient Boosting Trees classifications yielded the following estimations for Model 1/Model 2/ Model 3, respectively: Sensitivity = 0.87/0.77/0.89, Specificity = 0.68/0.47/0.70, PPV = 0.73/0.40/0.75, NVP = 0.84/0.81/0.87, F1 Score = 0.79/0.52/0.81, AUC = 0.78/0.67/0.79.

CONCLUSIONS

These analyses support the proposed model. The study offers algorithms for validated measures, which were developed from a well characterized clinical sample. Their accuracy will likely improve further with new data from diverse clinical settings. These results can serve primary care in a timely manner in light of the recent advances in pharmacological treatment of dementia and the expected increase in demand for screening.

c-Triadem: A constrained, explainable deep learning model to identify novel biomarkers in Alzheimer's disease

Alzheimer's disease (AD) is a neurodegenerative disorder that requires early diagnosis for effective management. However, issues with currently available diagnostic biomarkers preclude early diagnosis, necessitating the development of alternative biomarkers and methods, such as blood-based diagnostics. We propose c-Triadem (constrained triple-input Alzheimer's disease model), a novel deep neural network to identify potential blood-based biomarkers for AD and predict mild cognitive impairment (MCI) and AD with high accuracy. The model utilizes genotyping data, gene expression data, and clinical information to predict the disease status of participants, i.e., cognitively normal (CN), MCI, or AD. The nodes of the neural network represent genes and their related pathways, and the edges represent known relationships among the genes and pathways. We trained the model with blood genotyping data, microarray, and clinical features from the Alzheimer's Neuroimaging Disease Initiative (ADNI). We demonstrate that our model's performance is superior to previous models with an AUC of 97% and accuracy of 89%. We then identified the most influential genes and clinical features for prediction using SHapley Additive exPlanations (SHAP). Our SHAP analysis shows that CASP9, LCK, and SDC3 SNPs and PINK1, ATG5, and ubiquitin (UBB, UBC) expression have a higher impact on model performance. Our model has facilitated the identification of potential blood-based genetic markers of DNA damage response and mitophagy in affected regions of the brain. The model can be used for detection and biomarker identification in other related dementias.

Baseline multimodal imaging to predict longitudinal clinical decline in atypical Alzheimer's disease

There are recognized neuroimaging regions of interest in typical Alzheimer's disease which have been used to track disease progression and aid prognostication. However, there is a need for validated baseline imaging markers to predict clinical decline in atypical Alzheimer's Disease. We aimed to address this need by producing models from baseline imaging features using penalized regression and evaluating their predictive performance on various clinical measures. Baseline multimodal imaging data, in combination with clinical testing data at two time points from 46 atypical Alzheimer's Disease patients with a diagnosis of logopenic progressive aphasia (N = 24) or posterior cortical atrophy (N = 22), were used to generate our models. An additional 15 patients (logopenic progressive aphasia = 7, posterior cortical atrophy = 8), whose data were not used in our original analysis, were used to test our models. Patients underwent MRI, FDG-PET and Tau-PET imaging and a full neurologic battery at two time points. The Schaefer functional atlas was used to extract network-based and regional gray matter volume or PET SUVR values from baseline imaging. Penalized regression (Elastic Net) was used to create models to predict scores on testing at Time 2 while controlling for baseline performance, education, age, and sex. In addition, we created models using clinical or Meta Region of Interested (ROI) data to serve as comparisons. We found the degree of baseline involvement on neuroimaging was predictive of future performance on cognitive testing while controlling for the above measures on all three imaging modalities. In many cases, model predictability improved with the addition of network-based neuroimaging data to clinical data. We also found our network-based models performed superiorly to the comparison models comprised of only clinical or a Meta ROI score. Creating predictive models from imaging studies at a baseline time point that are agnostic to clinical diagnosis as we have described could prove invaluable in both the clinical and research setting, particularly in the development and implementation of future disease modifying therapies.

Genetic and clinical correlates of two neuroanatomical AI dimensions in the Alzheimer's disease continuum

Alzheimer's disease (AD) is associated with heterogeneous atrophy patterns. We employed a semi-supervised representation learning technique known as Surreal-GAN, through which we identified two latent dimensional representations of brain atrophy in symptomatic mild cognitive impairment (MCI) and AD patients: the "diffuse-AD" (R1) dimension shows widespread brain atrophy, and the "MTL-AD" (R2) dimension displays focal medial temporal lobe (MTL) atrophy. Critically, only R2 was associated with widely known sporadic AD genetic risk factors (e.g., APOE ε4) in MCI and AD patients at baseline. We then independently detected the presence of the two dimensions in the early stages by deploying the trained model in the general population and two cognitively unimpaired cohorts of asymptomatic participants. In the general population, genome-wide association studies found 77 genes unrelated to APOE differentially associated with R1 and R2. Functional analyses revealed that these genes were overrepresented in differentially expressed gene sets in organs beyond the brain (R1 and R2), including the heart (R1) and the pituitary gland, muscle, and kidney (R2). These genes were enriched in biological pathways implicated in dendritic cells (R2), macrophage functions (R1), and cancer (R1 and R2). Several of them were "druggable genes" for cancer (R1), inflammation (R1), cardiovascular diseases (R1), and diseases of the nervous system (R2). The longitudinal progression showed that APOE ε4, amyloid, and tau were associated with R2 at early asymptomatic stages, but this longitudinal association occurs only at late symptomatic stages in R1. Our findings deepen our understanding of the multifaceted pathogenesis of AD beyond the brain. In early asymptomatic stages, the two dimensions are associated with diverse pathological mechanisms, including cardiovascular diseases, inflammation, and hormonal dysfunction-driven by genes different from APOE-which may collectively contribute to the early pathogenesis of AD. All results are publicly available at https://labs-laboratory.com/medicine/ .

A transformer-based unified multimodal framework for Alzheimer's disease assessment

In Alzheimer's disease (AD) assessment, traditional deep learning approaches have often employed separate methodologies to handle the diverse modalities of input data. Recognizing the critical need for a cohesive and interconnected analytical framework, we propose the AD-Transformer, a novel transformer-based unified deep learning model. This innovative framework seamlessly integrates structural magnetic resonance imaging (sMRI), clinical, and genetic data from the extensive Alzheimer's Disease Neuroimaging Initiative (ADNI) database, encompassing 1651 subjects. By employing a Patch-CNN block, the AD-Transformer efficiently transforms image data into image tokens, while a linear projection layer adeptly converts non-image data into corresponding tokens. As the core, a transformer block learns comprehensive representations of the input data, capturing the intricate interplay between modalities. The AD-Transformer sets a new benchmark in AD diagnosis and Mild Cognitive Impairment (MCI) conversion prediction, achieving remarkable average area under curve (AUC) values of 0.993 and 0.845, respectively, surpassing those of traditional image-only models and non-unified multimodal models. Our experimental results confirmed the potential of the AD-Transformer as a potent tool in AD diagnosis and MCI conversion prediction. By providing a unified framework that jointly learns holistic representations of both image and non-image data, the AD-Transformer paves the way for more effective and precise clinical assessments, offering a clinically adaptable strategy for leveraging diverse data modalities in the battle against AD.

Long-term cognitive outcomes in Susac syndrome: A case series

Susac syndrome (SuS) presents with encephalopathy, visual disturbances, and hearing loss from immune-mediated microvascular occlusion. While acute SuS is well-described, long-term cognitive outcomes with current treatments are underknown. We assessed ten SuS patients treated in accordance with evidence-based guidelines using immunotherapies targeting humoral and cell-mediated pathways. Patients were followed for a median 3.6 years. Initially, cognition inversely correlated with corpus callosum lesions on MRI. All reported cognitive improvement; 5/10 patients had residual deficits in visual attention and executive function. Early, aggressive treatment was associated with good outcomes; extensive early corpus callosum lesions may identify patients at-risk of persistent cognitive deficits.

Cognitive functioning and sustained internet use amid the COVID-19 pandemic: longitudinal evidence from older adults in Switzerland

This study aimed to investigate the relationship between pre-pandemic objective and subjective cognitive functioning and sustained Internet use during the pandemic among older adults in Switzerland. Data from 1299 respondents of the Survey of Health, Ageing and Retirement in Europe (SHARE) in 2019/2020 and a supplementary technology use questionnaire during the pandemic in 2021 were used. Cognitive functioning was assessed in 2019/2020 through objective measures (delayed and immediate memory, verbal fluency) and self-rated memory. Sustained Internet use was defined as having used the Internet at least once in the past seven days in 2019/2020 and reporting daily or weekly use in 2021. We found that 73.1% of respondents consistently used Internet between 2019/2020 and 2021. Using multivariable probit regression models controlling for sociodemographic and health variables, we found that higher global cognition z-scores, especially in immediate and delayed memory, were associated with a higher likelihood of sustained Internet use. Additionally, respondents with good, very good, or excellent self-rated memory were more likely to sustain their Internet use. These findings highlight the potential critical role of cognitive health in shaping older adults' digital engagement, suggesting that cognitive assessments and training should be further considered in digital literacy initiatives for this population.

Alzheimer's disease: a review on the current trends of the effective diagnosis and therapeutics

The most prevalent cause of dementia is Alzheimer's disease. Cognitive decline and accelerating memory loss characterize it. Alzheimer's disease advances sequentially, starting with preclinical stages, followed by mild cognitive and/or behavioral impairment, and ultimately leading to Alzheimer's disease dementia. In recent years, healthcare providers have been advised to make an earlier diagnosis of Alzheimer's, prior to individuals developing Alzheimer's disease dementia. Regrettably, the identification of early-stage Alzheimer's disease in clinical settings can be arduous due to the tendency of patients and healthcare providers to disregard symptoms as typical signs of aging. Therefore, accurate and prompt diagnosis of Alzheimer's disease is essential in order to facilitate the development of disease-modifying and secondary preventive therapies prior to the onset of symptoms. There has been a notable shift in the goal of the diagnosis process, transitioning from merely confirming the presence of symptomatic AD to recognizing the illness in its early, asymptomatic phases. Understanding the evolution of disease-modifying therapies and putting effective diagnostic and therapeutic management into practice requires an understanding of this concept. The outcomes of this study will enhance in-depth knowledge of the current status of Alzheimer's disease's diagnosis and treatment, justifying the necessity for the quest for potential novel biomarkers that can contribute to determining the stage of the disease, particularly in its earliest stages. Interestingly, latest clinical trial status on pharmacological agents, the nonpharmacological treatments such as behavior modification, exercise, and cognitive training as well as alternative approach on phytochemicals as neuroprotective agents have been covered in detailed.

Analysis of Cerebrospinal Fluid, Plasma β-Amyloid Biomarkers, and Cognition from a 2-Year Phase 2 Trial Evaluating Oral ALZ-801/Valiltramiprosate in APOE4 Carriers with Early Alzheimer's Disease Using Quantitative Systems Pharmacology Model

INTRODUCTION

ALZ-801/valiltramiprosate is an oral, small-molecule inhibitor of beta-amyloid (Aβ) aggregation and oligomer formation in late-stage development as a disease-modifying therapy for early Alzheimer's disease (AD). The present investigation provides a quantitative systems pharmacology (QSP) analysis of amyloid fluid biomarkers and cognitive results from a 2-year ALZ-801 Phase 2 trial in APOE4 carriers with early AD.

METHODS

The single-arm, open-label phase 2 study evaluated effects of ALZ-801 265 mg two times daily (BID) on cerebrospinal fluid (CSF) and plasma amyloid fluid biomarkers over 104 weeks in APOE4 carriers with early AD [Mini-Mental State Examination (MMSE) ≥ 22]. Subjects with positive CSF biomarkers for amyloid (Aβ42/Aβ40) and tau pathology (p-tau181) were enrolled, with serial CSF and plasma levels of Aβ42 and Aβ40 measured over 104 weeks. Longitudinal changes of CSF Aβ42, plasma Aβ42/Aβ40 ratio, and cognitive Rey Auditory Verbal Learning Test (RAVLT) were compared with the established natural disease trajectories in AD using a QSP approach. The natural disease trajectory data for amyloid biomarkers and RAVLT were extracted from a QSP model and an Alzheimer's disease neuroimaging initiative population model, respectively. Analyses were stratified by disease severity and sex.

RESULTS

A total of 84 subjects were enrolled. Excluding one subject who withdrew at the early stage of the trial, data from 83 subjects were used for this analysis. The ALZ-801 treatment arrested the progressive decline in CSF Aβ42 level and plasma Aβ42/Aβ40 ratio, and stabilized RAVLT over 104 weeks. Both sexes showed comparable responses to ALZ-801, whereas mild cognitive impairment (MCI) subjects (MMSE ≥ 27) exhibited a larger biomarker response compared with more advanced mild AD subjects (MMSE 22-26).

CONCLUSIONS

In this genetically defined and biomarker-enriched early AD population, the QSP analysis demonstrated a positive therapeutic effect of oral ALZ-801 265 mg BID by arresting the natural decline of monomeric CSF and plasma amyloid biomarkers, consistent with the target engagement to prevent their aggregation into soluble neurotoxic oligomers and subsequently into insoluble fibrils and plaques over 104 weeks. Accompanying the amyloid biomarker changes, ALZ-801 also stabilized the natural trajectory decline of the RAVLT memory test, suggesting that the clinical benefits are consistent with its mechanism of action. This sequential effect arresting the disease progression on biomarkers and cognitive decline was more pronounced in the earlier symptomatic stages of AD. The QSP analysis provides fluid biomarker and clinical evidence for ALZ-801 as a first-in-class, oral small-molecule anti-Aβ oligomer agent with disease modification potential in AD.

TRIAL REGISTRY

https://clinicaltrials.gov/study/NCT04693520.

Choroid plexus volumes and auditory verbal learning scores are associated with conversion from mild cognitive impairment to Alzheimer's disease

PURPOSE

Mild cognitive impairment (MCI) can be the prodromal phase of Alzheimer's disease (AD) where appropriate intervention might prevent or delay conversion to AD. Given this, there has been increasing interest in using magnetic resonance imaging (MRI) and neuropsychological testing to predict conversion from MCI to AD. Recent evidence suggests that the choroid plexus (ChP), neural substrates implicated in brain clearance, undergo volumetric changes in MCI and AD. Whether the ChP is involved in memory changes observed in MCI and can be used to predict conversion from MCI to AD has not been explored.

METHOD

The current study used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database to investigate whether later progression from MCI to AD (progressive MCI [pMCI], n = 115) or stable MCI (sMCI, n = 338) was associated with memory scores using the Rey Auditory Verbal Learning Test (RAVLT) and ChP volumes as calculated from MRI. Classification analyses identifying pMCI or sMCI group membership were performed to compare the predictive ability of the RAVLT and ChP volumes.

FINDING

The results indicated a significant difference between pMCI and sMCI groups for right ChP volume, with the pMCI group showing significantly larger right ChP volume (p = .01, 95% confidence interval [-.116, -.015]). A significant linear relationship between the RAVLT scores and right ChP volume was found across all participants, but not for the two groups separately. Classification analyses showed that a combination of left ChP volume and auditory verbal learning scores resulted in the most accurate classification performance, with group membership accurately predicted for 72% of the testing data.

CONCLUSION

These results suggest that volumetric ChP changes appear to occur before the onset of AD and might provide value in predicting conversion from MCI to AD.

Multimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data

BACKGROUND

For successful biomarker discovery, it is essential to develop computational frameworks that summarize high-dimensional neuroimaging data in terms of involved sub-systems of the brain, while also revealing underlying heterogeneous functional and structural changes covarying with specific cognitive and biological traits. However, unsupervised decompositions do not inculcate clinical assessment information, while supervised approaches extract only individual feature importance, thereby impeding qualitative interpretation at the level of subspaces.

NEW METHOD

We present a novel framework to extract robust multimodal brain subspaces associated with changes in a given cognitive or biological trait. Our approach involves active subspace learning on the gradients of a trained machine learning model followed by clustering to extract and summarize the most salient and consistent subspaces associated with the target variable.

RESULTS

Through a rigorous cross-validation procedure on an Alzheimer's disease (AD) dataset, our framework successfully extracts multimodal subspaces specific to a given clinical assessment (e.g., memory and other cognitive skills), and also retains predictive performance in standard machine learning algorithms. We also show that the salient active subspace directions occur consistently across randomly sub-sampled repetitions of the analysis.

COMPARISON WITH EXISTING METHOD(S)

Compared to existing unsupervised decompositions based on principle component analysis, the subspace components in our framework retain higher predictive information.

CONCLUSIONS

As an important step towards biomarker discovery, our framework not only uncovers AD-related brain regions in the associated brain subspaces, but also enables automated identification of multiple underlying structural and functional sub-systems of the brain that collectively characterize changes in memory and proficiency in cognitive skills related to brain disorders like AD.

Energy landscape analysis of brain network dynamics in Alzheimer's disease

Background

Alzheimer's disease (AD) is a common neurodegenerative dementia, characterized by abnormal dynamic functional connectivity (DFC). Traditional DFC analysis, assuming linear brain dynamics, may neglect the complexity of the brain's nonlinear interactions. Energy landscape analysis offers a holistic, nonlinear perspective to investigate brain network attractor dynamics, which was applied to resting-state fMRI data for AD in this study.

Methods

This study utilized resting-state fMRI data from 60 individuals, comparing 30 Alzheimer's patients with 30 controls, from the Alzheimer's Disease Neuroimaging Initiative. Energy landscape analysis was applied to the data to characterize the aberrant brain network dynamics of AD patients.

Results

The AD group stayed in the co-activation state for less time than the healthy control (HC) group, and a positive correlation was identified between the transition frequency of the co-activation state and behavior performance. Furthermore, the AD group showed a higher occurrence frequency and transition frequency of the cognitive control state and sensory integration state than the HC group. The transition between the two states was positively correlated with behavior performance.

Conclusion

The results suggest that the co-activation state could be important to cognitive processing and that the AD group possibly raised cognitive ability by increasing the occurrence and transition between the impaired cognitive control and sensory integration states.

Seeing beyond the symptoms: biomarkers and brain regions linked to cognitive decline in Alzheimer's disease

Objective

Early Alzheimer's disease (AD) diagnosis remains challenging, necessitating specific biomarkers for timely detection. This study aimed to identify such biomarkers and explore their associations with cognitive decline.

Methods

A cohort of 1759 individuals across cognitive aging stages, including healthy controls (HC), mild cognitive impairment (MCI), and AD, was examined. Utilizing nine biomarkers from structural MRI (sMRI), diffusion tensor imaging (DTI), and positron emission tomography (PET), predictions were made for Mini-Mental State Examination (MMSE), Clinical Dementia Rating Scale Sum of Boxes (CDRSB), and Alzheimer's Disease Assessment Scale-Cognitive Subscale (ADAS). Biomarkers included four sMRI (e.g., average thickness [ATH]), four DTI (e.g., mean diffusivity [MD]), and one PET Amyloid-β (Aβ) measure. Ensemble regression tree (ERT) technique with bagging and random forest approaches were applied in four groups (HC/MCI, HC/AD, MCI/AD, and HC/MCI/AD).

Results

Aβ emerged as a robust predictor of cognitive scores, particularly in late-stage AD. Volumetric measures, notably ATH, consistently correlated with cognitive scores across early and late disease stages. Additionally, ADAS demonstrated links to various neuroimaging biomarkers in all subject groups, highlighting its efficacy in monitoring brain changes throughout disease progression. ERT identified key brain regions associated with cognitive scores, such as the right transverse temporal region for Aβ, left and right entorhinal cortex, left inferior temporal gyrus, and left middle temporal gyrus for ATH, and the left uncinate fasciculus for MD.

Conclusion

This study underscores the importance of an interdisciplinary approach in understanding AD mechanisms, offering potential contributions to early biomarker development.

Iron Deposition and Distribution Across the Hippocampus Is Associated with Pattern Separation and Pattern Completion in Older Adults at Risk for Alzheimer's Disease

Elevated iron deposition in the brain has been observed in older adult humans and persons with Alzheimer's disease (AD), and has been associated with lower cognitive performance. We investigated the impact of iron deposition, and its topographical distribution across hippocampal subfields and segments (anterior, posterior) measured along its longitudinal axis, on episodic memory in a sample of cognitively unimpaired older adults at elevated familial risk for AD (N = 172, 120 females, 52 males; mean age = 68.8 ± 5.4 years). MRI-based quantitative susceptibility maps were acquired to derive estimates of hippocampal iron deposition. The Mnemonic Similarity Task was used to measure pattern separation and pattern completion, two hippocampally mediated episodic memory processes. Greater hippocampal iron load was associated with lower pattern separation and higher pattern completion scores, both indicators of poorer episodic memory. Examination of iron levels within hippocampal subfields across its long axis revealed topographic specificity. Among the subfields and segments investigated here, iron deposition in the posterior hippocampal CA1 was the most robustly and negatively associated with the fidelity memory representations. This association remained after controlling for hippocampal volume and was observed in the context of normal performance on standard neuropsychological memory measures. These findings reveal that the impact of iron load on episodic memory performance is not uniform across the hippocampus. Both iron deposition levels as well as its spatial distribution, must be taken into account when examining the relationship between hippocampal iron and episodic memory in older adults at elevated risk for AD.

MAPPING ALZHEIMER'S DISEASE PSEUDO-PROGRESSION WITH MULTIMODAL BIOMARKER TRAJECTORY EMBEDDINGS

Alzheimer's Disease (AD) is a neurodegenerative disorder characterized by progressive cognitive degeneration and motor impairment, affecting millions worldwide. Mapping the progression of AD is crucial for early detection of loss of brain function, timely intervention, and development of effective treatments. However, accurate measurements of disease progression are still challenging at present. This study presents a novel approach to understanding the heterogeneous pathways of AD through longitudinal biomarker data from medical imaging and other modalities. We propose an analytical pipeline adopting two popular machine learning methods from the single-cell transcriptomics domain, PHATE and Slingshot, to project multimodal biomarker trajectories to a low-dimensional space. These embeddings serve as our pseudotime estimates. We applied this pipeline to the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to align longitudinal data across individuals at various disease stages. Our approach mirrors the technique used to cluster single-cell data into cell types based on developmental timelines. Our pseudotime estimates revealed distinct patterns of disease evolution and biomarker changes over time, providing a deeper understanding of the temporal dynamics of AD. The results show the potential of the approach in the clinical domain of neurodegenerative diseases, enabling more precise disease modeling and early diagnosis.

Differential predictability of cognitive profiles from brain structure in older males and females

Structural brain imaging parameters may successfully predict cognitive performance in neurodegenerative diseases but mostly fail to predict cognitive abilities in healthy older adults. One important aspect contributing to this might be sex differences. Behaviorally, older males and females have been found to differ in terms of cognitive profiles, which cannot be captured by examining them as one homogenous group. In the current study, we examined whether the prediction of cognitive performance from brain structure, i.e. region-wise grey matter volume (GMV), would benefit from the investigation of sex-specific cognitive profiles in a large sample of older adults (1000BRAINS; N = 634; age range 55-85 years). Prediction performance was assessed using a machine learning (ML) approach. Targets represented a) a whole-sample cognitive component solution extracted from males and females, and b) sex-specific cognitive components. Results revealed a generally low predictability of cognitive profiles from region-wise GMV. In males, low predictability was observed across both, the whole sample as well as sex-specific cognitive components. In females, however, predictability differences across sex-specific cognitive components were observed, i.e. visual working memory (WM) and executive functions showed higher predictability than fluency and verbal WM. Hence, results accentuated that addressing sex-specific cognitive profiles allowed a more fine-grained investigation of predictability differences, which may not be observable in the prediction of the whole-sample solution. The current findings not only emphasize the need to further investigate the predictive power of each cognitive component, but they also emphasize the importance of sex-specific analyses in older adults.

Trajectories of quality of life and cognition in different multimorbidity patterns: Evidence from SHARE

OBJECTIVES

The study aimed to observe the trajectory of quality of life (QoL) and cognition, and to a analyze the bidirectional association between cognition and QoL for diverse multimorbidity patterns.

METHODS

In total, 16,153 older participants age ≥50 years were included from the Survey of Health, Ageing and Retirement in Europe (SHARE). We used latent class analysis (LCA) to identify multimorbidity patterns in the baseline population. We used linear mixed models (LMM) to examine the trajectory of cognition and QoL in different multimorbidity patterns. A cross-lagged model was employed to analyze the bidirectional association between cognition and QoL in diverse multimorbidity patterns.

RESULTS

Latent class analysis identified four multimorbidity patterns: high and low comorbidity burden (HC and LC), cardiometabolic (CA), and osteoarthrosis (OS). The HC group had the poorest cognitive function and QoL (p for trend < 0.001). Delayed and immediate episodic memory in the OS group declined at a highest rate (p for trend < 0.001). Additionally, a bidirectional association between cognition and QoL was observed. The effect of cognitive function on QoL was relatively stronger than the reverse in the CA and LC groups.

CONCLUSIONS

The rate of decline in cognition and QoL over the time differs in diverse multimorbidity patterns, and patients with four or more chronic diseases should be specially considered. Notably, early monitoring of cognitive function and can help break the vicious cycle between cognitive deterioration and poor QoL in patients with OS or CA diseases.

Applications of Artificial Intelligence in the Neuropsychological Assessment of Dementia: A Systematic Review

In the context of advancing healthcare, the diagnosis and treatment of cognitive disorders, particularly Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD), pose significant challenges. This review explores Artificial Intelligence (AI) and Machine Learning (ML) in neuropsychological assessment for the early detection and personalized treatment of MCI and AD. The review includes 37 articles that demonstrate that AI could be an useful instrument for optimizing diagnostic procedures, predicting cognitive decline, and outperforming traditional tests. Three main categories of applications are identified: (1) combining neuropsychological assessment with clinical data, (2) optimizing existing test batteries using ML techniques, and (3) employing virtual reality and games to overcome the limitations of traditional tests. Despite advancements, the review highlights a gap in developing tools that simplify the clinician's workflow and underscores the need for explainable AI in healthcare decision making. Future studies should bridge the gap between technical performance measures and practical clinical utility to yield accurate results and facilitate clinicians' roles. The successful integration of AI/ML in predicting dementia onset could reduce global healthcare costs and benefit aging societies.

Neuronal microstructural changes in the human brain are associated with neurocognitive aging

Gray matter (GM) alterations play a role in aging-related disorders like Alzheimer's disease and related dementias, yet MRI studies mainly focus on macroscopic changes. Although reliable indicators of atrophy, morphological metrics like cortical thickness lack the sensitivity to detect early changes preceding visible atrophy. Our study aimed at exploring the potential of diffusion MRI in unveiling sensitive markers of cortical and subcortical age-related microstructural changes and assessing their associations with cognitive and behavioral deficits. We leveraged the Human Connectome Project-Aging cohort that included 707 unimpaired participants (394 female; median age = 58, range = 36-90 years) and applied the powerful mean apparent diffusion propagator model to measure microstructural parameters, along with comprehensive behavioral and cognitive test scores. Both macro- and microstructural GM characteristics were strongly associated with age, with widespread significant microstructural correlations reflective of cellular morphological changes, reduced cellular density, increased extracellular volume, and increased membrane permeability. Importantly, when correlating MRI and cognitive test scores, our findings revealed no link between macrostructural volumetric changes and neurobehavioral performance. However, we found that cellular and extracellular alterations in cortical and subcortical GM regions were associated with neurobehavioral performance. Based on these findings, it is hypothesized that increased microstructural heterogeneity and decreased neurite orientation dispersion precede macrostructural changes, and that they play an important role in subsequent cognitive decline. These alterations are suggested to be early markers of neurocognitive performance that may distinctly aid in identifying the mechanisms underlying phenotypic aging and subsequent age-related functional decline.

Prediction of declarative memory profile in panic disorder patients: a machine learning-based approach

OBJECTIVE

To develop a classification framework based on random forest (RF) modeling to outline the declarative memory profile of patients with panic disorder (PD) compared to a healthy control sample.

METHODS

We developed RF models to classify the declarative memory profile of PD patients in comparison to a healthy control sample using the Rey Auditory Verbal Learning Test (RAVLT). For this study, a total of 299 patients with PD living in the city of Rio de Janeiro (70.9% females, age 39.9 ± 7.3 years old) were recruited through clinician referrals or self/family referrals.

RESULTS

Our RF models successfully predicted declarative memory profiles in patients with PD based on RAVLT scores (lowest area under the curve [AUC] of 0.979, for classification; highest root mean squared percentage [RMSPE] of 17.2%, for regression) using relatively bias-free clinical data, such as sex, age, and body mass index (BMI).

CONCLUSIONS

Our findings also suggested that BMI, used as a proxy for diet and exercises habits, plays an important role in declarative memory. Our framework can be extended and used as a prospective tool to classify and examine associations between clinical features and declarative memory in PD patients.

The association between functional social support and memory in middle-aged and older adults: A Prospective Analysis of the Canadian Longitudinal Study on Aging's Comprehensive Cohort

BACKGROUND

Functional social support (FSS) impacts memory function through biological and psychological pathways. In a national sample of middle-aged and older adults in Canada, we explored the association between FSS and changes in memory over three years and investigated effect modification by age group and sex.

METHODS

We analyzed data from the Comprehensive Cohort of the Canadian Longitudinal Study on Aging (CLSA). FSS was measured with the Medical Outcomes Study - Social Support Survey; memory was measured with combined z-scores from immediate and delayed recall administrations of a modified version of the Rey Auditory Verbal Learning Test. We regressed memory change scores over three years on baseline overall FSS and four FSS subtypes in separate multiple linear regression models, controlling for sociodemographic, health, and lifestyle covariates. We also stratified our models by age group and sex.

RESULT

We found positive associations between higher FSS and improvement in memory score, although only the tangible FSS subtype (availability of practical assistance) was significantly associated with changes in memory (β^ = 0.07; 95% confidence interval = 0.01, 0.14). After stratification by age group and sex, this association remained significant for males, although we found no evidence of effect modification.

CONCLUSION

In a cognitively healthy sample of middle-aged and older adults, we found a statistically significant and positive association between tangible FSS and memory change over three years of follow-up. We did not find adults with low FSS to be at increased risk of memory decline compared to adults with higher FSS.

Screening strategies and dynamic risk prediction models for Alzheimer's disease

BACKGROUND

Characterizing the progression from Mild cognitive impairment (MCI) to Alzheimer's disease (AD) is essential for early AD prevention and targeted intervention. Our goal was to construct precise screening schemes for individuals with different risk of AD and to establish prognosis models for them.

METHODS

We constructed a retrospective cohort by reviewing individuals with baseline diagnosis of MCI and at least one follow-up visits between November 2005 and May 2021. They were stratified into high-risk and low-risk groups with longitudinal cognitive trajectory. Then, we established a screening framework and obtained optimal screening strategies for two risk groups. Cox and random survival forest (RSF) models were developed for dynamic prognosis prediction.

RESULTS

In terms of screening strategies, the combination of Clinical Dementia Rating Sum of Boxes (CDRSB) and hippocampus volume was recommended for the high-risk MCI group, while the combination of Alzheimer's Disease Assessment Scale Cognitive 13 items (ADAS13) and FAQ was recommended for low-risk MCI group. The concordance index (C-index) of the Cox model for the high-risk group was 0.844 (95% CI: 0.815-0.873) and adjustments for demographic information and APOE ε4. The RSF model incorporating longitudinal ADAS13, FAQ, and demographic information and APOE ε4 performed for the low-risk group.

CONCLUSION

This precise screening scheme will optimize allocation of medical resources and reduce the economic burden on individuals with low risk of MCI. Moreover, dynamic prognosis models may be helpful for early identification of individuals at risk and clinical decisions, which will promote the secondary prevention of AD.

Atrophy of specific amygdala subfields in subjects converting to mild cognitive impairment

Introduction

Accumulating evidence indicates that the amygdala exhibits early signs of Alzheimer's disease (AD) pathology. However, it is still unknown whether the atrophy of distinct subfields of the amygdala also participates in the transition from healthy cognition to mild cognitive impairment (MCI).

Methods

Our sample was derived from the AD Neuroimaging Initiative 3 and consisted of 97 cognitively healthy (HC) individuals, sorted into two groups based on their clinical follow-up: 75 who remained stable (s-HC) and 22 who converted to MCI within 48 months (c-HC). Anatomical magnetic resonance (MR) images were analyzed using a semi-automatic approach that combines probabilistic methods and a priori information from ex vivo MR images and histology to segment and obtain quantitative structural metrics for different amygdala subfields in each participant. Spearman's correlations were performed between MR measures and baseline and longitudinal neuropsychological measures. We also included anatomical measurements of the whole amygdala, the hippocampus, a key target of AD-related pathology, and the whole cortical thickness as a test of spatial specificity.

Results

Compared with s-HC individuals, c-HC subjects showed a reduced right amygdala volume, whereas no significant difference was observed for hippocampal volumes or changes in cortical thickness. In the amygdala subfields, we observed selected atrophy patterns in the basolateral nuclear complex, anterior amygdala area, and transitional area. Macro-structural alterations in these subfields correlated with variations of global indices of cognitive performance (measured at baseline and the 48-month follow-up), suggesting that amygdala changes shape the cognitive progression to MCI.

Discussion

Our results provide anatomical evidence for the early involvement of the amygdala in the preclinical stages of AD.

Highlights

Amygdala's atrophy marks elderly progression to mild cognitive impairment (MCI).Amygdala's was observed within the basolateral and amygdaloid complexes.Macro-structural alterations were associated with cognitive decline.No atrophy was found in the hippocampus and cortex.

Surface-based correlates of cognition along the Alzheimer's continuum in a memory clinic population

Composite cognitive measures in large-scale studies with biomarker data for amyloid and tau have been widely used to characterize Alzheimer's disease (AD). However, little is known about how the findings from these studies translate to memory clinic populations without biomarker data, using single measures of cognition. Additionally, most studies have utilized voxel-based morphometry or limited surface-based morphometry such as cortical thickness, to measure the neurodegeneration associated with cognitive deficits. In this study, we aimed to replicate and extend the biomarker, composite study relationships using expanded surface-based morphometry and single measures of cognition in a memory clinic population. We examined 271 clinically diagnosed symptomatic individuals with mild cognitive impairment (N = 93) and Alzheimer's disease dementia (N = 178), as well as healthy controls (N = 29). Surface-based morphometry measures included cortical thickness, sulcal depth, and gyrification index within the "signature areas" of Alzheimer's disease. The cognitive variables pertained to hallmark features of Alzheimer's disease including verbal learning, verbal memory retention, and language, as well as executive function. The results demonstrated that verbal learning, language, and executive function correlated with the cortical thickness of the temporal, frontal, and parietal areas. Verbal memory retention was correlated to the thickness of temporal regions and gyrification of the inferior temporal gyrus. Language was related to the temporal regions and the supramarginal gyrus' sulcal depth and gyrification index. Executive function was correlated with the medial temporal gyrus and supramarginal gyrus sulcal depth, and the gyrification index of temporal regions and supramarginal gyrus, but not with the frontal areas. Predictions of each of these cognitive measures were dependent on a combination of structures and each of the morphometry measurements, and often included medial temporal gyrus thickness and sulcal depth. Overall, the results demonstrated that the relationships between cortical thinning and cognition are widespread and can be observed using single measures of cognition in a clinically diagnosed AD population. The utility of sulcal depth and gyrification index measures may be more focal to certain brain areas and cognitive measures. The relative importance of temporal, frontal, and parietal regions in verbal learning, language, and executive function, but not verbal memory retention, was replicated in this clinic cohort.

Novel learning ratio from the NAB list learning test distinguishes between clinical groups: clinical validation and sex-related differences

List-learning tasks provide a wealth of information about an individual's cognitive abilities: attention, encoding, storage, retrieval, recognition. A more recently developed metric, the Learning Ratio (LR), supplements information about cognitive ability and can assist the clinician in determining whether an individual has cognitive impairment. The LR is calculated by taking the difference between the individuals' raw score on the first learning trial and their raw score on the last learning trial, which is then divided by the number of words left to be learned after the first learning trial. A LR derived from the list-learning task from the Neuropsychological Assessment Battery (NAB) was evaluated to determine ability to distinguish those with normal cognition from those with mild cognitive impairment (MCI) and dementia. Results from the present study indicate the NAB LR is able to distinguish between clinical groups; recommended cutoffs for the NAB LR scores are provided. We also found a significant female sex-advantage for the NAB LR in those with normal memory ability and demonstrated the female sex advantage decreased with increasing memory impairment. Taken together, the NAB LR may assist clinicians in making an accurate and early diagnosis and may be helpful for tracking learning and functioning across multiple assessments. .

A framework of biomarkers for brain aging: a consensus statement by the Aging Biomarker Consortium

China and the world are facing severe population aging and an increasing burden of age-related diseases. Aging of the brain causes major age-related brain diseases, such as neurodegenerative diseases and stroke. Identifying biomarkers for the effective assessment of brain aging and establishing a brain aging assessment system could facilitate the development of brain aging intervention strategies and the effective prevention and treatment of aging-related brain diseases. Thus, experts from the Aging Biomarker Consortium (ABC) have combined the latest research results and practical experience to recommend brain aging biomarkers and form an expert consensus, aiming to provide a basis for assessing the degree of brain aging and conducting brain-aging-related research with the ultimate goal of improving the brain health of elderly individuals in both China and the world.

The use of hippocampal grading as a biomarker for preclinical and prodromal Alzheimer's disease

Hippocampal changes are associated with increased age and cognitive decline due to mild cognitive impairment (MCI) and Alzheimer's disease (AD). These associations are often observed only in the later stages of decline. This study examined if hippocampal grading, a method measuring local morphological similarity of the hippocampus to cognitively normal controls (NCs) and AD participants, is associated with cognition in NCs, subjective cognitive decline (SCD), early (eMCI), late (lMCI), and AD. A total of 1620 Alzheimer's Disease Neuroimaging Initiative participants were examined (495 NC, 262 eMCI, 545 lMCI, and 318 AD) because they had baseline MRIs and Alzheimer's disease Assessment Scale (ADAS-13) and Clinical Dementia Rating-Sum of Boxes (CDR-SB) scores. In a sub-analysis, NCs with episodic memory scores (as measured by Rey Auditory Verbal Learning Test, RAVLT) were divided into those with subjective cognitive decline (SCD+; 103) and those without (SCD-; 390). Linear regressions evaluated the influence of hippocampal grading on cognition in preclinical and prodromal AD. Lower global cognition, as measured by increased ADAS-13, was associated with hippocampal grading: NC (p < .001), eMCI (p < .05), lMCI (p < .05), and AD (p = .01). Lower global cognition as measured increased CDR-SB was associated with hippocampal grading in lMCI (p < .05) and AD (p < .001). Lower RAVLT performance was associated with hippocampal grading in SCD- (p < .05) and SCD+ (p < .05). These findings suggest that hippocampal grading is associated with global cognition in NC, eMCI, lMCI, and AD. Early changes in episodic memory during pre-clinical AD are associated with changes in hippocampal grading. Hippocampal grading may be sensitive to progressive changes early in the disease course.

Connectome-based predictive modeling shows sex differences in brain-based predictors of memory performance

Alzheimer's disease (AD) takes a more aggressive course in women than men, with higher prevalence and faster progression. Amnestic AD specifically targets the default mode network (DMN), which subserves short-term memory; past research shows relative hyperconnectivity in the posterior DMN in aging women. Higher reliance on this network during memory tasks may contribute to women's elevated AD risk. Here, we applied connectome-based predictive modeling (CPM), a robust linear machine-learning approach, to the Lifespan Human Connectome Project-Aging (HCP-A) dataset (n = 579). We sought to characterize sex-based predictors of memory performance in aging, with particular attention to the DMN. Models were evaluated using cross-validation both across the whole group and for each sex separately. Whole-group models predicted short-term memory performance with accuracies ranging from ρ = 0.21-0.45. The best-performing models were derived from an associative memory task-based scan. Sex-specific models revealed significant differences in connectome-based predictors for men and women. DMN activity contributed more to predicted memory scores in women, while within- and between- visual network activity contributed more to predicted memory scores in men. While men showed more segregation of visual networks, women showed more segregation of the DMN. We demonstrate that women and men recruit different circuitry when performing memory tasks, with women relying more on intra-DMN activity and men relying more on visual circuitry. These findings are consistent with the hypothesis that women draw more heavily upon the DMN for recollective memory, potentially contributing to women's elevated risk of AD.

Patterns of structure-function association in normal aging and in Alzheimer's disease: Screening for mild cognitive impairment and dementia with ML regression and classification models

Background

The combined analysis of imaging and functional modalities is supposed to improve diagnostics of neurodegenerative diseases with advanced data science techniques.

Objective

To get an insight into normal and accelerated brain aging by developing the machine learning models that predict individual performance in neuropsychological and cognitive tests from brain MRI. With these models we endeavor to look for patterns of brain structure-function association (SFA) indicative of mild cognitive impairment (MCI) and Alzheimer's dementia.

Materials and methods

We explored the age-related variability of cognitive and neuropsychological test scores in normal and accelerated aging and constructed regression models predicting functional performance in cognitive tests from brain radiomics data. The models were trained on the three study cohorts from ADNI dataset-cognitively normal individuals, patients with MCI or dementia-separately. We also looked for significant correlations between cortical parcellation volumes and test scores in the cohorts to investigate neuroanatomical differences in relation to cognitive status. Finally, we worked out an approach for the classification of the examinees according to the pattern of structure-function associations into the cohorts of the cognitively normal elderly and patients with MCI or dementia.

Results

In the healthy population, the global cognitive functioning slightly changes with age. It also remains stable across the disease course in the majority of cases. In healthy adults and patients with MCI or dementia, the trendlines of performance in digit symbol substitution test and trail making test converge at the approximated point of 100 years of age. According to the SFA pattern, we distinguish three cohorts: the cognitively normal elderly, patients with MCI, and dementia. The highest accuracy is achieved with the model trained to predict the mini-mental state examination score from voxel-based morphometry data. The application of the majority voting technique to models predicting results in cognitive tests improved the classification performance up to 91.95% true positive rate for healthy participants, 86.21%-for MCI and 80.18%-for dementia cases.

Conclusion

The machine learning model, when trained on the cases of this of that group, describes a disease-specific SFA pattern. The pattern serves as a "stamp" of the disease reflected by the model.

Cognitive and behavioral abnormalities in individuals with Alzheimer’s disease, mild cognitive impairment, and subjective memory complaints

In this study, we investigated the ability of commonly used neuropsychological tests to detect cognitive and functional decline across the Alzheimer’s disease (AD) continuum. Moreover, as preclinical AD is a key area of investigation, we focused on the ability of neuropsychological tests to distinguish the early stages of the disease, such as individuals with Subjective Memory Complaints (SMC). This study included 595 participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset who were cognitively normal (CN), SMC, mild cognitive impairment (MCI; early or late stage), or AD. Our cognitive measures included the Rey Auditory Verbal Learning Test (RAVLT), the Everyday Cognition Questionnaire (ECog), the Functional Abilities Questionnaire (FAQ), the Alzheimer’s Disease Assessment Scale–Cognitive Subscale (ADAS-Cog), the Montreal Cognitive Assessment scale (MoCA), and the Trail Making test (TMT-B). Overall, our results indicated that the ADAS-13, RAVLT (learning), FAQ, ECog, and MoCA were all predictive of the AD progression continuum. However, TMT-B and the RAVLT (immediate and forgetting) were not significant predictors of the AD continuum. Indeed, contrary to our expectations ECog self-report (partner and patient) were the two strongest predictors in the model to detect the progression from CN to AD. Accordingly, we suggest using the ECog (both versions), RAVLT (learning), ADAS-13, and the MoCA to screen all stages of the AD continuum. In conclusion, we infer that these tests could help clinicians effectively detect the early stages of the disease (e.g., SMC) and distinguish the different stages of AD.

Episodic Memory-Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer's Disease: A Multicenter Study Based on Machine Learning

BACKGROUND

Individualized and reliable biomarkers are crucial for diagnosing Alzheimer's disease (AD). However, lack of accessibility and neurobiological correlation are the main obstacles to their clinical application. Machine learning algorithms can effectively identify personalized biomarkers based on the prominent symptoms of AD.

METHODS

Episodic memory-related magnetic resonance imaging (MRI) features of 143 patients with amnesic mild cognitive impairment (MCI) were identified using a multivariate relevance vector regression algorithm. The support vector machine classification model was constructed using these MRI features and verified in 2 independent datasets (N = 994). The neurobiological basis was also investigated based on cognitive assessments, neuropathologic biomarkers of cerebrospinal fluid, and positron emission tomography images of amyloid-β plaques.

RESULTS

The combination of gray matter volume and amplitude of low-frequency fluctuation MRI features accurately predicted episodic memory impairment in individual patients with amnesic MCI (r = 0.638) when measured using an episodic memory assessment panel. The MRI features that contributed to episodic memory prediction were primarily distributed across the default mode network and limbic network. The classification model based on these features distinguished patients with AD from normal control subjects with more than 86% accuracy. Furthermore, most identified episodic memory-related regions showed significantly different amyloid-β positron emission tomography measurements among the AD, MCI, and normal control groups. Moreover, the classification outputs significantly correlated with cognitive assessment scores and cerebrospinal fluid pathological biomarkers' levels in the MCI and AD groups.

CONCLUSIONS

Neuroimaging features can reflect individual episodic memory function and serve as potential diagnostic biomarkers of AD.

Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression

We consider the problem of predicting how the likelihood of an outcome of interest for a patient changes over time as we observe more of the patient's data. To solve this problem, we propose a supervised contrastive learning framework that learns an embedding representation for each time step of a patient time series. Our framework learns the embedding space to have the following properties: (1) nearby points in the embedding space have similar predicted class probabilities, (2) adjacent time steps of the same time series map to nearby points in the embedding space, and (3) time steps with very different raw feature vectors map to far apart regions of the embedding space. To achieve property (3), we employ a nearest neighbor pairing mechanism in the raw feature space. This mechanism also serves as an alternative to "data augmentation", a key ingredient of contrastive learning, which lacks a standard procedure that is adequately realistic for clinical tabular data, to our knowledge. We demonstrate that our approach outperforms state-of-the-art baselines in predicting mortality of septic patients (MIMIC-III dataset) and tracking progression of cognitive impairment (ADNI dataset). Our method also consistently recovers the correct synthetic dataset embedding structure across experiments, a feat not achieved by baselines. Our ablation experiments show the pivotal role of our nearest neighbor pairing.

The Effect of Surgical Weight Loss on Cognition in Individuals with Class II/III Obesity

BACKGROUND

Obesity is a global epidemic and is associated with cognitive impairment and dementia. It remains unknown whether weight loss interventions, such as bariatric surgery, can mitigate cognitive impairment.

OBJECTIVES

We aimed to determine the effect of surgical weight loss on cognition in individuals with class II/III obesity.

DESIGN

We performed a prospective cohort study of participants who underwent bariatric surgery. At baseline and two years following surgery, participants completed metabolic risk factor and neuropsychological assessments.

SETTING

Participants were enrolled from an academic suburban bariatric surgery clinic.

PARTICIPANTS

There were 113 participants who completed baseline assessments and 87 completed two-year follow-up assessments (66 in-person and 21 virtual) after bariatric surgery. The mean (SD) age was 46.8 (12.5) years and 64 (73.6%) were female.

INTERVENTION

Bariatric surgery. There were 77 (88.5%) participants that underwent sleeve gastrectomy and 10 (11.5%) that underwent gastric bypass surgery.

MEASUREMENTS

Cognition was assessed using the NIH toolbox cognitive battery (NIHTB-CB) and the Rey Auditory Verbal Learning Test (AVLT). The primary outcome was the change in NIHTB-CB fluid composite score before and after surgery.

RESULTS

The primary outcome, NIHTB-CB composite score, was stable following bariatric surgery (-0.4 (13.9), p=0.81,n=66). Among secondary outcomes, the NIHTB-CB dimensional card sorting test (executive function assessment), improved (+6.5 (19.9),p=0.01,n=66) while the Rey AVLT delayed recall test (memory assessment) declined (-0.24 (0.83),p=0.01,n=87) following surgery. Improvements to metabolic risk factors and diabetes complications were not associated with improvements to NIHTB-CB composite score. The other 4 NIHTB-CB subtests and Rey AVLT assessments of auditory learning and recognition were stable at follow-up.

CONCLUSIONS

Following bariatric surgery, the age-adjusted composite cognitive outcome did not change, but an executive subtest score improved. These results suggest that bariatric surgery may mitigate the natural history of cognitive decline in individuals with obesity, which is expected to be faster than normal aging, but confirmatory randomized controlled trials are needed. The decline in delayed recall also warrants further studies to determine potential differential effects on cognitive subtests.

Trajectories of Cognitive Impairment in Adults Bearing Vascular Risk Factors, with or without Diagnosis of Mild Cognitive Impairment: Findings from a Longitudinal Study Assessing Executive Functions, Memory, and Social Cognition

With the aging of the population, a key concern of both societies and health services is to keep the population cognitively healthy until the maximum age limit. It is a well-known fact that vascular aging has a negative effect on the cognitive skills of adults, putting them at greater risk of developing dementia. The present longitudinal study aimed to evaluate the main dimensions of cognition in two pathological groups with different health profiles: a group of adults with vascular risk factors (VRF) (n = 35) and a group of adults with vascular risk factors and mild cognitive impairment (VRF + MCI) (n = 35). The two groups were matched in age, education, and gender. They were assessed with extensive neuropsychological testing at three different times with a distance of about 8 months between them; the assessment regarded executive functions, memory capacity, and Theory of Mind abilities. The analyses carried out were (a) mixed-measures ANOVA, (b) repeated measures ANOVA, and (c) ANOVA. The findings showed that global cognitive status and short-term memory are the main cognitive abilities that decline in community dwelling people bearing VRF. Hence, this group of adults should be examined at least every 2 years for this decline. As regards people with both VRF and MCI, it seems that the assessment of Theory of Mind abilities can better capture their further impairment. Global cognitive status, task/rule switching function, and long-term memory (delayed verbal recall) were revealed as the abilities that clearly and steadily differentiate VRF people with and without MCI.

Depressive symptoms in cognitively unimpaired older adults are associated with lower structural and functional integrity in a frontolimbic network

Subclinical depressive symptoms are associated with increased risk of Alzheimer's disease (AD), but the brain mechanisms underlying this relationship are still unclear. We aimed to provide a comprehensive overview of the brain substrates of subclinical depressive symptoms in cognitively unimpaired older adults using complementary multimodal neuroimaging data. We included cognitively unimpaired older adults from the baseline data of the primary cohort Age-Well (n = 135), and from the replication cohort ADNI (n = 252). In both cohorts, subclinical depressive symptoms were assessed using the 15-item version of the Geriatric Depression Scale; based on this scale, participants were classified as having depressive symptoms (>0) or not (0). Voxel-wise between-group comparisons were performed to highlight differences in gray matter volume, glucose metabolism and amyloid deposition; as well as white matter integrity (only available in Age-Well). Age-Well participants with subclinical depressive symptoms had lower gray matter volume in the hippocampus and lower white matter integrity in the fornix and the posterior parts of the cingulum and corpus callosum, compared to participants without symptoms. Hippocampal atrophy was recovered in ADNI, where participants with subclinical depressive symptoms also showed glucose hypometabolism in the hippocampus, amygdala, precuneus/posterior cingulate cortex, medial and dorsolateral prefrontal cortex, insula, and temporoparietal cortex. Subclinical depressive symptoms were not associated with brain amyloid deposition in either cohort. Subclinical depressive symptoms in ageing are linked with neurodegeneration biomarkers in the frontolimbic network including brain areas particularly sensitive to AD. The relationship between depressive symptoms and AD may be partly underpinned by neurodegeneration in common brain regions.

Recent progress on the role of non-coding RNA in postoperative cognitive dysfunction

Postoperative cognitive dysfunction (POCD), especially in elderly patients, is a serious complication characterized by impairment of cognitive and sensory modalities after surgery. The pathogenesis of POCD mainly includes neuroinflammation, neuronal apoptosis, oxidative stress, accumulation of Aβ, and tau hyperphosphorylation; however, the exact mechanism remains unclear. Non-coding RNA (ncRNA) may play an important role in POCD. Some evidence suggests that microRNA, long ncRNA, and circular RNA can regulate POCD-related processes, making them promising biomarkers in POCD diagnosis, treatment, and prognosis. This article reviews the crosstalk between ncRNAs and POCD, and systematically discusses the role of ncRNAs in the pathogenesis and diagnosis of POCD. Additionally, we explored the possible mechanisms of ncRNA-associated POCD, providing new knowledge for developing ncRNA-based treatments for POCD.

Integration of GWAS and brain transcriptomic analyses in a multiethnic sample of 35,245 older adults identifies DCDC2 gene as predictor of episodic memory maintenance

Identifying genes underlying memory function will help characterize cognitively resilient and high-risk declining subpopulations contributing to precision medicine strategies. We estimated episodic memory trajectories in 35,245 ethnically diverse older adults representing eight independent cohorts. We conducted apolipoprotein E (APOE)-stratified genome-wide association study (GWAS) analyses and combined individual cohorts' results via meta-analysis. Three independent transcriptomics datasets were used to further interpret GWAS signals. We identified DCDC2 gene significantly associated with episodic memory (Pmeta = 3.3 x 10^-8 ) among non-carriers of APOE ε4 (N = 24,941). Brain transcriptomics revealed an association between episodic memory maintenance and (1) increased dorsolateral prefrontal cortex DCDC2 expression (P = 3.8 x 10^-4 ) and (2) lower burden of pathological Alzheimer's disease (AD) hallmarks (paired helical fragment tau P = .003, and amyloid beta load P = .008). Additional transcriptomics results comparing AD and cognitively healthy brain samples showed a downregulation of DCDC2 levels in superior temporal gyrus (P = .007) and inferior frontal gyrus (P = .013). Our work identified DCDC2 gene as a novel predictor of memory maintenance.

SVR-based Multimodal Active Subspace Analysis for the Brain using Neuroimaging Data.. [DOI: 10.1101/2022.07.28.501879] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Understanding the patterns of changes in brain function and structure due to various disorders and diseases is of utmost importance. There have been numerous efforts toward successful biomarker discovery for complex brain disorders by evaluating neuroimaging datasets with novel analytical frameworks. However, due to the multi-faceted nature of the disorders involving a wide and overlapping range of symptoms as well as complex changes in structural and functional brain networks, it is increasingly important to devise computational frameworks that can consider the underlying patterns of heterogeneous changes with specific target assessments, at the same time producing a summarizing output from the high-dimensional neuroimaging data. While various machine learning approaches focus on diagnostic prediction, many learning frameworks analyze important features at the level of brain regions involved in prediction using supervised methods. Unsupervised learning methods have also been utilized to break down the neuroimaging features into lower dimensional components. However, most learning frameworks either do not consider the target assessment information while extracting brain subspaces, or can extract only higher dimensional importance associations as an ordered list of involved features, making manual interpretation at the level of subspaces difficult. We present a novel multimodal active subspace learning framework to understand various subspaces within the brain that are associated with changes in particular biological and cognitive traits. For a given cognitive or biological trait, our framework performs a decomposition of the feature importances to extract robust multimodal subspaces that define the most significant change in the given trait. Through a rigorous cross-validation procedure on an Alzheimer’s disease (AD) dataset, we show that our framework can extract subspaces covering both functional and structural modalities, which are specific to a given clinical assessment (like memory and other cognitive skills) and also retain predictive performance in standard machine learning algorithms. We show that our framework not only uncovers AD-related brain regions (e.g., hippocampus, entorhinal cortex) in the associated brain subspaces, but also enables an automated identification of multiple underlying structural and functional sub-systems of the brain that collectively characterize changes in memory and cognitive skill proficiency related to brain disorders like AD.

The Role of Entropy in Construct Specification Equations (CSE) to Improve the Validity of Memory Tests: Extension to Word Lists

Metrological methods for word learning list tests can be developed with an information theoretical approach extending earlier simple syntax studies. A classic Brillouin entropy expression is applied to the analysis of the Rey’s Auditory Verbal Learning Test RAVLT (immediate recall), where more ordered tasks—with less entropy—are easier to perform. The findings from three case studies are described, including 225 assessments of the NeuroMET2 cohort of persons spanning a cognitive spectrum from healthy older adults to patients with dementia. In the first study, ordinality in the raw scores is compensated for, and item and person attributes are separated with the Rasch model. In the second, the RAVLT IR task difficulty, including serial position effects (SPE), particularly Primacy and Recency, is adequately explained (Pearson’s correlation R=0.80) with construct specification equations (CSE). The third study suggests multidimensionality is introduced by SPE, as revealed through goodness-of-fit statistics of the Rasch analyses. Loading factors common to two kinds of principal component analyses (PCA) for CSE formulation and goodness-of-fit logistic regressions are identified. More consistent ways of defining and analysing memory task difficulties, including SPE, can maintain the unique metrological properties of the Rasch model and improve the estimates and understanding of a person’s memory abilities on the path towards better-targeted and more fit-for-purpose diagnostics.

Categorical predictive and disease progression modeling in the early stage of Alzheimer's disease

BACKGROUND

A preclinical stage of Alzheimer's disease (AD) precedes the symptomatic phases of mild cognitive impairment (MCI) and dementia, which constitutes a window of opportunities for preventive therapies or delaying dementia onset.

NEW METHOD

We propose to use categorical predictive models based on survival analysis with longitudinal data which are capable of determining subsets of markers to classify cognitively unimpaired (CU) subjects who progress into MCI/dementia or not. Subsequently, the proposed combination of markers was used to construct disease progression models (DPMs), which reveal long-term pathological trajectories from short-term clinical data. The proposed methodology was applied to a population recruited by the ADNI.

RESULTS

A very small subset of standard MRI-based data, CSF markers and cognitive measures was used to predict CU-to-MCI/dementia progression. The longitudinal data of these selected markers were used to construct DPMs using the algorithms of growth models by alternating conditional expectation (GRACE) and the latent time joint mixed effects model (LTJMM). The results show that the natural history of the proposed cognitive decline classifies the subjects well according to the clinical groups and shows a moderate correlation between the conversion times and their estimates by the algorithms.

COMPARISON WITH EXISTING METHODS

Unlike the training of the DPM algorithms without preselection of the markers, here, it is proposed to construct and evaluate the DPMs using the subsets of markers defined by the categorical predictive models.

CONCLUSIONS

The estimates of the natural history of the proposed cognitive decline from GRACE were more robust than those using LTJMM. The transition from normal to cognitive decline is mostly associated with an increase in temporal atrophy, worsening of clinical scores and pTAU/Aβ. Furthermore, pTAU/Aβ, Everyday Cognition score and the normalized volume of the entorhinal cortex show alterations of more than 20% fifteen years before the onset of cognitive decline.

Effect of acupuncture on gut microbiota in participants with subjective cognitive decline

A close relationship has recently been described between subjective cognitive decline (SCD) and gut microbiota disorders. Herein, we aim to investigate the effect of electroacupuncture (EA) on gut microbiota in participants with SCD.We conducted a study of 60 participants with SCD. Sixty participants were allocated to either EA group (n = 30) or sham acupuncture group (n = 30). Both groups received 24 sessions of real acupuncture treatment or identical treatment sessions using the placebo needle. Global cognitive change based on a comprehensive neuropsychological test battery was evaluated to detect the clinical efficacy of acupuncture treatment at the baseline and the end of treatment. Faecal microbial analyses were carried out after collecting stools at T0 and T12 weeks. Microbiomes were analyzed by 16S ribosomal RNA gene sequencing. Correlation analyses were performed to investigate the relationships between the changes in gut microbiota and symptom improvement.Age is a particularly important factor leading to the severity of dementia. Compared with sham acupuncture group, the number of Escherichia-Shigella in EA group decreased after treatment. The number of Escherichia-Shigella in EA group decreased after treatment compared with EA group before treatment. Bifidobacterium is positively correlated with clinical efficacy Z-score and Montreal Cognitive Assessment Scale (both P < .005).Acupuncture could improve global cognitive change among SCD participants by regulating the intestinal flora. Dysbiosis was found in the gut microbiome in SCD and partially relieved by acupuncture. Our study suggests that gut microbiota could be a potential therapeutic target and diagnostic biomarker for SCD.

Mapping cerebral atrophic trajectory from amnestic mild cognitive impairment to Alzheimer's disease

Alzheimer's disease (AD) patients suffer progressive cerebral atrophy before dementia onset. However, the region-specific atrophic processes and the influences of age and apolipoprotein E (APOE) on atrophic trajectory are still unclear. By mapping the region-specific nonlinear atrophic trajectory of whole cerebrum from amnestic mild cognitive impairment (aMCI) to AD based on longitudinal structural magnetic resonance imaging data from Alzheimer's disease Neuroimaging Initiative (ADNI) database, we unraveled a quadratic accelerated atrophic trajectory of 68 cerebral regions from aMCI to AD, especially in the superior temporal pole, caudate, and hippocampus. Besides, interaction analyses demonstrated that APOE ε4 carriers had faster atrophic rates than noncarriers in 8 regions, including the caudate, hippocampus, insula, etc.; younger patients progressed faster than older patients in 32 regions, especially for the superior temporal pole, hippocampus, and superior temporal gyrus; and 15 regions demonstrated complex interaction among age, APOE, and disease progression, including the caudate, hippocampus, etc. (P < 0.05/68, Bonferroni correction). Finally, Cox proportional hazards regression model based on the identified region-specific biomarkers could effectively predict the time to AD conversion within 10 years. In summary, cerebral atrophic trajectory mapping could help a comprehensive understanding of AD development and offer potential biomarkers for predicting AD conversion.

Locus coeruleus integrity is related to tau burden and memory loss in autosomal-dominant Alzheimer's disease

Abnormally phosphorylated tau, an indicator of Alzheimer's disease, accumulates in the first decades of life in the locus coeruleus (LC), the brain's main noradrenaline supply. However, technical challenges in in-vivo assessments have impeded research into the role of the LC in Alzheimer's disease. We studied participants with or known to be at-risk for mutations in genes causing autosomal-dominant Alzheimer's disease (ADAD) with early onset, providing a unique window into the pathogenesis of Alzheimer's largely disentangled from age-related factors. Using high-resolution MRI and tau PET, we found lower rostral LC integrity in symptomatic participants. LC integrity was associated with individual differences in tau burden and memory decline. Post-mortem analyses in a separate set of carriers of the same mutation confirmed substantial neuronal loss in the LC. Our findings link LC degeneration to tau burden and memory in Alzheimer's, and highlight a role of the noradrenergic system in this neurodegenerative disease.

The Contribution of Working Memory Areas to Verbal Learning and Recall in Primary Progressive Aphasia

Recent evidence of domain-specific working memory (WM) systems has identified the areas and networks which are involved in phonological, orthographic, and semantic WM, as well as in higher level domain-general WM functions. The contribution of these areas throughout the process of verbal learning and recall is still unclear. In the present study, we asked, what is the contribution of domain-specific specialized WM systems in the course of verbal learning and recall? To answer this question, we regressed the perfusion data from pseudo-continuous arterial spin labeling (pCASL) MRI with all the immediate, consecutive, and delayed recall stages of the Rey Auditory Verbal Learning Test (RAVLT) from a group of patients with Primary Progressive Aphasia (PPA), a neurodegenerative syndrome in which language is the primary deficit. We found that the early stages of verbal learning involve the areas with subserving phonological processing (left superior temporal gyrus), as well as semantic WM memory (left angular gyrus, AG_L). As learning unfolds, areas with subserving semantic WM (AG_L), as well as lexical/semantic (inferior temporal and fusiform gyri, temporal pole), and episodic memory (hippocampal complex) become more involved. Finally, a delayed recall depends entirely on semantic and episodic memory areas (hippocampal complex, temporal pole, and gyri). Our results suggest that AG_L subserving domain-specific (semantic) WM is involved only during verbal learning, but a delayed recall depends only on medial and cortical temporal areas.