Multiomics analysis to explore blood metabolite biomarkers in an Alzheimer's Disease Neuroimaging Initiative cohort.

Alzheimer's disease (AD) is a neurodegenerative disease that commonly causes dementia. Identifying biomarkers for the early detection of AD is an emerging need, as brain dysfunction begins two decades before the onset of clinical symptoms. To this end, we reanalyzed untargeted metabolomic mass spectrometry data from 905 patients enrolled in the AD Neuroimaging Initiative (ADNI) cohort using MS-DIAL, with 1,304,633 spectra of 39,108 unique biomolecules. Metabolic profiles of 93 hydrophilic metabolites were determined. Additionally, we integrated targeted lipidomic data (4873 samples from 1524 patients) to explore candidate biomarkers for predicting progressive mild cognitive impairment (pMCI) in patients diagnosed with AD within two years using the baseline metabolome. Patients with lower ergothioneine levels had a 12% higher rate of AD progression with the significance of P = 0.012 (Wald test). Furthermore, an increase in ganglioside (GM3) and decrease in plasmalogen lipids, many of which are associated with apolipoprotein E polymorphism, were confirmed in AD patients, and the higher levels of lysophosphatidylcholine (18:1) and GM3 d18:1/20:0 showed 19% and 17% higher rates of AD progression, respectively (Wald test: P = 3.9 × 10-8 and 4.3 × 10-7). Palmitoleamide, oleamide, diacylglycerols, and ether lipids were also identified as significantly altered metabolites at baseline in patients with pMCI. The integrated analysis of metabolites and genomics data showed that combining information on metabolites and genotypes enhances the predictive performance of AD progression, suggesting that metabolomics is essential to complement genomic data. In conclusion, the reanalysis of multiomics data provides new insights to detect early development of AD pathology and to partially understand metabolic changes in age-related onset of AD.

Neuron-level explainable AI for Alzheimer's Disease assessment from fundus images.

Alzheimer's Disease (AD) is a progressive neurodegenerative disease and the leading cause of dementia. Early diagnosis is critical for patients to benefit from potential intervention and treatment. The retina has emerged as a plausible diagnostic site for AD detection owing to its anatomical connection with the brain. However, existing AI models for this purpose have yet to provide a rational explanation behind their decisions and have not been able to infer the stage of the disease's progression. Along this direction, we propose a novel model-agnostic explainable-AI framework, called Granu la ̲ r Neuron-le v ̲ el Expl a ̲ iner (LAVA), an interpretation prototype that probes into intermediate layers of the Convolutional Neural Network (CNN) models to directly assess the continuum of AD from the retinal imaging without the need for longitudinal or clinical evaluations. This innovative approach aims to validate retinal vasculature as a biomarker and diagnostic modality for evaluating Alzheimer's Disease. Leveraged UK Biobank cognitive tests and vascular morphological features demonstrate significant promise and effectiveness of LAVA in identifying AD stages across the progression continuum.

Central inhibition of stearoyl-CoA desaturase has minimal effects on the peripheral metabolic symptoms of the 3xTg Alzheimer's disease mouse model.

Evidence from genetic and epidemiological studies point to lipid metabolism defects in both the brain and periphery being at the core of Alzheimer's disease (AD) pathogenesis. Previously, we reported that central inhibition of the rate-limiting enzyme in monounsaturated fatty acid synthesis, stearoyl-CoA desaturase (SCD), improves brain structure and function in the 3xTg mouse model of AD (3xTg-AD). Here, we tested whether these beneficial central effects involve recovery of peripheral metabolic defects, such as fat accumulation and glucose and insulin handling. As early as 3 months of age, 3xTg-AD mice exhibited peripheral phenotypes including increased body weight and visceral and subcutaneous white adipose tissue as well as diabetic-like peripheral gluco-regulatory abnormalities. We found that intracerebral infusion of an SCD inhibitor that normalizes brain fatty acid desaturation, synapse loss and learning and memory deficits in middle-aged memory-impaired 3xTg-AD mice did not affect these peripheral phenotypes. This suggests that the beneficial effects of central SCD inhibition on cognitive function are not mediated by recovery of peripheral metabolic abnormalities. Given the widespread side-effects of systemically administered SCD inhibitors, these data suggest that selective inhibition of SCD in the brain may represent a clinically safer and more effective strategy for AD.

Associations between breakfast skipping and outcomes in neuropsychiatric disorders, cognitive performance, and frailty: a Mendelian randomization study.

BACKGROUND: Prior studies have identified a correlation between breakfast skipping and a heightened risk of mental health issues. This investigation aimed to employ a Two-Sample Mendelian Randomization (MR) approach to explore the potential causal links between breakfast skipping and various psychiatric, neurological disorders, cognitive performance, and frailty. METHODS: Utilizing data from genome-wide association studies within European demographics, this research scrutinized the association between breakfast habits and several neuropsychiatric conditions and physical health outcomes, including Alzheimer's disease (AD), Attention Deficit Hyperactivity Disorder (ADHD), Bipolar Disorder (BD), Major Depressive Disorder (MDD), Narcolepsy, Insomnia, cognitive performance, and frailty. In this MR analysis, the Inverse Variance Weighted (IVW) method was primarily utilized for evaluation. Outcomes were reported as Odds Ratios (OR) and regression coefficients (ß), and underwent validation through False Discovery Rate (FDR) corrections, thereby offering a rigorous evaluation of the effects of breakfast habits on both mental and physical health dimensions. RESULTS: Findings demonstrate a significant causal link between skipping breakfast and an increased risk of ADHD (OR = 2.74, 95%CI: 1.54-4.88, PFDR = 0.003) and MDD (OR = 1.7, 95%CI: 1.22-2.37, PFDR = 0.005). Conversely, no substantial causal associations were identified between breakfast skipping and AD, BD, narcolepsy, or insomnia (PFDR > 0.05). Moreover, a notable causal relationship was established between skipping breakfast and a reduction in cognitive performance (ß = -0.16, 95%CI: -0.29-0.04, PFDR = 0.024) and an increase in frailty (ß = 0.29, 95%CI: 0.12-0.45, PFDR = 0.003). CONCLUSION: The MR analysis reveals that skipping breakfast is associated with an increased risk of ADHD, MDD, decreased cognitive performance, and greater frailty, while showing no associations were found with AD, BD, narcolepsy, or insomnia. These findings warrant further investigation into the underlying mechanisms and emphasize the importance of regular breakfast consumption for mental and physical well-being.

Association between Fine Particulate Matter Exposure and Cerebrospinal Fluid Biomarkers of Alzheimer's Disease among a Cognitively Healthy Population-Based Cohort.

BACKGROUND: Epidemiological evidence suggests air pollution adversely affects cognition and increases the risk of Alzheimer's disease (AD), but little is known about the biological effects of fine particulate matter (PM2.5, particulate matter with aerodynamic diameter ≤2.5µm) on early predictors of future disease risk. OBJECTIVES: We investigated the association between 1-, 3-, and 5-y exposure to ambient and traffic-related PM2.5 and cerebrospinal fluid (CSF) biomarkers of AD. METHODS: We conducted a cross-sectional analysis using data from 1,113 cognitively healthy adults (45-75 y of age) from the Emory Healthy Brain Study in Georgia in the United States. CSF biomarker concentrations of Aß42, tTau, and pTau, were collected at enrollment (2016-2020) and analyzed with the Roche Elecsys system. Annual ambient and traffic-related residential PM2.5 concentrations were estimated at a 1-km and 250-m resolution, respectively, and computed for each participant's geocoded address, using three exposure time periods based on specimen collection date. Associations between PM2.5 and CSF biomarker concentrations, considering continuous and dichotomous (dichotomized at clinical cutoffs) outcomes, were estimated with multiple linear/logistic regression, respectively, controlling for potential confounders (age, gender, race, ethnicity, body mass index, and neighborhood socioeconomic status). RESULTS: Interquartile range (IQR; IQR=0.845) increases in 1-y [ß:-0.101; 95% confidence interval (CI): -0.18, -0.02] and 3-y (ß:-0.078; 95% CI: -0.15, -0.00) ambient PM2.5 exposures were negatively associated with Aß42 CSF concentrations. Associations between ambient PM2.5 and Aß42 were similar for 5-y estimates (ß:-0.076; 95% CI: -0.160, 0.005). Dichotomized CSF variables revealed similar associations between ambient PM2.5 and Aß42. Associations with traffic-related PM2.5 were similar but not significant. Associations between PM2.5 exposures and tTau, pTau tTau/Aß42, or pTau/Aß42 levels were mainly null. CONCLUSION: In our study, consistent trends were found between 1-y PM2.5 exposure and decreased CSF Aß42, which suggests an accumulation of amyloid plaques in the brain and an increased risk of developing AD. https://doi.org/10.1289/EHP13503.

Antibody-mediated targeting of human microglial leukocyte Ig-like receptor B4 attenuates amyloid pathology in a mouse model.

Microglia help limit the progression of Alzheimer's disease (AD) by constraining amyloid-ß (Aß) pathology, effected through a balance of activating and inhibitory intracellular signals delivered by distinct cell surface receptors. Human leukocyte Ig-like receptor B4 (LILRB4) is an inhibitory receptor of the immunoglobulin (Ig) superfamily that is expressed on myeloid cells and recognizes apolipoprotein E (ApoE) among other ligands. Here, we find that LILRB4 is highly expressed in the microglia of patients with AD. Using mice that accumulate Aß and carry a transgene encompassing a portion of the LILR region that includes LILRB4, we corroborated abundant LILRB4 expression in microglia wrapping around Aß plaques. Systemic treatment of these mice with an anti-human LILRB4 monoclonal antibody (mAb) reduced Aß load, mitigated some Aß-related behavioral abnormalities, enhanced microglia activity, and attenuated expression of interferon-induced genes. In vitro binding experiments established that human LILRB4 binds both human and mouse ApoE and that anti-human LILRB4 mAb blocks such interaction. In silico modeling, biochemical, and mutagenesis analyses identified a loop between the two extracellular Ig domains of LILRB4 required for interaction with mouse ApoE and further indicated that anti-LILRB4 mAb may block LILRB4-mApoE by directly binding this loop. Thus, targeting LILRB4 may be a potential therapeutic avenue for AD.

Dementia-Related Disparities in Adult Day Centers: Results of a Bivariate Analysis.

PURPOSE: Adult day services (ADS) are a valuable resource for people living with Alzheimer's disease and Alzheimer's disease and related dementias (AD/ADRD) and serve a large population of late-life immigrants, often with limited English proficiency (LEP). This secondary data analysis examined potential disparities in diagnosis, dementia severity, medical complexity, and dementia-related behavioral problems in persons with AD/ADRD with LEP within the ADS setting. METHOD: The current study used data from TurboTAR, the electronic health record for ADS in California. Bivariate analyses were conducted to examine differences in clinical management for those with and without LEP. RESULTS: Of 3,053 participants included in the study, 42.3% had LEP. Participants with LEP had higher rates of emergency department use and medication mismanagement. However, due to non-standard data collection, there was a significant amount of missing data on language preference (38.1%) and race/ethnicity (46.5%). Although these findings suggest LEP may play a role in the clinical management of persons with AD/ADRD in ADS, missing data caused by lack of standardized collection compromise the results. CONCLUSION: It is essential to improve data collection practices in ADS on language, race, and ethnicity to help identify health disparities and promote equitable care for marginalized older adults. [Journal of Gerontological Nursing, 50(4), 42-47.].

[Cortico-basal syndrome and cortico-basal degeneration: From the clinical diagnosis to the lesional substrate for an adapted care]. / Le syndrome cortico-basal et la dégénérescence cortico-basale : du diagnostic clinique au substrat lésionnel pour une prise en charge adaptée.

Cortico-basal degeneration is a relatively uncommon cause of degenerative parkinsonism in the elderly. From a clinical point of view, it manifests as a cortico-basal syndrome (CBS), featuring a highly asymmetrical akinetic-rigid syndrome, dystonia, myoclonus and cognitive-behavioral impairment with predominant apraxia. Other clinical phenotypes are possible, including variants with mainly language or behavioral impairment, or with axial, symmetrical parkinsonism resembling progressive supranuclear palsy (PSP). Current diagnostic criteria take into account the heterogeneity of clinical presentations. However, a diagnosis of certainty can only be reached by a pathological study, with the evidence of TAU-positive intraneuronal inclusions. Indeed SCB may be underpinned by other lesional substrates, ranging from frontotemporal degeneration to Alzheimer's disease. Symptom management must be early, multidisciplinary and adapted to the progression of the disorder. The identification of the pathological substrate is an essential prerequisite for pathophysiological therapeutic trials.

Hippocampal acetylcholinesterase activation induced by streptozotocin in mice is protected by an organotellurium compound without evidence of toxicity.

The cognitive deficit, which is like Alzheimer's disease and is associated with oxidative damage, may be induced by exposure to streptozotocin. This study aimed to evaluate if the tellurium-containing organocompound, 3j, 5'-arylchalcogeno-3-aminothymidine derivative, interferes with the effects of streptozotocin, as well as to investigate its toxicity in adult mice. Cognitive deficit was induced by two doses of streptozotocin (2.25 mg/kg/day, 48 h interval) intracerebroventricularly. After, the mice were subcutaneously treated with 3j (8.62 mg/kg/day) for 25 days. The effects were assessed by evaluating hippocampal and cortical acetylcholinesterase and behavioral tasks. 3j toxicity was investigated for 10 (0, 21.55, or 43.10 mg/kg/day) and 37 (0, 4.31, or 8.62 mg/kg/day) days by assessing biometric parameters and glucose and urea levels, and alanine aminotransferase activity in blood plasma. 3j exposure did not alter the behavioral alterations induced by streptozotocin exposure. On the other hand, 3j exposure normalized hippocampus acetylcholinesterase activity, which is enhanced by streptozotocin exposure. Toxicity evaluation showed that the administration of 3j for either 10 or 37 days did not cause harmful effects on the biometric and biochemical parameters analyzed. Therefore, 3j does not present any apparent toxicity and reverts acetylcholinesterase activity increase induced by streptozotocin in young adult mice.

A Multi-Modal Classification Method for Early Diagnosis of Mild Cognitive Impairment and Alzheimer's Disease Using Three Paradigms With Various Task Difficulties.

Alzheimer's Disease (AD) accounts for the majority of dementia, and Mild Cognitive Impairment (MCI) is the early stage of AD. Early and accurate diagnosis of dementia plays a vital role in more targeted treatments and effectively halting disease progression. However, the clinical diagnosis of dementia requires various examinations, which are expensive and require a high level of expertise from the doctor. In this paper, we proposed a classification method based on multi-modal data including Electroencephalogram (EEG), eye tracking and behavioral data for early diagnosis of AD and MCI. Paradigms with various task difficulties were used to identify different severity of dementia: eye movement task and resting-state EEG tasks were used to detect AD, while eye movement task and delayed match-to-sample task were used to detect MCI. Besides, the effects of different features were compared and suitable EEG channels were selected for the detection. Furthermore, we proposed a data augmentation method to enlarge the dataset, designed an extra ERPNet feature extract layer to extract multi-modal features and used domain-adversarial neural network to improve the performance of MCI diagnosis. We achieved an average accuracy of 88.81% for MCI diagnosis and 100% for AD diagnosis. The results of this paper suggest that our classification method can provide a feasible and affordable way to diagnose dementia.

Profiling of long non-coding RNAs in hippocampal-entorhinal system subfields: impact of RN7SL1 on neuroimmune response modulation in Alzheimer's disease.

Alzheimer's disease (AD) is recognized as the predominant cause of dementia, and neuroimmune processes play a pivotal role in its pathological progression. The involvement of long non-coding RNAs (lncRNAs) in AD has attracted widespread attention. Herein, transcriptomic analysis of 262 unique samples extracted from five hippocampal-entorhinal system subfields of individuals with AD pathology and without AD pathology revealed distinctive lncRNA expression profiles. Through differential expression and coexpression analyses, we identified 16 pivotal lncRNAs. Notably, RN7SL1 knockdown significantly modulated microglial responses upon oligomeric amyloid-ß stimulation, resulting in a considerable decrease in proinflammatory cytokine production and subsequent neuronal damage. These findings highlight RN7SL1 as an essential neuroimmune-related lncRNA that could serve as a prospective target for AD diagnosis and treatment.

Loss of GDE2 leads to complex behavioral changes including memory impairment.

BACKGROUND: Alzheimer's disease (AD) and amyotrophic lateral sclerosis/frontotemporal dementia (ALS/FTD) are debilitating neurodegenerative diseases for which there are currently no cures. Familial cases with known genetic causes make up less than 10% of these diseases, and little is known about the underlying mechanisms that contribute to sporadic disease. Accordingly, it is important to expand investigations into possible pathways that may contribute to disease pathophysiology. Glycerophosphodiester phosphodiesterase 2 (GDE2 or GDPD5) is a membrane-bound enzyme that acts at the cell surface to cleave the glycosylphosphatidylinositol (GPI)-anchor that tethers distinct proteins to the membrane. GDE2 abnormally accumulates in intracellular compartments in the brain of patients with AD, ALS, and ALS/FTD, indicative of GDE2 dysfunction. Mice lacking GDE2 (Gde2KO) show neurodegenerative changes such as neuronal loss, reduced synaptic proteins and synapse loss, and increased Aß deposition, raising the possibility that GDE2 disruption in disease might contribute to disease pathophysiology. However, the effect of GDE2 loss on behavioral function and learning/memory has not been characterized. RESULTS: Here, we show that GDE2 is expressed throughout the adult mouse brain in areas including the cortex, hippocampus, habenula, thalamus, and amygdala. Gde2KO and WT mice were tested in a set of behavioral tasks between 7 and 16 months of age. Compared to WT, Gde2KO mice display moderate hyperactivity that becomes more pronounced with age across a variety of behavioral tests assessing novelty-induced exploratory activity. Additionally, Gde2KO mice show reduced startle response, with females showing additional defects in prepulse inhibition. No changes in anxiety-associated behaviors were found, but Gde2KOs show reduced sociability. Notably, aged Gde2KO mice demonstrate impaired short/long-term spatial memory and cued fear memory/secondary contextual fear acquisition. CONCLUSIONS: Taken together, these observations suggest that loss of GDE2 leads to behavioral deficits, some of which are seen in neurodegenerative disease models, implying that loss of GDE2 may be an important contributor to phenotypes associated with neurodegeneration.

The concept of resilience to Alzheimer's Disease: current definitions and cellular and molecular mechanisms.

Some individuals are able to maintain their cognitive abilities despite the presence of significant Alzheimer's Disease (AD) neuropathological changes. This discrepancy between cognition and pathology has been labeled as resilience and has evolved into a widely debated concept. External factors such as cognitive stimulation are associated with resilience to AD, but the exact cellular and molecular underpinnings are not completely understood. In this review, we discuss the current definitions used in the field, highlight the translational approaches used to investigate resilience to AD and summarize the underlying cellular and molecular substrates of resilience that have been derived from human and animal studies, which have received more and more attention in the last few years. From these studies the picture emerges that resilient individuals are different from AD patients in terms of specific pathological species and their cellular reaction to AD pathology, which possibly helps to maintain cognition up to a certain tipping point. Studying these rare resilient individuals can be of great importance as it could pave the way to novel therapeutic avenues for AD.

Polygenic risk associated with Alzheimer's disease and other traits influences genes involved in T cell signaling and activation.

Introduction: T cells, known for their ability to respond to an enormous variety of pathogens and other insults, are increasingly recognized as important mediators of pathology in neurodegeneration and other diseases. T cell gene expression phenotypes can be regulated by disease-associated genetic variants. Many complex diseases are better represented by polygenic risk than by individual variants. Methods: We first compute a polygenic risk score (PRS) for Alzheimer's disease (AD) using genomic sequencing data from a cohort of Alzheimer's disease (AD) patients and age-matched controls, and validate the AD PRS against clinical metrics in our cohort. We then calculate the PRS for several autoimmune disease, neurological disorder, and immune function traits, and correlate these PRSs with T cell gene expression data from our cohort. We compare PRS-associated genes across traits and four T cell subtypes. Results: Several genes and biological pathways associated with the PRS for these traits relate to key T cell functions. The PRS-associated gene signature generally correlates positively for traits within a particular category (autoimmune disease, neurological disease, immune function) with the exception of stroke. The trait-associated gene expression signature for autoimmune disease traits was polarized towards CD4+ T cell subtypes. Discussion: Our findings show that polygenic risk for complex disease and immune function traits can have varying effects on T cell gene expression trends. Several PRS-associated genes are potential candidates for therapeutic modulation in T cells, and could be tested in in vitro applications using cells from patients bearing high or low polygenic risk for AD or other conditions.

Effect of total flavonoids of Dracocephalum moldavica L. On neuroinflammation in Alzheimer's disease model amyloid-ß (Aß1-42)-peptide-induced astrocyte activation.

One of the main pathological features noted in Alzheimer's disease (AD) is the presence of plagues of aggregated ß-amyloid (Aß1-42)-peptides. Excess deposition of amyloid-ß oligomers (AßO) are known to promote neuroinflammation. Sequentially, following neuroinflammation astrocytes become activated with cellular characteristics to initiate activated astrocytes. The purpose of this study was to determine whether total flavonoids derived from Dracocephalum moldavica L. (TFDM) inhibited Aß1-42-induced damage attributed to activated C8-D1A astrocytes. Western blotting and ELISA were used to determine the expression of glial fibrillary acidic protein (GFAP), and complement C3 to establish the activation status of astrocytes following induction from exposure to Aß1-42. Data demonstrated that stimulation of C8-D1A astrocytes by treatment with 40 µM Aß1-42 for 24 hr produced significant elevation in protein expression and protein levels of acidic protein (GFAP) and complement C3 accompanied by increased expression and levels of inflammatory cytokines. Treatment with TFDM or the clinically employed drug donepezil in AD therapy reduced production of inflammatory cytokines, and toxicity initiated following activation of C8-D1A astrocytes following exposure to Aß1-42. Therefore, TFDM similar to donepezil inhibited inflammatory secretion in reactive astrocytes, suggesting that TFDM may be considered as a potential compound to be utilized in AD therapy.

Universal and Language-Specific Connected Speech Characteristics of Bilingual Speakers With Alzheimer's Disease: Insights From Case Studies of Structurally Distinct Languages.

PURPOSE: Connected speech analysis has been effectively utilized for the diagnosis and disease monitoring of individuals with Alzheimer's disease (AD). Existing research has been conducted mostly in monolingual English speakers with a noticeable lack of evidence from bilinguals and non-English speakers, particularly in non-European languages. Using a case study approach, we characterized connected speech profiles of two Bengali-English bilingual speakers with AD to determine the universal features of language impairments in both languages, identify language-specific differences between the languages, and explore language impairment characteristics of the participants with AD in relation to their bilingual language experience. METHOD: Participants included two Bengali-English bilingual speakers with AD and a group of age-, gender-, education-, and language-matched neurologically healthy controls. Connected speech samples were collected in first language (L1; Bengali) and second language (L2; English) using a novel storytelling task (i.e., Frog, Where Are You?). These samples were analyzed using an augmented quantitative production analysis and correct information unit analyses for productivity, fluency, syntactic and morphosyntactic features, and lexical and semantic characteristics. RESULTS: Irrespective of the language, AD impacted speech productivity (speech rate and fluency) and semantic characteristics in both languages. Unique language-specific differences were noted on syntactic measures (reduced sentence length in Bengali), lexical distribution (fewer pronouns and absence of reduplication in Bengali), and inflectional properties (no difficulties with noun or verb inflections in Bengali). Among the two participants with AD, the individual who showed lower proficiency and usage in L2 (English) demonstrated reduced syntactic complexity and morphosyntactic richness in English. CONCLUSIONS: Evidence from these case studies suggests that language impairment features in AD are not universal across languages, particularly in comparison to impairments typically associated with language breakdowns in English. This study underscores the importance of establishing connected speech profiles in AD for non-English-speaking populations, especially for structurally different languages. This would in turn lead to the development of language-specific markers that can facilitate early detection of language deterioration and aid in improving diagnosis of AD in individuals belonging to underserved linguistically diverse populations. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.25412458.

Shared Manifold Regularized Joint Feature Selection for Joint Classification and Regression in Alzheimer's Disease Diagnosis.

In Alzheimer's disease (AD) diagnosis, joint feature selection for predicting disease labels (classification) and estimating cognitive scores (regression) with neuroimaging data has received increasing attention. In this paper, we propose a model named Shared Manifold regularized Joint Feature Selection (SMJFS) that performs classification and regression in a unified framework for AD diagnosis. For classification, unlike the existing works that build least squares regression models which are insufficient in the ability of extracting discriminative information for classification, we design an objective function that integrates linear discriminant analysis and subspace sparsity regularization for acquiring an informative feature subset. Furthermore, the local data relationships are learned according to the samples' transformed distances to exploit the local data structure adaptively. For regression, in contrast to previous works that overlook the correlations among cognitive scores, we learn a latent score space to capture the correlations and employ the latent space to design a regression model with l2,1 -norm regularization, facilitating the feature selection in regression task. Moreover, the missing cognitive scores can be recovered in the latent space for increasing the number of available training samples. Meanwhile, to capture the correlations between the two tasks and describe the local relationships between samples, we construct an adaptive shared graph to guide the subspace learning in classification and the latent cognitive score learning in regression simultaneously. An efficient iterative optimization algorithm is proposed to solve the optimization problem. Extensive experiments on three datasets validate the discriminability of the features selected by SMJFS.