Search

Abstract Objective To identify white matter fiber injury and network changes that may lead to mild cognitive impairment (MCI) progression, then a joint model was constructed based on neuropsychological scales to predict high-risk individuals for Alzheimer's disease (AD) progression among older adults with MCI. Methods A total of 173 MCI patients were included from the Alzheimer's Disease Neuroimaging Initiative(ADNI) database and randomly divided into training and testing cohorts. Forty-five progressed to AD during a 4-year follow-up period. Diffusion tensor imaging (DTI) techniques extracted relevant DTI quantitative features for each patient. In addition, brain networks were constructed based on white matter fiber bundles to extract network property features. Ensemble dimensionality reduction was applied to reduce both DTI quantitative features and network features from the training cohort, and machine learning algorithms were added to construct white matter signature. In addition, 52 patients from the National Alzheimer's Coordinating Center (NACC) database were used for external validation of white matter signature. A joint model was subsequently generated by combining with scale scores, and its performance was evaluated using data from the testing cohort. Results Based on multivariate logistic regression, clinical dementia rating and Alzheimer’s disease assessment scales (CDRS and ADAS, respectively) were selected as independent predictive factors. A joint model was constructed in combination with the white matter signature. The AUC, sensitivity, and specificity in the training cohort were 0.938, 0.937, and 0.91, respectively, and the AUC, sensitivity, and specificity in the test cohort were 0.905, 0.923, and 0.872, respectively. The Delong test showed a statistically significant difference between the joint model and CDRS or ADAS scores (P

Abstract Background The cerebrospinal fluid (CSF), primarily generated by the choroid plexus (ChP), is the major carrier of the glymphatic system. The alternations of CSF production and the ChP can be associated with the Alzheimer’s disease (AD). The present work investigated the roles of the ChP in the AD based on a proposed ChP image segmentation pipeline. Methods A human-in-the-loop ChP image segmentation pipeline was implemented with intermediate and active learning datasets. The performance of the proposed pipeline was evaluated on manual contours by five radiologists, compared to the FreeSurfer and FastSurfer toolboxes. The ChP volume and blood flow were investigated among AD groups. The correlations between the ChP volume and AD CSF biomarkers including phosphorylated tau (p-tau), total tau (t-tau), amyloid-β42 (Aβ42), and amyloid-β40 (Aβ40) was investigated using three models (univariate, multiple variables, and stepwise regression) on two datasets with 806 and 320 subjects. Results The proposed ChP segmentation pipeline achieved superior performance with a Dice coefficient of 0.620 on the test dataset, compared to the FreeSurfer (0.342) and FastSurfer (0.371). Significantly larger volumes (p

Abstract Background Leveraging Alzheimer’s disease (AD) imaging biomarkers and longitudinal cognitive data may allow us to establish evidence of cognitive resilience (CR) to AD pathology in-vivo. Here, we applied latent class mixture modeling, adjusting for sex, baseline age, and neuroimaging biomarkers of amyloid, tau and neurodegeneration, to a sample of cognitively unimpaired older adults to identify longitudinal trajectories of CR. Methods We identified 200 Harvard Aging Brain Study (HABS) participants (mean age = 71.89 years, SD = 9.41 years, 59% women) who were cognitively unimpaired at baseline with 2 or more timepoints of cognitive assessment following a single amyloid-PET, tau-PET and structural MRI. We examined latent class mixture models with longitudinal cognition as the dependent variable and time from baseline, baseline age, sex, neocortical Aβ, entorhinal tau, and adjusted hippocampal volume as independent variables. We then examined group differences in CR-related factors across the identified subgroups from a favored model. Finally, we applied our favored model to a dataset from the Alzheimer’s Disease Neuroimaging Initiative (ADNI; n = 160, mean age = 73.9 years, SD = 7.6 years, 60% women). Results The favored model identified 3 latent subgroups, which we labelled as Normal (71% of HABS sample), Resilient (22.5%) and Declining (6.5%) subgroups. The Resilient subgroup exhibited higher baseline cognitive performance and a stable cognitive slope. They were differentiated from other groups by higher levels of verbal intelligence and past cognitive activity. In ADNI, this model identified a larger Normal subgroup (88.1%), a smaller Resilient subgroup (6.3%) and a Declining group (5.6%) with a lower cognitive baseline. Conclusion These findings demonstrate the value of data-driven approaches to identify longitudinal CR groups in preclinical AD. With such an approach, we identified a CR subgroup who reflected expected characteristics based on previous literature, higher levels of verbal intelligence and past cognitive activity.

Abstract To uncover molecular changes underlying blood-brain-barrier dysfunction in Alzheimer’s disease, we performed single nucleus RNA sequencing in 24 Alzheimer’s disease and control brains and focused on vascular and astrocyte clusters as main cell types of blood-brain-barrier gliovascular-unit. The majority of the vascular transcriptional changes were in pericytes. Of the vascular molecular targets predicted to interact with astrocytic ligands, SMAD3, upregulated in Alzheimer’s disease pericytes, has the highest number of ligands including VEGFA, downregulated in Alzheimer’s disease astrocytes. We validated these findings with external datasets comprising 4,730 pericyte and 150,664 astrocyte nuclei. Blood SMAD3 levels are associated with Alzheimer’s disease-related neuroimaging outcomes. We determined inverse relationships between pericytic SMAD3 and astrocytic VEGFA in human iPSC and zebrafish models. Here, we detect vast transcriptome changes in Alzheimer’s disease at the gliovascular-unit, prioritize perturbed pericytic SMAD3-astrocytic VEGFA interactions, and validate these in cross-species models to provide a molecular mechanism of blood-brain-barrier disintegrity in Alzheimer’s disease.

Abstract Background Past research suggests that low testosterone levels relate to poorer cognitive function and higher Alzheimer’s disease (AD) risk; however, these findings are inconsistent and are mostly derived from male samples, despite similar age-related testosterone decline in females. Both animal and human studies demonstrate that testosterone’s effects on brain health may be moderated by apolipoprotein E ε4 allele (APOE-ε4) carrier status, which may explain some previous inconsistencies. We examined how testosterone relates to cognitive function in older women versus men across healthy aging and the AD continuum and the moderating role of APOE-ε4 genotype. Methods Five hundred and sixty one participants aged 55–90 (155 cognitively normal (CN), 294 mild cognitive impairment (MCI), 112 AD dementia) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), who had baseline cognitive and plasma testosterone data, as measured by the Rules Based Medicine Human DiscoveryMAP Panel were included. There were 213 females and 348 males (self-reported sex assigned at birth), and 52% of the overall sample were APOE-ε4 carriers. We tested the relationship of plasma testosterone levels and its interaction with APOE-ε4 status on clinical diagnostic group (CN vs. MCI vs. AD), global, and domain-specific cognitive performance using ANOVAs and linear regression models in sex-stratified samples. Cognitive domains included verbal memory, executive function, processing speed, and language. Results We did not observe a significant difference in testosterone levels between clinical diagnostic groups in either sex, regrardless of APOE-ε4 status. Across clinical diagnostic group, we found a significant testosterone by APOE-ε4 interaction in females, such that lower testosterone levels related to worse global cognition, processing speed, and verbal memory in APOE-ε4 carriers only. We did not find that testosterone, nor its interaction with APOE-ε4, related to cognitive outcomes in males. Conclusions Findings suggest that low testosterone levels in older female APOE-ε4 carriers across the aging-MCI-AD continuum may have deleterious, domain-specific effects on cognitive performance. Although future studies including additional sex hormones and longitudinal cognitive trajectories are needed, our results highlight the importance of including both sexes and considering APOE-ε4 carrier status when examining testosterone’s role in cognitive health.

Abstract Background Alzheimer’s Disease (AD) is a progressive memory disorder that causes irreversible cognitive decline. Given that there is currently no cure, it is critical to detect AD in its early stage during the disease progression. Recently, many statistical learning methods have been presented to identify cognitive decline with temporal data, but few of these methods integrate heterogeneous phenotype and genetic information together to improve the accuracy of prediction. In addition, many of these models are often unable to handle incomplete temporal data; this often manifests itself in the removal of records to ensure consistency in the number of records across participants. Results To address these issues, in this work we propose a novel approach to integrate the genetic data and the longitudinal phenotype data to learn a fixed-length “enriched” biomarker representation derived from the temporal heterogeneous neuroimaging records. Armed with this enriched representation, as a fixed-length vector per participant, conventional machine learning models can be used to predict clinical outcomes associated with AD. Conclusion The proposed method shows improved prediction performance when applied to data derived from Alzheimer’s Disease Neruoimaging Initiative cohort. In addition, our approach can be easily interpreted to allow for the identification and validation of biomarkers associated with cognitive decline.

Abstract Background An elevated neutrophil–lymphocyte ratio (NLR) in blood has been associated with Alzheimer’s disease (AD). However, an elevated NLR has also been implicated in many other conditions that are risk factors for AD, prompting investigation into whether the NLR is directly linked with AD pathology or a result of underlying comorbidities. Herein, we explored the relationship between the NLR and AD biomarkers in the cerebrospinal fluid (CSF) of cognitively unimpaired (CU) subjects. Adjusting for sociodemographics, APOE4, and common comorbidities, we investigated these associations in two cohorts: the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the M.J. de Leon CSF repository at NYU. Specifically, we examined associations between the NLR and cross-sectional measures of amyloid-β42 (Aβ42), total tau (t-tau), and phosphorylated tau181 (p-tau), as well as the trajectories of these CSF measures obtained longitudinally. Results A total of 111 ADNI and 190 NYU participants classified as CU with available NLR, CSF, and covariate data were included. Compared to NYU, ADNI participants were older (73.79 vs. 61.53, p

Abstract Background Irregular word reading has been used to estimate premorbid intelligence in Alzheimer’s disease (AD) dementia. However, reading models highlight the core influence of semantic abilities on irregular word reading, which shows early decline in AD. The primary objective of this study is to ascertain whether irregular word reading serves as an indicator of cognitive and semantic decline in AD, potentially discouraging its use as a marker for premorbid intellectual abilities. Method Six hundred eighty-one healthy controls (HC), 104 subjective cognitive decline, 290 early and 589 late mild cognitive impairment (EMCI, LMCI) and 348 AD participants from the Alzheimer’s Disease Neuroimaging Initiative were included. Irregular word reading was assessed with the American National Adult Reading Test (AmNART). Multiple linear regressions were conducted predicting AmNART score using diagnostic category, general cognitive impairment and semantic tests. A generalized logistic mixed-effects model predicted correct reading using extracted psycholinguistic characteristics of each AmNART words. Deformation-based morphometry was used to assess the relationship between AmNART scores and voxel-wise brain volumes, as well as with the volume of a region of interest placed in the left anterior temporal lobe (ATL), a region implicated in semantic memory. Results EMCI, LMCI and AD patients made significantly more errors in reading irregular words compared to HC, and AD patients made more errors than all other groups. Across the AD continuum, as well as within each diagnostic group, irregular word reading was significantly correlated to measures of general cognitive impairment / dementia severity. Neuropsychological tests of lexicosemantics were moderately correlated to irregular word reading whilst executive functioning and episodic memory were respectively weakly and not correlated. Age of acquisition, a primarily semantic variable, had a strong effect on irregular word reading accuracy whilst none of the phonological variables significantly contributed. Neuroimaging analyses pointed to bilateral hippocampal and left ATL volume loss as the main contributors to decreased irregular word reading performances. Conclusions While the AmNART may be appropriate to measure premorbid intellectual abilities in cognitively unimpaired individuals, our results suggest that it captures current semantic decline in MCI and AD patients and may therefore underestimate premorbid intelligence. On the other hand, irregular word reading tests might be clinically useful to detect semantic impairments in individuals on the AD continuum.

Abstract Background Individuals on the preclinical Alzheimer's continuum, particularly those with both amyloid and tau positivity (A + T +), display a rapid cognitive decline and elevated disease progression risk. However, limited studies exist on brain atrophy trajectories within this continuum over extended periods. Methods This study involved 367 ADNI participants grouped based on combinations of amyloid and tau statuses determined through cerebrospinal fluid tests. Using longitudinal MRI scans, brain atrophy was determined according to the whole brain, lateral ventricle, and hippocampal volumes and cortical thickness in AD-signature regions. Cognitive performance was evaluated with the Preclinical Alzheimer's Cognitive Composite (PACC). A generalized linear mixed-effects model was used to examine group × time interactions for these measures. In addition, progression risks to mild cognitive impairment (MCI) or dementia were compared among the groups using Cox proportional hazards models. Results A total of 367 participants (48 A + T + , 86 A + T − , 63 A − T + , and 170 A − T − ; mean age 73.8 years, mean follow-up 5.1 years, and 47.4% men) were included. For the lateral ventricle and PACC score, the A + T − and A + T + groups demonstrated statistically significantly greater volume expansion and cognitive decline over time than the A − T − group (lateral ventricle: β = 0.757 cm3/year [95% confidence interval 0.463 to 1.050], P

BackgroundStable mild cognitive impairment (sMCI) and progressive mild cognitive impairment (pMCI) represent two distinct subtypes of mild cognitive impairment (MCI). Early and effective diagnosis and accurate differentiation between sMCI and pMCI are crucial for administering targeted early intervention and preventing cognitive decline. This study investigated the intrinsic dysconnectivity patterns in sMCI and pMCI based on degree centrality (DC) and effective connectivity (EC) analyses, with the goal of uncovering shared and distinct neuroimaging mechanisms between subtypes.MethodsResting-state functional magnetic resonance imaging combined with DC analysis was used to explore the functional connectivity density in 42 patients with sMCI, 31 patients with pMCI, and 82 healthy control (HC) participants. Granger causality analysis was used to assess changes in EC based on the significant clusters found in DC. Furthermore, correlation analysis was conducted to examine the associations between altered DC/EC values and cognitive function. Receiver operating characteristic curve analysis was performed to determine the accuracy of abnormal DC and EC values in distinguishing sMCI from pMCI.ResultsCompared with the HC group, both pMCI and sMCI groups exhibited increased DC in the left inferior temporal gyrus (ITG), left posterior cerebellum lobe (CPL), and right cerebellum anterior lobe (CAL), along with decreased DC in the left medial frontal gyrus. Moreover, the sMCI group displayed reduced EC from the right CAL to bilateral CPL, left superior temporal gyrus, and bilateral caudate compared with HC. pMCI demonstrated elevated EC from the right CAL to left ITG, which was linked to episodic memory and executive function. Notably, the EC from the right CAL to the right ITG effectively distinguished sMCI from pMCI, with sensitivity, specificity, and accuracy of 0.5806, 0.9512, and 0.828, respectively.ConclusionThis study uncovered shared and distinct alterations in DC and EC between sMCI and pMCI, highlighting their involvement in cognitive function. Of particular significance are the unidirectional EC disruptions from the cerebellum to the temporal lobe, which serve as a discriminating factor between sMCI and pMCI and provide a new perspective for understanding the temporal-cerebellum. These findings offer novel insights into the neural circuit mechanisms involving the temporal-cerebellum connection in MCI.

IntroductionAlzheimer’s disease (AD) is highly heterogeneous, with substantial individual variabilities in clinical progression and neurobiology. Amyloid deposition has been thought to drive cognitive decline and thus a major contributor to the variations in cognitive deterioration in AD. However, the clinical heterogeneity of patients with early symptomatic AD (mild cognitive impairment or mild dementia due to AD) already with evidence of amyloid abnormality in the brain is still unknown.MethodsParticipants with a baseline diagnosis of mild cognitive impairment or mild dementia, a positive amyloid-PET scan, and more than one follow-up Alzheimer’s Disease Assessment Scale-Cognitive Subscale-13 (ADAS-Cog-13) administration within a period of 5-year follow-up were selected from the Alzheimer’s Disease Neuroimaging Initiative database (n = 421; age = 73±7; years of education = 16 ± 3; percentage of female gender = 43%; distribution of APOE4 carriers = 68%). A non-parametric k-means longitudinal clustering analysis in the context of the ADAS-Cog-13 data was performed to identify cognitive subtypes.ResultsWe found a highly variable profile of cognitive decline among patients with early AD and identified 4 clusters characterized by distinct rates of cognitive progression. Among the groups there were significant differences in the magnitude of rates of changes in other cognitive and functional outcomes, clinical progression from mild cognitive impairment to dementia, and changes in markers presumed to reflect neurodegeneration and neuronal injury. A nomogram based on a simplified logistic regression model predicted steep cognitive trajectory with an AUC of 0.912 (95% CI: 0.88 – 0.94). Simulation of clinical trials suggested that the incorporation of the nomogram into enrichment strategies would reduce the required sample sizes from 926.8 (95% CI: 822.6 – 1057.5) to 400.9 (95% CI: 306.9 – 516.8).DiscussionOur findings show usefulness in the stratification of patients in early AD and may thus increase the chances of finding a treatment for future AD clinical trials.

Abstract Spontaneous reversion from mild cognitive impairment (MCI) to normal cognition (NC) is little known. Based on the data of the Genetics of Personality Consortium and MCI participants from Alzheimer's Disease Neuroimaging Initiative, the authors investigate the effect of polygenic scores (PGS) for personality traits on the reversion of MCI to NC and its underlying neurobiology. PGS analysis reveals that PGS for conscientiousness (PGS‐C) is a protective factor that supports the reversion from MCI to NC. Gene ontology enrichment analysis and tissue‐specific enrichment analysis indicate that the protective effect of PGS‐C may be attributed to affecting the glutamatergic synapses of subcortical structures, such as hippocampus, amygdala, nucleus accumbens, and caudate nucleus. The structural covariance network (SCN) analysis suggests that the left whole hippocampus and its subfields, and the left whole amygdala and its subnuclei show significantly stronger covariance with several high‐cognition relevant brain regions in the MCI reverters compared to the stable MCI participants, which may help illustrate the underlying neural mechanism of the protective effect of PGS‐C.

Abstract 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.

IntroductionThis study aimed to investigate the cognitive profile and prospective cognitive changes in non-demented adults with elevated Modified Dementia Risk Scores (MDRS), while also exploring the potential relationship between these associations and cerebrospinal fluid (CSF) biomarkers of Alzheimer’s disease (AD) pathology and neuroinflammation.MethodsWithin the Chinese Alzheimer’s Biomarker and LifestylE (CABLE) database, 994 participants without dementia were assessed on MDRS, CSF biomarkers and cognition. We examined the associations of the MDRS with CSF biomarkers and cognitive scores using linear regressions. Causal mediation analyses were conducted to analyze the associations among MDRS, brain pathologies, and cognition. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) study was used to validate the mediation effects and to investigate the longitudinal association between MDRS and cognitive decline.ResultsThe results revealed that higher MDRS were linked to poorer cognitive performance (Model 1: PFDR

Abstract Background Functional connectivity (FC) biomarkers play a crucial role in the early diagnosis and mechanistic study of Alzheimer’s disease (AD). However, the identification of effective FC biomarkers remains challenging. In this study, we introduce a novel approach, the spatiotemporal graph convolutional network (ST-GCN) combined with the gradient-based class activation mapping (Grad-CAM) model (STGC-GCAM), to effectively identify FC biomarkers for AD. Methods This multi-center cross-racial retrospective study involved 2,272 participants, including 1,105 cognitively normal (CN) subjects, 790 mild cognitive impairment (MCI) individuals, and 377 AD patients. All participants underwent functional magnetic resonance imaging (fMRI) and T1-weighted MRI scans. In this study, firstly, we optimized the STGC-GCAM model to enhance classification accuracy. Secondly, we identified novel AD-associated biomarkers using the optimized model. Thirdly, we validated the imaging biomarkers using Kaplan–Meier analysis. Lastly, we performed correlation analysis and causal mediation analysis to confirm the physiological significance of the identified biomarkers. Results The STGC-GCAM model demonstrated great classification performance (The average area under the curve (AUC) values for different categories were: CN vs MCI = 0.98, CN vs AD = 0.95, MCI vs AD = 0.96, stable MCI vs progressive MCI = 0.79). Notably, the model identified specific brain regions, including the sensorimotor network (SMN), visual network (VN), and default mode network (DMN), as key differentiators between patients and CN individuals. These brain regions exhibited significant associations with the severity of cognitive impairment (p

Abstract Background Identifying individuals with mild cognitive impairment (MCI) at risk of progressing to Alzheimer’s disease (AD) provides a unique opportunity for early interventions. Therefore, accurate and long-term prediction of the conversion from MCI to AD is desired but, to date, remains challenging. Here, we developed an interpretable deep learning model featuring a novel design that incorporates interaction effects and multimodality to improve the prediction accuracy and horizon for MCI-to-AD progression. Methods This multi-center, multi-cohort retrospective study collected structural magnetic resonance imaging (sMRI), clinical assessments, and genetic polymorphism data of 252 patients with MCI at baseline from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Our deep learning model was cross-validated on the ADNI-1 and ADNI-2/GO cohorts and further generalized in the ongoing ADNI-3 cohort. We evaluated the model performance using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score. Results On the cross-validation set, our model achieved superior results for predicting MCI conversion within 4 years (AUC, 0.962; accuracy, 92.92%; sensitivity, 88.89%; specificity, 95.33%) compared to all existing studies. In the independent test, our model exhibited consistent performance with an AUC of 0.939 and an accuracy of 92.86%. Integrating interaction effects and multimodal data into the model significantly increased prediction accuracy by 4.76% (P = 0.01) and 4.29% (P = 0.03), respectively. Furthermore, our model demonstrated robustness to inter-center and inter-scanner variability, while generating interpretable predictions by quantifying the contribution of multimodal biomarkers. Conclusions The proposed deep learning model presents a novel perspective by combining interaction effects and multimodality, leading to more accurate and longer-term predictions of AD progression, which promises to improve pre-dementia patient care.

Abstract Background Glymphatic dysfunction is a crucial pathway for dementia. Alzheimer’s disease (AD) pathologies co-existing with cerebral small vessel disease (CSVD) is the most common pathogenesis for dementia. We hypothesize that AD pathologies and CSVD could be associated with glymphatic dysfunction, contributing to cognitive impairment. Method Participants completed with amyloid PET, diffusion tensor imaging (DTI), and T2 fluid-attenuated inversion-recovery (FLAIR) sequences were included from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). White matter hyperintensities (WMH), the most common CSVD marker, was evaluated from T2FLAIR images and represented the burden of CSVD. Amyloid PET was used to assess Aβ aggregation in the brain. We used diffusion tensor image analysis along the perivascular space (DTI-ALPS) index, the burden of enlarged perivascular spaces (PVS), and choroid plexus volume to reflect glymphatic function. The relationships between WMH burden/Aβ aggregation and these glymphatic markers as well as the correlations between glymphatic markers and cognitive function were investigated. Furthermore, we conducted mediation analyses to explore the potential mediating effects of glymphatic markers in the relationship between WMH burden/Aβ aggregation and cognition. Results One hundred and thirty-three participants along the AD continuum were included, consisting of 40 CN − , 48 CN + , 26 MCI + , and 19 AD + participants. Our findings revealed that there were negative associations between whole-brain Aβ aggregation (r = − 0.249, p = 0.022) and WMH burden (r = − 0.458, p

Abstract Background The pathophysiology of Alzheimer’s disease (AD) involves $$\beta$$ β -amyloid (A $$\beta$$ β ) accumulation. Early identification of individuals with abnormal $$\beta$$ β -amyloid levels is crucial, but A $$\beta$$ β quantification with positron emission tomography (PET) and cerebrospinal fluid (CSF) is invasive and expensive. Methods We propose a machine learning framework using standard non-invasive (MRI, demographics, APOE, neuropsychology) measures to predict future A $$\beta$$ β -positivity in A $$\beta$$ β -negative individuals. We separately study A $$\beta$$ β -positivity defined by PET and CSF. Results Cross-validated AUC for 4-year A $$\beta$$ β conversion prediction was 0.78 for the CSF-based and 0.68 for the PET-based A $$\beta$$ β definitions. Although not trained for the clinical status-change prediction, the CSF-based model excelled in predicting future mild cognitive impairment (MCI)/dementia conversion in cognitively normal/MCI individuals (AUCs, respectively, 0.76 and 0.89 with a separate dataset). Conclusion Standard measures have potential in detecting future A $$\beta$$ β -positivity and assessing conversion risk, even in cognitively normal individuals. The CSF-based definition led to better predictions than the PET-based definition.

Abstract Parkinson’s disease (PD) is the second most common neurodegenerative disease. Accurate PD diagnosis is crucial for effective treatment and prognosis but can be challenging, especially at early disease stages. This study aimed to develop and evaluate an explainable deep learning model for PD classification from multimodal neuroimaging data. The model was trained using one of the largest collections of T1-weighted and diffusion-tensor magnetic resonance imaging (MRI) datasets. A total of 1264 datasets from eight different studies were collected, including 611 PD patients and 653 healthy controls (HC). These datasets were pre-processed and non-linearly registered to the MNI PD25 atlas. Six imaging maps describing the macro- and micro-structural integrity of brain tissues complemented with age and sex parameters were used to train a convolutional neural network (CNN) to classify PD/HC subjects. Explainability of the model’s decision-making was achieved using SmoothGrad saliency maps, highlighting important brain regions. The CNN was trained using a 75%/10%/15% train/validation/test split stratified by diagnosis, sex, age, and study, achieving a ROC-AUC of 0.89, accuracy of 80.8%, specificity of 82.4%, and sensitivity of 79.1% on the test set. Saliency maps revealed that diffusion tensor imaging data, especially fractional anisotropy, was more important for the classification than T1-weighted data, highlighting subcortical regions such as the brainstem, thalamus, amygdala, hippocampus, and cortical areas. The proposed model, trained on a large multimodal MRI database, can classify PD patients and HC subjects with high accuracy and clinically reasonable explanations, suggesting that micro-structural brain changes play an essential role in the disease course.

Abstract Background Functional decline associated with dementia, including in Alzheimer’s disease (AD), is not uniform across individuals, and respective heterogeneity is not yet fully explained. Such heterogeneity may in part be related to genetic variability among individuals. In this study, we investigated whether the SNP rs6859 in nectin cell adhesion molecule 2 (NECTIN2) gene (a major risk factor for AD) influences trajectories of cognitive decline in older participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Methods We retrospectively analyzed records on 1310 participants from the ADNI database for the multivariate analysis. We used longitudinal measures of Mini-Mental State Examination (MMSE) scores in participants, who were cognitively normal, or having AD, or other cognitive deficits to investigate the trajectories of cognitive changes. Multiple linear regression, linear mixed models and latent class analyses were conducted to investigate the association of the SNP rs6859 with MMSE. Results The regression coefficient per one allele dose of the SNP rs6859 was independently associated with MMSE in both cross-sectional (-2.23, p

IntroductionMild cognitive impairment (MCI) is an important stage in Alzheimer’s disease (AD) research, focusing on early pathogenic factors and mechanisms. Examining MCI patient subtypes and identifying their cognitive and neuropathological patterns as the disease progresses can enhance our understanding of the heterogeneous disease progression in the early stages of AD. However, few studies have thoroughly analyzed the subtypes of MCI, such as the cortical atrophy, and disease development characteristics of each subtype.MethodsIn this study, 396 individuals with MCI, 228 cognitive normal (CN) participants, and 192 AD patients were selected from ADNI database, and a semi-supervised mixture expert algorithm (MOE) with multiple classification boundaries was constructed to define AD subtypes. Moreover, the subtypes of MCI were obtained by using the multivariate linear boundary mapping of support vector machine (SVM). Then, the gray matter atrophy regions and severity of each MCI subtype were analyzed and the features of each subtype in demography, pathology, cognition, and disease progression were explored combining the longitudinal data collected for 2 years and analyzed important factors that cause conversion of MCI were analyzed.ResultsThree MCI subtypes were defined by MOE algorithm, and the three subtypes exhibited their own features in cortical atrophy. Nearly one-third of patients diagnosed with MCI have almost no significant difference in cerebral cortex from the normal aging population, and their conversion rate to AD are the lowest. The subtype characterized by severe atrophy in temporal lobe and frontal lobe have a faster decline rate in many cognitive manifestations than the subtype featured with diffuse atrophy in the whole cortex. APOE ε4 is an important factor that cause the conversion of MCI to AD.ConclusionIt was proved through the data-driven method that MCI collected by ADNI baseline presented different subtype features. The characteristics and disease development trajectories among subtypes can help to improve the prediction of clinical progress in the future and also provide necessary clues to solve the classification accuracy of MCI.

ObjectiveEarly 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.MethodsA 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).ResultsAβ 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.ConclusionThis study underscores the importance of an interdisciplinary approach in understanding AD mechanisms, offering potential contributions to early biomarker development.

Abstract INTRODUCTION The development and progression of Alzheimer's disease (AD) is a complex process, during which genetic influences on phenotypes may also change. Incorporating longitudinal phenotypes in genome‐wide association studies (GWAS) could unmask these genetic loci. METHODS We conducted a longitudinal GWAS using a varying coefficient test to identify age‐dependent single nucleotide polymorphisms (SNPs) in AD. Data from 1877 Alzheimer's Neuroimaging Data Initiative participants, including impairment status and amyloid positron emission tomography (PET) scan standardized uptake value ratio (SUVR) scores, were analyzed using a retrospective varying coefficient mixed model association test (RVMMAT). RESULTS RVMMAT identified 244 SNPs with significant time‐varying effects on AD impairment status, with 12 SNPs on chromosome 19 validated using National Alzheimer's Coordinating Center data. Age‐stratified analyses showed these SNPs’ effects peaked between 70 and 80 years. Additionally, 73 SNPs were linked to longitudinal amyloid accumulation changes. Pathway analyses implicated immune and neuroinflammation‐related disruptions. DISCUSSION Our findings demonstrate that longitudinal GWAS models can uncover time‐varying genetic signals in AD. Highlights Identify time‐varying genetic effects using a longitudinal GWAS model in AD. Illustrate age‐dependent genetic effects on both diagnoses and amyloid accumulation. Replicate time‐varying effect of APOE in a second dataset.

Abstract Introduction The distribution of voxel‐ and connection‐based white matter hyperintensity (WMH) patterns in early‐onset Alzheimer's disease (EOAD) and late‐onset Alzheimer's disease (LOAD), as well as factors associated with these patterns, remain unclear. Method We analyzed the WMH distribution patterns in EOAD and LOAD at the voxel and connection levels, each compared with their age‐matched cognitively unimpaired participants. Linear regression assessed the independent effects of amyloid and vascular risk factors on WMH distribution patterns in both groups. Results Patients with EOAD showed increased WMH burden in the posterior region at the voxel level, and in occipital region tracts and visual network at the connection level, compared to controls. LOAD exhibited extensive involvement across various brain areas in both levels. Amyloid accumulation was associated WMH distribution in the early‐onset group, whereas the late‐onset group demonstrated associations with both amyloid and vascular risk factors. Discussion EOAD showed posterior‐focused WMH distribution pattern, whereas LOAD was with a wider distribution. Amyloid accumulation was associated with connection‐based WMH patterns in both early‐onset and late‐onset groups, with additional independent effects of vascular risk factors in late‐onset group. Highlights Both early‐onset Alzheimer's disease (EOAD) and late‐onset AD (LOAD) showed increased white matter hyperintensity (WMH) volume compared with their age‐matched cognitively unimpaired participants. EOAD and LOAD exhibited distinct patterns of WMH distribution, with EOAD showing a posterior‐focused pattern and LOAD displaying a wider distribution across both voxel‐ and connection‐based levels. In both EOAD and LOAD, amyloid accumulation was associated with connection‐based WMH patterns, with additional independent effects of vascular risk factors observed in LOAD.

Abstract Background Alzheimer’s disease is a neurodegenerative condition associated with the accumulation of two misfolded proteins, amyloid-beta (A $$\beta$$ β ) and tau. We study their effect on neuronal activity, with the aim of assessing their individual and combined impact. Methods We use a whole-brain dynamic model to find the optimal parameters that best describe the effects of A $$\beta$$ β and tau on the excitation-inhibition balance of the local nodes. Results We found a clear dominance of A $$\beta$$ β over tau in the early disease stages (MCI), while tau dominates over A $$\beta$$ β in the latest stages (AD). We identify crucial roles for A $$\beta$$ β and tau in complex neuronal dynamics and demonstrate the viability of using regional distributions to define models of large-scale brain function in AD. Conclusions Our study provides further insight into the dynamics and complex interplay between these two proteins, opening the path for further investigations on biomarkers and candidate therapeutic targets in-silico.

Abstract Random Survival Forests (RSF) has recently showed better performance than statistical survival methods as Cox proportional hazard (CPH) in predicting conversion risk from mild cognitive impairment (MCI) to Alzheimer’s disease (AD). However, RSF application in real-world clinical setting is still limited due to its black-box nature. For this reason, we aimed at providing a comprehensive study of RSF explainability with SHapley Additive exPlanations (SHAP) on biomarkers of stable and progressive patients (sMCI and pMCI) from Alzheimer’s Disease Neuroimaging Initiative. We evaluated three global explanations—RSF feature importance, permutation importance and SHAP importance—and we quantitatively compared them with Rank-Biased Overlap (RBO). Moreover, we assessed whether multicollinearity among variables may perturb SHAP outcome. Lastly, we stratified pMCI test patients in high, medium and low risk grade, to investigate individual SHAP explanation of one pMCI patient per risk group. We confirmed that RSF had higher accuracy (0.890) than CPH (0.819), and its stability and robustness was demonstrated by high overlap (RBO > 90%) between feature rankings within first eight features. SHAP local explanations with and without correlated variables had no substantial difference, showing that multicollinearity did not alter the model. FDG, ABETA42 and HCI were the first important features in global explanations, with the highest contribution also in local explanation. FAQ, mPACCdigit, mPACCtrailsB and RAVLT immediate had the highest influence among all clinical and neuropsychological assessments in increasing progression risk, as particularly evident in pMCI patients’ individual explanation. In conclusion, our findings suggest that RSF represents a useful tool to support clinicians in estimating conversion-to-AD risk and that SHAP explainer boosts its clinical utility with intelligible and interpretable individual outcomes that highlights key features associated with AD prognosis. Graphical Abstract

Abstract Background Alzheimer’s disease (AD) is an incurable, debilitating neurodegenerative disorder. Current biomarkers for AD diagnosis require expensive neuroimaging or invasive cerebrospinal fluid sampling, thus precluding early detection. Blood-based biomarker discovery in Alzheimer’s can facilitate less-invasive, routine diagnostic tests to aid early intervention. Therefore, we propose “c-Diadem” (constrained dual-input Alzheimer’s disease model), a novel deep learning classifier which incorporates KEGG (Kyoto Encyclopedia of Genes and Genomes) pathway constraints on the input genotyping data to predict disease, i.e., mild cognitive impairment (MCI)/AD or cognitively normal (CN). SHAP (SHapley Additive exPlanations) was used to explain the model and identify novel, potential blood-based genetic markers of MCI/AD. Methods We developed a novel constrained deep learning neural network which utilizes SNPs (single nucleotide polymorphisms) and microarray data from ADNI (Alzheimer’s Disease Neuroimaging Initiative) to predict the disease status of participants, i.e., CN or with disease (MCI/AD), and identify potential blood-based biomarkers for diagnosis and intervention. The dataset contains samples from 626 participants, of which 212 are CN (average age 74.6 ± 5.4 years) and 414 patients have MCI/AD (average age 72.7 ± 7.6 years). KEGG pathway information was used to generate constraints applied to the input tensors, thus enhancing the interpretability of the model. SHAP scores were used to identify genes which could potentially serve as biomarkers for diagnosis and targets for drug development. Results Our model’s performance, with accuracy of 69% and AUC of 70% in the test dataset, is superior to previous models. The SHAP scores show that SNPs in PRKCZ, PLCB1 and ITPR2 as well as expression of HLA-DQB1, EIF1AY, HLA-DQA1, and ZFP57 have more impact on model predictions. Conclusions In addition to predicting MCI/AD, our model has been interrogated for potential genetic biomarkers using SHAP. From our analysis, we have identified blood-based genetic markers related to Ca2+ ion release in affected regions of the brain, as well as depression. The findings from our study provides insights into disease mechanisms, and can facilitate innovation in less-invasive, cost-effective diagnostics. To the best of our knowledge, our model is the first to use pathway constraints in a multimodal neural network to identify potential genetic markers for AD.

IntroductionIn the last few years, several models trying to calculate the biological brain age have been proposed based on structural magnetic resonance imaging scans (T1-weighted MRIs, T1w) using multivariate methods and machine learning. We developed and validated a convolutional neural network (CNN)-based biological brain age prediction model that uses one T1w MRI preprocessing step when applying the model to external datasets to simplify implementation and increase accessibility in research settings. Our model only requires rigid image registration to the MNI space, which is an advantage compared to previous methods that require more preprocessing steps, such as feature extraction.MethodsWe used a multicohort dataset of cognitively healthy individuals (age range = 32.0–95.7 years) comprising 17,296 MRIs for training and evaluation. We compared our model using hold-out (CNN1) and cross-validation (CNN2–4) approaches. To verify generalisability, we used two external datasets with different populations and MRI scan characteristics to evaluate the model. To demonstrate its usability, we included the external dataset’s images in the cross-validation training (CNN3). To ensure that our model used only the brain signal on the image, we also predicted brain age using skull-stripped images (CNN4).Results:The trained models achieved a mean absolute error of 2.99, 2.67, 2.67, and 3.08 years for CNN1–4, respectively. The model’s performance in the external dataset was in the typical range of mean absolute error (MAE) found in the literature for testing sets. Adding the external dataset to the training set (CNN3), overall, MAE is unaffected, but individual cohort MAE improves (5.63–2.25 years). Salience maps of predictions reveal that periventricular, temporal, and insular regions are the most important for age prediction.DiscussionWe provide indicators for using biological (predicted) brain age as a metric for age correction in neuroimaging studies as an alternative to the traditional chronological age. In conclusion, using different approaches, our CNN-based model showed good performance using one T1w brain MRI preprocessing step. The proposed CNN model is made publicly available for the research community to be easily implemented and used to study ageing and age-related disorders.

Abstract Introduction It is important to study apathy in Alzheimer's disease (AD) to better understand its underlying neurobiology and develop effective interventions. In the current study, we sought to examine the relationships between longitudinal apathy and regional tau burden in cognitively impaired older adults from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Methods Three hundred and nineteen ADNI participants with mild cognitive impairment (MCI) or AD dementia underwent flortaucipir (FTP) tau positron emission tomography (PET) imaging and clinical assessment with the Neuropsychiatric Inventory (NPI) annually. Longitudinal NPI Apathy (NPI‐A) scores were examined in relation to baseline tau PET signal in three a priori selected regions implicated in AD and AD‐related apathy (supramarginal gyrus, entorhinal cortex [EC] and rostral anterior cingulate cortex [rACC]). Secondary models were adjusted for global cognition (Mini‐Mental State Examination score) and cortical amyloid (florbetapir PET). Results Higher baseline supramarginal gyrus and EC tau burden were each significantly associated with greater NPI‐A over time, while rACC tau was associated with higher NPI‐A but did not predict its trajectory over time. These results were retained for supramarginal and EC tau after adjusting models for global cognition and cortical amyloid. Discussion Our findings suggest that baseline in vivo tau burden in parietal and temporal brain regions affected in AD, and less so in a medial frontal region involved in motivational control, is associated with increasing apathy over time in older adults with MCI and AD dementia. Future work studying emergent apathy in relation to not only core AD pathology but also circuit level dysfunction may provide additional insight into the neurobiology of apathy in AD and opportunities for intervention. Highlights Tau (Flortaucipir PET) in regions implicated in AD was associated with increasing apathy over time Cortical amyloid was also found to be a robust predictor of the trajectory of apathy Evidence of synergy between regional tau and amyloid in overall higher levels of apathy

Abstract Objective This study investigated cerebral small vessel disease (CSVD) damage patterns in early‐onset and late‐onset Alzheimer's disease (EOAD and LOAD) and their effects on cognitive function. Methods This study included 93 participants, 45 AD patients (14 EOAD and 31 LOAD), and 48 normal controls (13 YNC and 35 ONC) from the ADNI database. All participants had diffusion tensor imaging data; some had amyloid PET and plasma p‐tau181 data. The study used peak width of skeletonized mean diffusivity (PSMD) to measure CSVD severity and compared PSMD between patients and age‐matched controls. The effect of age on the relationship between PSMD and cognition was also examined. The study also repeated the analysis in amyloid‐positive AD patients and amyloid‐negative controls in another independent database (31 EOAD and 38 LOAD), and the merged database. Results EOAD and LOAD showed similar cognitive function and disease severity. PSMD was validated as a reliable correlate of cognitive function. In the ADNI database, PSMD was significantly higher for LOAD and showed a tendency to increase for EOAD; in the independent and merged databases, PSMD was significantly higher for both LOAD and EOAD. The impact of PSMD on cognitive function was notably greater in the younger group (YNC and EOAD) than in the older group (ONC and LOAD), as supported by the ADNI and merged databases. Interpretation EOAD has less CSVD burden than LOAD, but has a greater impact on cognition. Proactive cerebrovascular prevention strategies may have potential clinical value for younger older adults with cognitive decline.

Abstract Background The recent advances in biotechnology and computer science have led to an ever-increasing availability of public biomedical data distributed in large databases worldwide. However, these data collections are far from being “standardized” so to be harmonized or even integrated, making it impossible to fully exploit the latest machine learning technologies for the analysis of data themselves. Hence, facing this huge flow of biomedical data is a challenging task for researchers and clinicians due to their complexity and high heterogeneity. This is the case of neurodegenerative diseases and the Alzheimer’s Disease (AD) in whose context specialized data collections such as the one by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) are maintained. Methods Ontologies are controlled vocabularies that allow the semantics of data and their relationships in a given domain to be represented. They are often exploited to aid knowledge and data management in healthcare research. Computational Ontologies are the result of the combination of data management systems and traditional ontologies. Our approach is i) to define a computational ontology representing a logic-based formal conceptual model of the ADNI data collection and ii) to provide a means for populating the ontology with the actual data in the Alzheimer Disease Neuroimaging Initiative (ADNI). These two components make it possible to semantically query the ADNI database in order to support data extraction in a more intuitive manner. Results We developed: i) a detailed computational ontology for clinical multimodal datasets from the ADNI repository in order to simplify the access to these data; ii) a means for populating this ontology with the actual ADNI data. Such computational ontology immediately makes it possible to facilitate complex queries to the ADNI files, obtaining new diagnostic knowledge about Alzheimer’s disease. Conclusions The proposed ontology will improve the access to the ADNI dataset, allowing queries to extract multivariate datasets to perform multidimensional and longitudinal statistical analyses. Moreover, the proposed ontology can be a candidate for supporting the design and implementation of new information systems for the collection and management of AD data and metadata, and for being a reference point for harmonizing or integrating data residing in different sources.

Abstract Background The AT(N) research framework for Alzheimer's disease (AD) remains unclear on how to best deal with borderline cases. Our aim was to characterise patients with suspected AD with a borderline Aß1-42/Aß1-40 ratio in cerebrospinal fluid. Methods We analysed retrospective data from two cohorts (memory clinic cohort and ADNI) of patients (n = 63) with an Aß1-42/Aß1-40 ratio within a predefined borderline area—Q1 above the validated cut-off value(grey zone). We compared demographic, clinical, neuropsychological and neuroimaging features between grey zone patients and patients with low Aß1-42 (normal Aß ratio but pathological Aß1-42, n = 42) and patients with AD (pathological Aß, P-Tau, und T-Tau, n = 80). Results Patients had mild cognitive impairment or mild dementia and a median age of 72 years. Demographic and general clinical characteristics did not differ between the groups. Patients in the grey zone group were the least impaired in cognition. However, they overlapped with the low Aß1-42 group in verbal episodic memory performance, especially in delayed recall and recognition. The grey zone group had less severe medial temporal atrophy, but mild posterior atrophy and mild white matter hyperintensities, similar to the low Aß1-42 group. Conclusions Patients in the Aß ratio grey zone were less impaired, but showed clinical overlap with patients on the AD continuum. These borderline patients may be at an earlier disease stage. Assuming an increased risk of AD and progressive cognitive decline, careful consideration of clinical follow-up is recommended when using dichotomous approaches to classify Aß status.

Abstract There is strong interest in developing predictive models to better understand individual heterogeneity and disease progression in Alzheimer's disease (AD). We have built upon previous longitudinal AD progression models, using a nonlinear, mixed‐effect modeling approach to predict Clinical Dementia Rating Scale – Sum of Boxes (CDR‐SB) progression. Data from the Alzheimer's Disease Neuroimaging Initiative (observational study) and placebo arms from four interventional trials (N = 1093) were used for model building. The placebo arms from two additional interventional trials (N = 805) were used for external model validation. In this modeling framework, CDR‐SB progression over the disease trajectory timescale was obtained for each participant by estimating disease onset time (DOT). Disease progression following DOT was described by both global progression rate (RATE) and individual progression rate (α). Baseline Mini‐Mental State Examination and CDR‐SB scores described the interindividual variabilities in DOT and α well. This model successfully predicted outcomes in the external validation datasets, supporting its suitability for prospective prediction and use in design of future trials. By predicting individual participants' disease progression trajectories using baseline characteristics and comparing these against the observed responses to new agents, the model can help assess treatment effects and support decision making for future trials.

Abstract Introduction Estimation of brain amyloid accumulation is valuable for evaluation of patients with cognitive impairment in both research and clinical routine. The development of high throughput and accurate strategies for the determination of amyloid status could be an important tool in patient selection for clinical trials and amyloid directed treatment. Here, we propose the use of deep learning to quantify amyloid accumulation using standardized uptake value ratio (SUVR) and classify amyloid status based on their PET images. Methods A total of 1309 patients with cognitive impairment scanned with [11C]PIB PET/CT or PET/MRI were included. Two convolutional neural networks (CNNs) for reading-based amyloid status and SUVR prediction were trained using 75% of the PET/CT data. The remaining PET/CT (n = 300) and all PET/MRI (n = 100) data was used for evaluation. Results The prevalence of amyloid positive patients was 61%. The amyloid status classification model reproduced the expert reader’s classification with 99% accuracy. There was a high correlation between reference and predicted SUVR (R 2 = 0.96). Both reference and predicted SUVR had an accuracy of 97% compared to expert classification when applying a predetermined SUVR threshold of 1.35 for binary classification of amyloid status. Conclusion The proposed CNN models reproduced both the expert classification and quantitative measure of amyloid accumulation in a large local dataset. This method has the potential to replace or simplify existing clinical routines and can facilitate fast and accurate classification well-suited for a high throughput pipeline.

Abstract Background Emerging difficulty performing cognitively complex everyday tasks, or ‘instrumental activities of daily living’ (IADL) may be an early clinical sign of Alzheimer’s disease (AD). We aimed to investigate how changes over time in everyday functioning relate to cerebral tau burden across the AD clinical spectrum. Methods We included 581 participants (73.9 ± 7.6 years old; 52% female) from the Alzheimer’s Disease Neuroimaging Initiative who underwent tau positron emission tomography (PET) and completed at least two assessments of the Functional Activities Questionnaire (FAQ). Participants were classified as cognitively normal (n = 334) or symptomatic (n = 247). We analyzed the association between longitudinal FAQ scores and baseline tau in six temporal, parietal, and frontal brain regions in mixed-effects models. Models were run in the entire sample, as well as stratified by diagnostic group (cognitively normal or symptomatic). We additionally investigated tau-PET adjusted for, as well as interacting with, amyloid-β. Results Greater tau burden in several frontal, temporal, and parietal regions was associated with steeper decline over time in everyday functioning. These findings remained when adjusting for baseline global cortical amyloid-β; amyloid-β itself was only associated with change over time in FAQ scores when tau was not included in the model. When stratifying by diagnostic group, most associations between tau and everyday functioning, adjusted for amyloid-β, were present only in the symptomatic group. Conclusions The rate of change in everyday functioning is related to baseline tau burden in various brain regions, more strongly so than global cortical amyloid-β, specifically in cognitively symptomatic individuals. Longitudinal studies in incident dementia populations are needed to better understand functional changes in response to AD pathology across the disease.

Mild Cognitive Impairment (MCI) is a cognitive state frequently observed in older adults, characterized by significant alterations in memory, thinking, and reasoning abilities that extend beyond typical cognitive decline. It is worth noting that around 10–15% of individuals with MCI are projected to develop Alzheimer’s disease, effectively positioning MCI as an early stage of Alzheimer’s. In this study, a novel approach is presented involving the utilization of eXtreme Gradient Boosting to predict the onset of Alzheimer’s disease during the MCI stage. The methodology entails utilizing data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Through the analysis of longitudinal data, spanning from the baseline visit to the 12-month follow-up, a predictive model was constructed. The proposed model calculates, over a 36-month period, the likelihood of progression from MCI to Alzheimer’s disease, achieving an accuracy rate of 85%. To further enhance the precision of the model, this study implements feature selection using the Recursive Feature Elimination technique. Additionally, the Shapley method is employed to provide insights into the model’s decision-making process, thereby augmenting the transparency and interpretability of the predictions.

Alzheimer’s disease (AD) is the most prevalent neurodegenerative disease, yet its current treatments are limited to stopping disease progression. Moreover, the effectiveness of these treatments remains uncertain due to the heterogeneity of the disease. Therefore, it is essential to identify disease subtypes at a very early stage. Current data-driven approaches can be used to classify subtypes during later stages of AD or related disorders, but making predictions in the asymptomatic or prodromal stage is challenging. Furthermore, the classifications of most existing models lack explainability, and these models rely solely on a single modality for assessment, limiting the scope of their analysis. Thus, we propose a multimodal framework that utilizes early-stage indicators, including imaging, genetics, and clinical assessments, to classify AD patients into progression-specific subtypes at an early stage. In our framework, we introduce a tri-modal co-attention mechanism (Tri-COAT) to explicitly capture cross-modal feature associations. Data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (slow progressing = 177, intermediate = 302, and fast = 15) were used to train and evaluate Tri-COAT using a 10-fold stratified cross-testing approach. Our proposed model outperforms baseline models and sheds light on essential associations across multimodal features supported by known biological mechanisms. The multimodal design behind Tri-COAT allows it to achieve the highest classification area under the receiver operating characteristic curve while simultaneously providing interpretability to the model predictions through the co-attention mechanism.

Abstract Background Alzheimer’s disease is a neurodegenerative disorder associated with the abnormal deposition of pathological processes, such as amyloid-ß and tau, which produces nonlinear changes in the functional connectivity patterns between different brain regions across the Alzheimer’s disease continuum. However, the mechanisms underlying these nonlinear changes remain largely unknown. Here, we address this question using a novel method based on temporal or delayed correlations and calculate new whole-brain functional networks to tackle these mechanisms. Methods To assess our method, we evaluated 166 individuals from the ADNI database, including amyloid-beta negative and positive cognitively normal subjects, patients with mild cognitive impairment, and patients with Alzheimer’s disease dementia. We used the clustering coefficient and the global efficiency to measure the functional network topology and assessed their relationship with amyloid and tau pathology measured by positron emission tomography, as well as cognitive performance using tests measuring memory, executive function, attention, and global cognition. Results Our study found nonlinear changes in the global efficiency, but not in the clustering coefficient, showing that the nonlinear changes in functional connectivity are due to an altered ability of brain regions to communicate with each other through direct paths. These changes in global efficiency were most prominent in early disease stages. However, later stages of Alzheimer’s disease were associated with widespread network disruptions characterized by changes in both network measures. The temporal delays required for the detection of these changes varied across the Alzheimer’s disease continuum, with shorter delays necessary to detect changes in early stages and longer delays necessary to detect changes in late stages. Both global efficiency and clustering coefficient showed quadratic associations with pathological amyloid and tau burden as well as cognitive decline. Conclusions This study suggests that global efficiency is a more sensitive indicator of network changes in Alzheimer’s disease when compared to clustering coefficient. Both network properties were associated with pathology and cognitive performance, demonstrating their relevance in clinical settings. Our findings provide an insight into the mechanisms underlying nonlinear changes in functional network organization in Alzheimer’s disease, suggesting that it is the lack of direct connections that drives these functional changes.

Abstract Background Alzheimer’s disease-related pattern (ADRP) is a metabolic brain biomarker of Alzheimer’s disease (AD). While ADRP is being introduced into research, the effect of the size of the identification cohort and the effect of the resolution of identification and validation images on ADRP’s performance need to be clarified. Methods 240 2-[18F]fluoro-2-deoxy-d-glucose positron emission tomography images [120 AD/120 cognitive normals (CN)] were selected from the Alzheimer's disease neuroimaging initiative database. A total of 200 images (100 AD/100 CN) were used to identify different versions of ADRP using a scaled subprofile model/principal component analysis. For this purpose, five identification groups were randomly selected 25 times. The identification groups differed in the number of images (20 AD/20 CN, 30 AD/30 CN, 40 AD/40 CN, 60 AD/60 CN, and 80 AD/80 CN) and image resolutions (6, 8, 10, 12, 15 and 20 mm). A total of 750 ADRPs were identified and validated through the area under the curve (AUC) values on the remaining 20 AD/20 CN with six different image resolutions. Results ADRP’s performance for the differentiation between AD patients and CN demonstrated only a marginal average AUC increase, when the number of subjects in the identification group increases (AUC increase for about 0.03 from 20 AD/20 CN to 80 AD/80 CN). However, the average of the lowest five AUC values increased with the increasing number of participants (AUC increase for about 0.07 from 20 AD/20 CN to 30 AD/30 CN and for an additional 0.02 from 30 AD/30 CN to 40 AD/40 CN). The resolution of the identification images affects ADRP’s diagnostic performance only marginally in the range from 8 to 15 mm. ADRP’s performance stayed optimal even when applied to validation images of resolution differing from the identification images. Conclusions While small (20 AD/20 CN images) identification cohorts may be adequate in a favorable selection of cases, larger cohorts (at least 30 AD/30 CN images) shall be preferred to overcome possible/random biological differences and improve ADRP’s diagnostic performance. ADRP’s performance stays stable even when applied to the validation images with a resolution different than the resolution of the identification ones.

Abstract Background The progression of Alzheimer’s dementia (AD) can be classified into three stages: cognitive unimpairment (CU), mild cognitive impairment (MCI), and AD. The purpose of this study was to implement a machine learning (ML) framework for AD stage classification using the standard uptake value ratio (SUVR) extracted from 18F-flortaucipir positron emission tomography (PET) images. We demonstrate the utility of tau SUVR for AD stage classification. We used clinical variables (age, sex, education, mini-mental state examination scores) and SUVR extracted from PET images scanned at baseline. Four types of ML frameworks, such as logistic regression, support vector machine (SVM), extreme gradient boosting, and multilayer perceptron (MLP), were used and explained by Shapley Additive Explanations (SHAP) to classify the AD stage. Results Of a total of 199 participants, 74, 69, and 56 patients were in the CU, MCI, and AD groups, respectively; their mean age was 71.5 years, and 106 (53.3%) were men. In the classification between CU and AD, the effect of clinical and tau SUVR was high in all classification tasks and all models had a mean area under the receiver operating characteristic curve (AUC) > 0.96. In the classification between MCI and AD, the independent effect of tau SUVR in SVM had an AUC of 0.88 (p

Abstract Introduction Although machine learning classifiers have been frequently used to detect Alzheimer’s disease (AD) based on structural brain MRI data, potential bias with respect to sex and age has not yet been addressed. Here, we examine a state-of-the-art AD classifier for potential sex and age bias even in the case of balanced training data. Methods Based on an age- and sex-balanced cohort of 432 subjects (306 healthy controls, 126 subjects with AD) extracted from the ADNI data base, we trained a convolutional neural network to detect AD in MRI brain scans and performed ten different random training-validation-test splits to increase robustness of the results. Classifier decisions for single subjects were explained using layer-wise relevance propagation. Results The classifier performed significantly better for women (balanced accuracy $$87.58\pm 1.14\%$$ 87.58 ± 1.14 % ) than for men ( $$79.05\pm 1.27\%$$ 79.05 ± 1.27 % ). No significant differences were found in clinical AD scores, ruling out a disparity in disease severity as a cause for the performance difference. Analysis of the explanations revealed a larger variance in regional brain areas for male subjects compared to female subjects. Discussion The identified sex differences cannot be attributed to an imbalanced training dataset and therefore point to the importance of examining and reporting classifier performance across population subgroups to increase transparency and algorithmic fairness. Collecting more data especially among underrepresented subgroups and balancing the dataset are important but do not always guarantee a fair outcome.

Abstract Background Crucial to the success of clinical trials targeting early Alzheimer’s disease (AD) is recruiting participants who are more likely to progress over the course of the trials. We hypothesize that a combination of plasma and structural MRI biomarkers, which are less costly and non-invasive, is predictive of longitudinal progression measured by atrophy and cognitive decline in early AD, providing a practical alternative to PET or cerebrospinal fluid biomarkers. Methods Longitudinal T1-weighted MRI, cognitive (memory-related test scores and clinical dementia rating scale), and plasma measurements of 245 cognitively normal (CN) and 361 mild cognitive impairment (MCI) patients from ADNI were included. Subjects were further divided into β-amyloid positive/negative (Aβ+/Aβ−)] subgroups. Baseline plasma (p-tau181 and neurofilament light chain) and MRI-based structural medial temporal lobe subregional measurements and their association with longitudinal measures of atrophy and cognitive decline were tested using stepwise linear mixed effect modeling in CN and MCI, as well as separately in the Aβ+/Aβ− subgroups. Receiver operating characteristic (ROC) analyses were performed to investigate the discriminative power of each model in separating fast and slow progressors (first and last terciles) of each longitudinal measurement. Results A total of 245 CN (35.0% Aβ+) and 361 MCI (53.2% Aβ+) participants were included. In the CN and MCI groups, both baseline plasma and structural MRI biomarkers were included in most models. These relationships were maintained when limited to the Aβ+ and Aβ− subgroups, including Aβ− CN (normal aging). ROC analyses demonstrated reliable discriminative power in identifying fast from slow progressors in MCI [area under the curve (AUC): 0.78–0.93] and more modestly in CN (0.65–0.73). Conclusions The present data support the notion that plasma and MRI biomarkers, which are relatively easy to obtain, provide a prediction for the rate of future cognitive and neurodegenerative progression that may be particularly useful in clinical trial stratification and prognosis. Additionally, the effect in Aβ− CN indicates the potential use of these biomarkers in predicting a normal age-related decline.

Alzheimer’s disease (AD) is an irreversible neurodegenerative disease with a high prevalence in the elderly population over 65 years of age. Intervention in the early stages of AD is of great significance to alleviate the symptoms. Recent advances in deep learning have shown extreme advantages in computer-aided diagnosis of AD. However, most studies only focus on extracting features from slices in specific directions or whole brain images, ignoring the complementarity between features from different angles. To overcome the above problem, attention-based multi-view slice fusion (AMSF) is proposed for accurate early diagnosis of AD. It adopts the fusion of three-dimensional (3D) global features with multi-view 2D slice features by using an attention mechanism to guide the fusion of slice features for each view, to generate a comprehensive representation of the MRI images for classification. The experiments on the public dataset demonstrate that AMSF achieves 94.3% accuracy with 1.6–7.1% higher than other previous promising methods. It indicates that the better solution for AD early diagnosis depends not only on the large scale of the dataset but also on the organic combination of feature construction strategy and deep neural networks.

IntroductionAlzheimer’s disease (AD) is a complex neurodegenerative disease with high heritability. Compared to autosomes, a higher proportion of disorder-associated genes on X chromosome are expressed in the brain. However, only a few studies focused on the identification of the susceptibility loci for AD on X chromosome.MethodsUsing the data from the Alzheimer’s Disease Neuroimaging Initiative Study, we conducted an X chromosome-wide association study between 16 AD quantitative biomarkers and 19,692 single nucleotide polymorphisms (SNPs) based on both the cross-sectional and longitudinal studies.ResultsWe identified 15 SNPs statistically significantly associated with different quantitative biomarkers of the AD. For the cross-sectional study, six SNPs (rs5927116, rs4596772, rs5929538, rs2213488, rs5920524, and rs5945306) are located in or near to six genes DMD, TBX22, LOC101928437, TENM1, SPANXN1, and ZFP92, which have been reported to be associated with schizophrenia or neuropsychiatric diseases in literature. For the longitudinal study, four SNPs (rs4829868, rs5931111, rs6540385, and rs763320) are included in or near to two genes RAC1P4 and AFF2, which have been demonstrated to be associated with brain development or intellectual disability in literature, while the functional annotations of other five novel SNPs (rs12157031, rs428303, rs5953487, rs10284107, and rs5955016) have not been found.Discussion15 SNPs were found statistically significantly associated with the quantitative biomarkers of the AD. Follow-up study in molecular genetics is needed to verify whether they are indeed related to AD. The findings in this article expand our understanding of the role of the X chromosome in exploring disease susceptibility, introduce new insights into the molecular genetics behind the AD, and may provide a mechanistic clue to further AD-related studies.

Abstract Introduction It is unclear how rates of white matter microstructural decline differ between normal aging and abnormal aging. Methods Diffusion MRI data from several well‐established longitudinal cohorts of aging (Alzheimer's Disease Neuroimaging Initiative [ADNI], Baltimore Longitudinal Study of Aging [BLSA], Vanderbilt Memory & Aging Project [VMAP]) were free‐water corrected and harmonized. This dataset included 1723 participants (age at baseline: 72.8 ± 8.87 years, 49.5% male) and 4605 imaging sessions (follow‐up time: 2.97 ± 2.09 years, follow‐up range: 1–13 years, mean number of visits: 4.42 ± 1.98). Differences in white matter microstructural decline in normal and abnormal agers was assessed. Results While we found a global decline in white matter in normal/abnormal aging, we found that several white matter tracts (e.g., cingulum bundle) were vulnerable to abnormal aging. Conclusions There is a prevalent role of white matter microstructural decline in aging, and future large‐scale studies in this area may further refine our understanding of the underlying neurodegenerative processes. HIGHLIGHTS Longitudinal data were free‐water corrected and harmonized. Global effects of white matter decline were seen in normal and abnormal aging. The free‐water metric was most vulnerable to abnormal aging. Cingulum free‐water was the most vulnerable to abnormal aging.

Abstract INTRODUCTION The precise apolipoprotein E (APOE) ε4‐specific molecular pathway(s) for Alzheimer's disease (AD) risk are unclear. METHODS Plasma protein modules/cascades were analyzed using weighted gene co‐expression network analysis (WGCNA) in the Alzheimer's Disease Neuroimaging Initiative study. Multivariable regression analyses were used to examine the associations among protein modules, AD diagnoses, cerebrospinal fluid (CSF) phosphorylated tau (p‐tau), and brain glucose metabolism, stratified by APOE genotype. RESULTS The Green Module was associated with AD diagnosis in APOE ε4 homozygotes. Three proteins from this module, C‐reactive protein (CRP), complement C3, and complement factor H (CFH), had dose‐dependent associations with CSF p‐tau and cognitive impairment only in APOE ε4 homozygotes. The link among these three proteins and glucose hypometabolism was observed in brain regions of the default mode network (DMN) in APOE ε4 homozygotes. A Framingham Heart Study validation study supported the findings for AD. DISCUSSION The study identifies the APOE ε4–specific CRP–C3–CFH inflammation pathway for AD, suggesting potential drug targets for the disease. Highlights Identification of an APOE ε4 specific molecular pathway involving blood CRP, C3, and CFH for the risk of AD. CRP, C3, and CFH had dose‐dependent associations with CSF p‐Tau and brain glucose hypometabolism as well as with cognitive impairment only in APOE ε4 homozygotes. Targeting CRP, C3, and CFH may be protective and therapeutic for AD onset in APOE ε4 carriers.

Abstract INTRODUCTION BrainAge models based on neuroimaging data have diagnostic classification power but have replicability issues due to site and patient variability. BrainAge models trained on neuropsychological tests could help distinguish stable mild cognitive impairment (sMCI) from progressive MCI (pMCI) to Alzheimer's disease (AD). METHODS A linear regressor BrainAge model was trained on healthy controls using neuropsychological tests and neuroimaging features separately. The BrainAge delta, predicted age minus chronological age, was used to distinguish between sMCI and pMCI. RESULTS The cross‐validated area under the receiver‐operating characteristic (ROC) curve for sMCI versus pMCI was 0.91 for neuropsychological features in contrast to 0.68 for neuroimaging features. The BrainAge delta was correlated with the time to conversion, the time taken for a pMCI subject to convert to AD. DISCUSSION The BrainAge delta from neuropsychological tests is a good biomarker to distinguish between sMCI and pMCI. Other neurological and psychiatric disorders could be studied using this strategy. Highlights BrainAge models based on neuropsychological tests outperform models based on neuroimaging features when distinguishing between stable mild cognitive impairment (sMCI) from progressive MCI (pMCI) to Alzheimer's disease (AD). The combination of neuropsychological tests with neuroimaging features does not lead to an improvement in sMCI versus pMCI classification compared to using neuropsychological tests on their own. BrainAge delta of both neuroimaging and neuropsychological models was correlated with the time to conversion, the time taken for a pMCI subject to convert to AD.

Abstract Introduction Discovery of the associations between brain structural connectivity and clinical and demographic variables can help to better understand the vulnerability and resilience of the brain architecture to neurodegenerative diseases and to discover biomarkers. Methods We used four diffusion‐MRI databases, three related to Alzheimer's disease (AD), to exploratorily correlate structural connections between 85 brain regions with non‐MRI variables, while stringently correcting the significance values for multiple testing and ruling out spurious correlations via careful visual inspection. We repeated the analysis with brain connectivity augmented with multi‐synaptic neural pathways. Results We found 85 and 101 significant relationships with direct and augmented connectivity, respectively, which were generally stronger for the latter. Age was consistently linked to decreased connectivity, and healthier clinical scores were generally linked to increased connectivity. Discussion Our findings help to elucidate which structural brain networks are affected in AD and aging and highlight the importance of including indirect connections.

IntroductionStratification of Alzheimer’s disease (AD) patients into risk subgroups using Polygenic Risk Scores (PRS) presents novel opportunities for the development of clinical trials and disease-modifying therapies. However, the heterogeneous nature of AD continues to pose significant challenges for the clinical broadscale use of PRS. PRS remains unfit in demonstrating sufficient accuracy in risk prediction, particularly for individuals with mild cognitive impairment (MCI), and in allowing feasible interpretation of specific genes or SNPs contributing to disease risk. We propose adORS, a novel oligogenic risk score for AD, to better predict risk of disease by using an optimized list of relevant genetic risk factors.MethodsUsing whole genome sequencing data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort (n = 1,545), we selected 20 genes that exhibited the strongest correlations with FDG-PET and AV45-PET, recognized neuroimaging biomarkers that detect functional brain changes in AD. This subset of genes was incorporated into adORS to assess, in comparison to PRS, the prediction accuracy of CN vs. AD classification and MCI conversion prediction, risk stratification of the ADNI cohort, and interpretability of the genetic information included in the scores.ResultsadORS improved AUC scores over PRS in both CN vs. AD classification and MCI conversion prediction. The oligogenic model also refined risk-based stratification, even without the assistance of APOE, thus reflecting the true prevalence rate of the ADNI cohort compared to PRS. Interpretation analysis shows that genes included in adORS, such as ATF6, EFCAB11, ING5, SIK3, and CD46, have been observed in similar neurodegenerative disorders and/or are supported by AD-related literature.DiscussionCompared to conventional PRS, adORS may prove to be a more appropriate choice of differentiating patients into high or low genetic risk of AD in clinical studies or settings. Additionally, the ability to interpret specific genetic information allows the focus to be shifted from general relative risk based on a given population to the information that adORS can provide for a single individual, thus permitting the possibility of personalized treatments for AD.

Abstract Background There is a critical need for novel primary endpoints designed to detect early and subtle changes in cognition in clinical trials targeting the asymptomatic (preclinical) phase of Alzheimer’s disease (AD). The Alzheimer’s Prevention Initiative (API) Generation Program, conducted in cognitively unimpaired individuals at risk of developing AD (e.g., enriched by the apolipoprotein E (APOE) genotype), used a novel dual primary endpoints approach, whereby demonstration of treatment effect in one of the two endpoints is sufficient for trial success. The two primary endpoints were (1) time to event (TTE)—with an event defined as a diagnosis of mild cognitive impairment (MCI) due to AD and/or dementia due to AD—and (2) change from baseline to month 60 in the API Preclinical Composite Cognitive (APCC) test score. Methods Historical observational data from three sources were used to fit models to describe the TTE and the longitudinal APCC decline, both in people who do and do not progress to MCI or dementia due to AD. Clinical endpoints were simulated based on the TTE and APCC models to assess the performance of the dual endpoints versus each of the two single endpoints, with the selected treatment effect ranging from a hazard ratio (HR) of 0.60 (40% risk reduction) to 1 (no effect). Results A Weibull model was selected for TTE, and power and linear models were selected to describe the APCC score for progressors and non-progressors, respectively. Derived effect sizes in terms of reduction of the APCC change from baseline to year 5 were low (0.186 for HR = 0.67). The power for the APCC alone was consistently lower compared to the power of TTE alone (58% [APCC] vs 84% [TTE] for HR = 0.67). Also, the overall power was higher for the 80%/20% distribution (82%) of the family-wise type 1 error rate (alpha) between TTE and APCC compared to 20%/80% (74%). Conclusions Dual endpoints including TTE and a measure of cognitive decline perform better than the cognitive decline measure as a single primary endpoint in a cognitively unimpaired population at risk of AD (based on the APOE genotype). Clinical trials in this population, however, need to be large, include older age, and have a long follow-up period of at least 5 years to be able to detect treatment effects.