AI-Based Classification of Mild Cognitive Impairment and Cognitively Normal Patients.

Decision letter: Stage-dependent differential influence of metabolic and structural networks on memory across Alzheimer’s disease continuum

Search for Clinical Markers Could? Transform Alzheimer's Drug Research

BackgroundEarly prevention of Alzheimer’s disease (AD) is a feasible way to delay AD onset and progression. Information on AD prediction at the individual patient level will be useful in AD prevention. In this study, we aim to develop risk models for predicting AD onset at individual level using optimal set of predictors from multiple features.MethodsA total of 487 cognitively normal (CN) individuals and 796 mild cognitive impairment (MCI) patients were included from Alzheimer's Disease Neuroimaging Initiative. All the participants were assessed for clinical, cognitive, magnetic resonance imaging and cerebrospinal fluid (CSF) markers and followed for mean periods of 5.6 years for CN individuals and 4.6 years for MCI patients to ascertain progression from CN to incident prodromal stage of AD or from MCI to AD dementia. Least Absolute Shrinkage and Selection Operator Cox regression was applied for predictors selection and model construction.ResultsDuring the follow-up periods, 139 CN participants had progressed to prodromal AD (CDR ≥ 0.5) and 321 MCI patients had progressed to AD dementia. In the prediction of individual risk of incident prodromal stage of AD in CN individuals, the AUC of the final CN model was 0.81 within 5 years. The final MCI model predicted individual risk of AD dementia in MCI patients with an AUC of 0.92 within 5 years. The models were also associated with longitudinal change of Mini-Mental State Examination (p < 0.001 for CN and MCI models). An Alzheimer’s continuum model was developed which could predict the Alzheimer’s continuum for individuals with normal AD biomarkers within 3 years with high accuracy (AUC = 0.91).ConclusionsThe risk models were able to provide personalized risk for AD onset at each year after evaluation. The models may be useful for better prevention of AD.

BackgroundAlzheimer's Disease (AD) presents a major health challenge, with complex and variable neurodegenerative progression. Traditional neuroimaging falls short in fully capturing this heterogeneity. Our study addresses this gap by applying an Event‐Based Model (EBM) to Alzheimer's Disease Neuroimaging Initiative (ADNI) Positron Emission Tomography (PET) data, enriched with connectomics data. This innovative approach promises a more individualized understanding of AD progression, combining PET imaging with insights into brain connectivity from connectomics. Our work aims to enhance early diagnosis and personalized treatment strategies in AD research.MethodOur study applied an Event‐Based Model (EBM) to Alzheimer's Disease Neuroimaging Initiative (ADNI) datasets across ADNI1, ADNI2, and ADNI3. We analyzed a diverse cohort including Alzheimer's Disease (AD), Mild Cognitive Impairment (MCI), Late MCI (LMCI), Early MCI (EMCI), and cognitively normal (CN) groups, using Amyloid (AMY), Fluorodeoxyglucose (FDG), and Tau PET scans. The methodology integrated connectomics data and employed Monte Carlo Markov Chain (MCMC) techniques for enhanced modeling precision. This approach provided an in‐depth understanding of AD progression, combining advanced statistical analysis with diverse neuroimaging data.ResultOptimal order of neurodegenerative events ‐ stages of disease progression as measured by changes in metabolic signature (FDG) or Amyloid accumulation ‐ largely followed previously published results. Earliest regions of Amyloid accumulation mirrored the default mode network (Figure 1). Metabolic changes, notably reduction in FDG SUVR, occurred earliest in the same top 10 regions. Also Z‐test statistic (‐4.78): Indicates a significant difference between the average stages of AD and MCI patients, with AD stages being lower than those of MCI. P‐value (∼0.00000177): Implies an extremely low probability that the observed difference in stages occurred by chance, strongly suggesting a true difference between the groups.ConclusionWe have presented a novel connectome‐informed progression model of amyloid‐beta accumulation and metabolic changes in the brain. The model discriminates well between stages of cognitive decline and suggests that amyloid accumulation and metabolic changes both follow a similar early of pattern conditioned on white‐matter connectivity

In recent years, increasing attention has been given to the identification of the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD). Brain neuroimaging techniques have been widely used to support the classification or prediction of MCI. The present study combined magnetic resonance imaging (MRI), 18F-fluorodeoxyglucose PET (FDG-PET), and 18F-florbetapir PET (florbetapir-PET) to discriminate MCI converters (MCI-c, individuals with MCI who convert to AD) from MCI non-converters (MCI-nc, individuals with MCI who have not converted to AD in the follow-up period) based on the partial least squares (PLS) method. Two types of PLS models (informed PLS and agnostic PLS) were built based on 64 MCI-c and 65 MCI-nc from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The results showed that the three-modality informed PLS model achieved better classification accuracy of 81.40%, sensitivity of 79.69%, and specificity of 83.08% compared with the single-modality model, and the three-modality agnostic PLS model also achieved better classification compared with the two-modality model. Moreover, combining the three modalities with clinical test score (ADAS-cog), the agnostic PLS model (independent data: florbetapir-PET; dependent data: FDG-PET and MRI) achieved optimal accuracy of 86.05%, sensitivity of 81.25%, and specificity of 90.77%. In addition, the comparison of PLS, support vector machine (SVM), and random forest (RF) showed greater diagnostic power of PLS. These results suggested that our multimodal PLS model has the potential to discriminate MCI-c from the MCI-nc and may therefore be helpful in the early diagnosis of AD.

Mild cognitive impairment (MCI) and preclinical MCI (e.g., subjective cognitive decline, SCD) are considered risk states of dementia, such as Alzheimer's Disease (AD). However, it is challenging to accurately predict conversion from normal cognition (NC) to MCI, which is important for early detection and intervention. Since neuropathological changes may have occurred in the brain many years before clinical AD, we sought to detect the subtle brain changes in the pre-MCI stage using a deep-learning method based on structural Magnetic Resonance Imaging (MRI). To discover early structural neuroimaging changes that differentiate between stable and progressive cognitive status, and to establish a predictive model for MCI conversion. We first created a unique deep-learning framework for pre-AD conversion prediction through the Alzheimer's Disease Neuroimaging Initiative-1 (ADNI-1) database (n = 845). Then, we tested the model on ADNI-2 (n = 321, followed 3 years) and our private study (n = 109), the China Longitudinal Aging Study (CLAS), to validate the rationality for pre-MCI conversion prediction. The CLAS is a 7-year community-based cohort study in Shanghai. Our framework consisted of two steps: 1) a single-ROI-based network (SRNet) for identifying informative regions in the brain, and 2) a multi-ROI-based network (MRNet) for pre-AD conversion prediction. We then utilized these "ROI-based deep learning" neural networks to create a composite score using advanced algorithm-building. We coined this score as the Progressive Index (PI), which serves as a metric for assessing the propensity of AD conversion. Ultimately, we employed the PI to gauge its predictive capability for MCI conversion in both ADNI-2 and CLAS datasets. We primarily utilized baseline T1-weighted MRI scans to identify the most discriminative brain regions and subsequently developed the PI in both training and validation datasets. We compared the PI across different cognitive groups and conducted logistic regression models along with their AUCs, adjusting for education level, gender, neuropsychological test scores, and the presence of comorbid conditions. We trained the SRNet and MRNet using 845 subjects from ADNI-1 with baseline MRI data, in which AD and progressive MCI (converting to AD within 3 years) patients were considered as positive samples, while NC and stable MCI (remaining stable for 3 years) subjects were considered as negative samples. The convolutional neural networks identified the top 10 regions of interest (ROIs) for distinguishing progressive from stable cases. These key brain regions included the hippocampus, amygdala, temporal lobe, insula, and anterior cerebellum. A total of 321 subjects from ADNI-2, including 209 NC (18 progressive NC (pNC), 113 stable NC (sNC), and 78 remaining NC (rNC)) and 112 SCD (11 pSCD, 5 sSCD, and 96 rSCD), as well as 109 subjects from CLAS, including 17 sNC, 16 pNC, 52 sSCD and 24 pSCD participated in the test set, separately. We found that the PI score effectively sorted all subjects by their stages (stable vs progressive). Furthermore, the PI score demonstrated excellent discrimination between the two outcomes in the CLAS data(p<0.001), even after controlling for age, gender, education level, depression symptoms, anxiety symptoms, somatic diseases, and baseline MoCA score. Better performance for prediction progression to MCI in CLAS was obtained when the PI score was combined with clinical measures (AUC=0.812; 95 %CI: 0.725-0.900). This study effectively predicted the progression to MCI among order individuals at normal cognition state by deep learning algorithm with MRI scans. Exploring the key brain alterations during the very early stages, specifically the transition from NC to MCI, based on deep learning methods holds significant potential for further research and contributes to a deeper understanding of disease mechanisms.

Obesity is linked with lower brain volume in 700 AD and MCI patients.

BackgroundAlzheimer's Disease (AD) presents a major health challenge, with complex and variable neurodegenerative progression. Traditional neuroimaging falls short in fully capturing this heterogeneity. Our study addresses this gap by applying an Event‐Based Model (EBM) to Alzheimer's Disease Neuroimaging Initiative (ADNI) Positron Emission Tomography (PET) data, enriched with connectomics data. This innovative approach promises a more individualized understanding of AD progression, combining PET imaging with insights into brain connectivity from connectomics. Our work aims to enhance early diagnosis and personalized treatment strategies in AD research.MethodOur study applied an Event‐Based Model (EBM) to Alzheimer's Disease Neuroimaging Initiative (ADNI) datasets across ADNI1, ADNI2, and ADNI3. We analyzed a diverse cohort including Alzheimer's Disease (AD), Mild Cognitive Impairment (MCI), Late MCI (LMCI), Early MCI (EMCI), and cognitively normal (CN) groups, using Amyloid (AMY), Fluorodeoxyglucose (FDG), and Tau PET scans. The methodology integrated connectomics data and employed Monte Carlo Markov Chain (MCMC) techniques for enhanced modeling precision. This approach provided an in‐depth understanding of AD progression, combining advanced statistical analysis with diverse neuroimaging data.ResultOptimal order of neurodegenerative events ‐ stages of disease progression as measured by changes in metabolic signature (FDG) or Amyloid accumulation ‐ largely followed previously published results. Earliest regions of Amyloid accumulation mirrored the default mode network (Figure 1). Metabolic changes, notably reduction in FDG SUVR, occurred earliest in the same top 10 regions. Also Z‐test statistic (‐4.78): Indicates a significant difference between the average stages of AD and MCI patients, with AD stages being lower than those of MCI.P‐value (∼0.00000177): Implies an extremely low probability that the observed difference in stages occurred by chance, strongly suggesting a true difference between the groups.ConclusionWe have presented a novel connectome‐informed progression model of amyloid‐beta accumulation and metabolic changes in the brain. The model discriminates well between stages of cognitive decline and suggests that amyloid accumulation and metabolic changes both follow a similar early of pattern conditioned on white‐matter connectivity

Spatio-temporal convolution for classification of alzheimer disease and mild cognitive impairment

α-Synuclein (α-Syn) pathology is present in 30-50 % of Alzheimer's disease (AD) patients, and its interactions with tau proteins may further exacerbate pathological changes in AD. However, the specific role of different aggregation forms of α-Syn in the progression of AD remains unclear. To explore the relationship between various aggregation types of CSF α-Syn and Alzheimer's disease progression. We conducted a retrospective analysis of data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to examine the association between different α-Syn aggregation forms-Syn0 (no detectable α-Syn aggregates) and Syn1 (α-Syn aggregates detected, resembling those found in Parkinson's disease)-with the pathological and clinical features of AD. Additionally, we evaluated their potential as predictors of conversion from mild cognitive impairment (MCI) to AD. The ADNI database. A total of 250 participants, including 70 cognitively normal controls, 119 patients diagnosed with MCI, and 61 patients diagnosed with AD. Pearson correlation was employed to assess the relationship between α-Syn levels and cerebrospinal fluid (CSF) biomarkers, including total tau (T-tau), phosphorylated tau (p-tau), and amyloid-β42 (Aβ42). Multivariate Cox proportional hazards models were applied, adjusting for APOE4 status, age, and sex, to determine the association between α-Syn forms and AD-related pathological and clinical outcomes. Kaplan-Meier curves were used to evaluate the prognostic value of different α-Syn aggregation states in predicting the conversion from MCI to AD. Compared with controls, overall MCI and AD patients had elevated α-Syn levels. Notably, in the α-Syn0 group, α-Syn levels were increased in the MCI patients and further increased in AD patients, whereas in the α-Syn1 group, α-Syn levels did not significantly differ across diagnostic groups. Both in the α-Syn0 and α-Syn1 groups, α-Syn levels were found to correlate more strongly with CSF tau levels than with Aβ42, indicating a possible role for α-Syn in tau-related pathology in AD. Importantly, α-Syn0-AD patients exhibited more rapid cognitive decline and greater hippocampal atrophy than α-Syn1-AD patients. However, MCI patients with CSF α-Syn1 aggregation status had an increased risk of conversion to AD. CSF α-Syn is associated with tau pathology and neurodegeneration in Alzheimer's disease. The distinct aggregation profiles of α-Syn serve as valuable biomarkers, offering insights into differing prognoses in AD and aiding in the prediction of early disease progression.

High Activities of BACE1 in Brains with Mild Cognitive Impairment

INTRODUCTIONHearing loss is identified as one of the largest modifiable risk factors for cognitive impairment and dementia. Studies evaluating this relationship have yielded mixed results.METHODSWe investigated the longitudinal relationship between self‐reported hearing loss and cognitive/functional performance in 695 cognitively normal (CN) and 941 participants with mild cognitive impairment (MCI) enrolled in the Alzheimer's Disease Neuroimaging Initiative.RESULTSWithin CN participants with hearing loss, there was a significantly greater rate of cognitive decline per modified preclinical Alzheimer's cognitive composite. Within both CN and MCI participants with hearing loss, there was a significantly greater rate of functional decline per the functional activities questionnaire (FAQ). In CN and MCI participants, hearing loss did not significantly contribute to the risk of progression to a more impaired diagnosis.DISCUSSIONThese results confirm previous studies demonstrating a significant longitudinal association between self‐reported hearing loss and cognition/function but do not demonstrate an increased risk of conversion to a more impaired diagnosis.CLINICAL TRIAL REGISTRATION INFORMATIONNCT00106899 (ADNI: Alzheimer's Disease Neuroimaging Initiative, clinicaltrials.gov), NCT01078636 (ADNI‐GO: Alzheimer's Disease Neuroimaging Initiative Grand Opportunity, clinicaltrials.gov), NCT01231971 (ADNI2: Alzheimer's Disease Neuroimaging Initiative 2, clinicaltrials.gov), NCT02854033 (ADNI3: Alzheimer's Disease Neuroimaging Initiative 3, clinicaltrials.gov).HighlightsHearing loss is a potential modifiable risk factor for dementia.We assessed the effect of self‐reported hearing loss on cognition and function in the ADNI cohort.Hearing loss contributes to significantly faster cognitive and functional decline.Hearing loss was not associated with conversion to a more impaired diagnosis.

Background and Aims The glymphatic system is a network of extracellular spaces between neurons, glial cells, and capillaries that promotes the elimination of soluble molecules from the brain. Its dysfunction is probably relevant for neurodegenerative diseases such as Alzheimer's disease (AD). It is widely accepted that cognitive impairment accompanies chronic kidney disease (CKD). CKD is also a risk factor for dementia. However, the role of the glymphatic system in this process is unknown. A recent method to study the glymphatic system in human subjects has been proposed based on Diffusion Tensor Imaging (DTI) data and water diffusion calculation along with perivascular spaces. This approach is based on calculating a diffusion index named ALPS and showed that the glymphatic flow is reduced in MCI. Method To analyze the role of glymphatic system in CKD patients, we took advantage of the Alzheimer's Disease Neuroimaging Initiative (ADNI). ADNI is a longitudinal multicenter study helping researchers to monitor Alzheimer's disease and Mild Cognitive Impairment (MCI) progression. This database has a cohort of control patients and MCI patients, among which several patients with CKD stage II-III were identifiable from the creatinine values. Patients with Alzheimer's disease were excluded for this study. Among the control and MCI patients, we identified 12 CKD patients and pair-matched 12 non-CKD patients comparable for age, gender, and MoCA score. Magnetic resonance data with DTI sequences were retrieved for all patients, and the glymphatic system was characterized by the ALPS index. Tensor values were calculated using the FSL software; the diffusion values were calculated on tensor images using the ImageJ software. Differences in ALPS between CKD and non-CKD patients with and without MCI were tested. Results Analysis of DTI data confirmed that control patients without CKD had lower ALPS values when MCI was present compared to the non-MCI patients, suggesting a reduction of water diffusion in the glymphatic system. However, the presence of CKD had a different effect: in the absence of MCI, CKD did not modify ALPS values compared to non-CKD patients. At variance, in patients with MCI, CKD resulted in a significant increase of water diffusion in the glymphatic system compared to the controls. Conclusion In this preliminary study, MCI and CKD exerted opposite effects on the diffusion of water within the glymphatic system: MCI was accompanied by a reduction of water diffusion whereas CKD by an increased diffusion in the glymphatic spaces. It is possible that small modification of water balance in CKD may be responsible for the increased diffusion of water in glymphatics in CKD. Further studies are needed to verify whether this unexpected phenomenon may modify cognitive function with a mechanism rather different from Alzheimer's disease.

Twelve-month metabolic declines in probable Alzheimer's disease and amnestic mild cognitive impairment assessed using an empirically pre-defined statistical region-of-interest: Findings from the Alzheimer's Disease Neuroimaging Initiative

Brain controllability distinctiveness between depression and cognitive impairment