Alzheimer disease brain atrophy subtypes are associated with cognition and rate of decline

Risacher, Shannon L.; Anderson, Wesley; Charil, Arnaud; Castelluccio, Peter; Shcherbinin, Sergey; Saykin, Andrew J.; Schwarz, Adam J.

doi:10.1212/wnl.0000000000004670

Cited by 142 publications

(206 citation statements)

References 33 publications

Supporting

Mentioning

185

Contrasting

Order By: Relevance

“…There are also several limitations. First, compared with other studies, we had an overrepresentation of limbic‐predominant and especially hippocampal‐sparing cases relative to typical patients with AD, possibly due to cohort effects, methodological aspects, or the relatively young mean age of the sample. However, group characteristics were largely in line with previous studies (e.g., younger age and APOE ɛ4 prevalence in hippocampal‐sparing AD), suggesting that comparable subtypes were captured across studies.…”

Section: Discussionmentioning

confidence: 87%

“…Various structural neuroimaging approaches have been used to identify subtypes of Alzheimer's disease (AD) based on patterns of regional atrophy . These studies identified reproducible AD subtypes, namely “limbic‐predominant”, “hippocampal‐sparing”, “typical” (i.e., a combination of limbic‐predominant and hippocampal‐sparing) AD, and, to a lesser extent, “mild atrophy” AD .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distinct tau PET patterns in atrophy‐defined subtypes of Alzheimer's disease

Ossenkoppele

Lyoo

Sudre

et al. 2020

Alzheimer's & Dementia

View full text Add to dashboard Cite

Introduction: Differential patterns of brain atrophy on structural magnetic resonance imaging (MRI) revealed four reproducible subtypes of Alzheimer's disease (AD): (1) "typical", (2) "limbic-predominant", (3) "hippocampal-sparing", and (4) "mild atrophy". We examined the neurobiological characteristics and clinical progression of these atrophydefined subtypes. Methods:The four subtypes were replicated using a clustering method on MRI data in 260 amyloid--positive patients with mild cognitive impairment or AD dementia, and we subsequently tested whether the subtypes differed on [ 18 F]flortaucipir (tau) positron emission tomography, white matter hyperintensity burden, and rate of global cognitive decline. Results: Voxel-wise and region-of-interest analyses revealed the greatest neocortical tau load in hippocampal-sparing (frontoparietal-predominant) and typicalThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made. c ○ 2019 The Authors. Alzheimer's & Dementia published by Wiley Periodicals, Inc. on behalf of Alzheimer's Association. Alzheimer's Dement. 2020;16:335-344. wileyonlinelibrary.com/journal/alz 335 336 OSSENKOPPELE ET AL.

show abstract

Section: Discussionmentioning

confidence: 87%

Section: Introductionmentioning

confidence: 99%

Distinct tau PET patterns in atrophy‐defined subtypes of Alzheimer's disease

Ossenkoppele

Lyoo

Sudre

et al. 2020

Alzheimer's & Dementia

View full text Add to dashboard Cite

show abstract

“…One possible future direction is to investigate new features, e.g., those derived from diffusion MRI or arterial spin labeling. Previous studies have also suggested that different atrophy patterns (beyond the temporal lobe) might influence cognitive decline early in the disease process (Noh et al, 2014;Byun et al, 2015;Ferreira et al, 2017;Zhang et al, 2016;Risacher et al, 2017;Sun et al, 2019), so the atrophy features considered in this study (Table 1) might not be optimal. Although the new features may be correlated with currently used features, the new features might still provide complementary information when modeling AD progression (Popescu et al, 2019).…”

Section: Discussionmentioning

confidence: 96%

“…Consequently, there is significant interest in predicting the longitudinal disease progression of individuals. A major difficulty is that although AD commonly presents as an amnestic syndrome, there is significant heterogeneity across individuals (Murray et al, 2011;Noh et al, 2014;Zhang et al, 2016;Risacher et al, 2017;Young et al, 2018;Sun et al, 2019). Since AD dementia is marked by beta-amyloid-and tau-mediated injuries, followed by brain atrophy and cognitive decline (Jack et al, , 2013, a multimodal approach might be more effective than a single modality approach to disentangle this heterogeneity and predict longitudinal disease progression .…”

Section: Introductionmentioning

confidence: 99%

Predicting Alzheimer’s disease progression using deep recurrent neural networks

Nguyen

et al. 2019

Preprint

View full text Add to dashboard Cite

Early identification of individuals at risk of developing Alzheimer's disease (AD) dementia is important for developing disease-modifying therapies. In this study, given multimodal AD markers and clinical diagnosis of an individual from one or more timepoints, we seek to predict the clinical diagnosis, cognition and ventricular volume of the individual for every month (indefinitely) into the future. We proposed a recurrent neural network (RNN) model and applied it to data from The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) challenge, comprising longitudinal data of 1677 participants (Marinescu et al. 2018) from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We compared the performance of the RNN model and three baseline algorithms up to 6 years into the future.Most previous work on predicting AD progression ignore the issue of missing data, which is a prevalent issue in longitudinal data. Here, we explored three different strategies to handle missing data. Two of the strategies treated the missing data as a "preprocessing" issue, by imputing the missing data using the previous timepoint ("forward filling") or linear interpolation ("linear filling). The third strategy utilized the RNN model itself to fill in the missing data both during training and testing ("model filling"). Our analyses suggest that the RNN with "model filling" was better than baseline algorithms, including support vector machine/regression and linear state space (LSS) models. However, there was no statistical difference between the RNN and LSS for predicting cognition and ventricular volume.Importantly, although the training procedure utilized longitudinal data, we found that the trained RNN model exhibited similar performance, when using only 1 input timepoint or 4 input timepoints, suggesting that our approach might work well with just cross-sectional data.An earlier version of our approach was ranked 5th (out of 53 entries) in the TADPOLE challenge in 2019. The current approach is ranked 2nd out of 56 entries as of August 12th, 2019.

show abstract

“…9,14,37 In fact, cognition has been identified as a primary predictor as well as a moderator variable when examining different types of functioning. 9,38 Compromised attention, frontal dysfunction (ie, initiation, perseveration, and conceptualization), poor construction abilities, and impaired memory, all cognitive abilities measured in this study, would explain worsening abilities to accomplish many instrumental activities of daily living (IADLs). New important scientific work in brain network connectivity for persons with dementia, 39 and specifically among persons with DLB, 40 may hold structural and functional explanations for the association between worsening cognition and function.…”

Section: Compromised Cognitionmentioning

confidence: 92%

Associations among Braak stage, Parkinsonian gait, cognition, and functional status in autopsy‐confirmed dementia with Lewy bodies

Mayo

Peavy

2019

Int J Geriat Psychiatry

View full text Add to dashboard Cite

Objective Compromised functional abilities in older adults with dementia with Lewy bodies (DLB) represent a significant burden to families and frequently lead to institutionalization. Contributing factors to this compromise are poorly understood. Methods Using data collected at a first study visit, multiple regression modeling was used to examine the associations between Braak staged Alzheimer disease (AD) pathology, Apolipoprotein E (ApoE) status, Parkinsonian gait, cognition, and functional status from a cohort of 102 cases with an autopsy‐confirmed diagnosis of dementia stemming from combined Lewy body and AD pathology. Results On average, 60% of functional activities were compromised per case. Worse functional status was associated with older age at first study visit, compromised cognitive status, and Parkinsonian gait after controlling for gender, mental status, and other covariates. Worse cognitive status predicted worse functional status in both the low and high Braak groups. Conclusions Older persons with DLB presenting with moderately compromised cognition and Parkinsonian gait should be expected to have impaired functional abilities. Providing these patients with supportive environments may help them to remain independent for longer periods of time.

show abstract

Alzheimer disease brain atrophy subtypes are associated with cognition and rate of decline

Cited by 142 publications

References 33 publications

Distinct tau PET patterns in atrophy‐defined subtypes of Alzheimer's disease

Distinct tau PET patterns in atrophy‐defined subtypes of Alzheimer's disease

Predicting Alzheimer’s disease progression using deep recurrent neural networks

Associations among Braak stage, Parkinsonian gait, cognition, and functional status in autopsy‐confirmed dementia with Lewy bodies

Contact Info

Product

Resources

About