Dataset Information

Improving brain age prediction models: incorporation of amyloid status in Alzheimer's disease.

ABSTRACT: Brain age prediction is a machine learning method that estimates an individual's chronological age from their neuroimaging scans. Brain age indicates whether an individual's brain appears "older" than age-matched healthy peers, suggesting that they may have experienced a higher cumulative exposure to brain insults or were more impacted by those pathological insults. However, contemporary brain age models include older participants with amyloid pathology in their training sets and thus may be confounded when studying Alzheimer's disease (AD). We showed that amyloid status is a critical feature for brain age prediction models. We trained a model on T1-weighted MRI images participants without amyloid pathology. MRI data were processed to estimate gray matter density voxel-wise, which were then used to predict chronological age. Our model performed accurately comparable to previous models. Notably, we demonstrated more significant differences between AD diagnostic groups than other models. In addition, our model was able to delineate significant differences in brain age relative to chronological age between cognitively normal individuals with and without amyloid. Incorporation of amyloid status in brain age prediction models ultimately improves the utility of brain age as a biomarker for AD.

SUBMITTER: Ly M

PROVIDER: S-EPMC7064421 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving brain age prediction models: incorporation of amyloid status in Alzheimer's disease.

Ly Maria M Yu Gary Z GZ Karim Helmet T HT Muppidi Nishita R NR Mizuno Akiko A Klunk William E WE Aizenstein Howard J HJ

Neurobiology of aging 20191114

Brain age prediction is a machine learning method that estimates an individual's chronological age from their neuroimaging scans. Brain age indicates whether an individual's brain appears "older" than age-matched healthy peers, suggesting that they may have experienced a higher cumulative exposure to brain insults or were more impacted by those pathological insults. However, contemporary brain age models include older participants with amyloid pathology in their training sets and thus may be con ...[more]

PMID: 31843257

Similar Datasets

Project description:Machine Learning methods are often adopted to infer useful biomarkers for the early diagnosis of many neurodegenerative diseases and, in general, of neuroanatomical ageing. Some of these methods estimate the subject age from morphological brain data, which is then indicated as "brain age". The difference between such a predicted brain age and the actual chronological age of a subject can be used as an indication of a pathological deviation from normal brain ageing. An important use of the brain age model as biomarker is the prediction of Alzheimer's disease (AD) from structural Magnetic Resonance Imaging (MRI). Many different machine learning approaches have been applied to this specific predictive task, some of which have achieved high accuracy at the expense of the descriptiveness of the model. This work investigates an appropriate combination of data science techniques and linear models to provide, at the same time, high accuracy and good descriptiveness. The proposed method is based on a data workflow that include typical data science methods, such as outliers detection, feature selection, linear regression, and logistic regression. In particular, a novel inductive bias is introduced in the regression model, which is aimed at improving the accuracy and the specificity of the classification task. The method is compared to other machine learning approaches for AD classification based on morphological brain data with and without the use of the brain age, including Support Vector Machines and Deep Neural Networks. This study adopts brain MRI scans of 1, 901 subjects which have been acquired from three repositories (ADNI, AIBL, and IXI). A predictive model based only on the proposed apparent brain age and the chronological age has an accuracy of 88% and 92%, respectively, for male and female subjects, in a repeated cross-validation analysis, thus achieving a comparable or superior performance than state of the art machine learning methods. The advantage of the proposed method is that it maintains the morphological semantics of the input space throughout the regression and classification tasks. The accurate predictive model is also highly descriptive and can be used to generate potentially useful insights on the predictions.

Project description:Alzheimer's disease begins about two decades before the onset of symptoms or neuron death, and is believed to be caused by pathogenic amyloid-? aggregates that initiate a cascade of molecular events culminating in widespread neurodegeneration. The microtubule binding protein tau may mediate the effects of amyloid-? in this cascade. Amyloid plaques comprised of insoluble, fibrillar amyloid-? aggregates are the most characteristic feature of Alzheimer's disease. However, the correspondence between the distribution of plaques and the pattern of neurodegeneration is tenuous. This discrepancy has stimulated the investigation of other amyloid-? aggregates, including soluble amyloid-? oligomers. Different soluble amyloid-? oligomers have been studied in several mouse models, but not systematically in humans. Here, we measured three amyloid-? oligomers previously described in mouse models-amyloid-? trimers, A?*56 and amyloid-? dimers-in brain tissue from 75 cognitively intact individuals, ranging from young children to the elderly, and 58 impaired subjects with mild cognitive impairment or probable Alzheimer's disease. As in mouse models, where amyloid-? trimers appear to be the fundamental amyloid-? assembly unit of A?*56 and are present in young mice prior to memory decline, amyloid-? trimers in humans were present in children and adolescents; their levels rose gradually with age and were significantly above baseline in subjects in their 70s. A?*56 levels were negligible in children and young adults, rose significantly above baseline in subjects in their 40s and increased steadily thereafter. Amyloid-? dimers were undetectable until subjects were in their 60s; their levels then increased sharply and correlated with plaque load. Remarkably, in cognitively intact individuals we found strong positive correlations between A?*56 and two pathological forms of soluble tau (tau-CP13 and tau-Alz50), and negative correlations between A?*56 and two postsynaptic proteins (drebrin and fyn kinase), but none between amyloid-? dimers or amyloid-? trimers and tau or synaptic proteins. Comparing impaired with age-matched unimpaired subjects, we found the highest levels of amyloid-? dimers, but the lowest levels of A?*56 and amyloid-? trimers, in subjects with probable Alzheimer's disease. In conclusion, in cognitively normal adults A?*56 increased ahead of amyloid-? dimers or amyloid-? trimers, and pathological tau proteins and postsynaptic proteins correlated with A?*56, but not amyloid-? dimers or amyloid-? trimers. We propose that A?*56 may play a pathogenic role very early in the pathogenesis of Alzheimer's disease.

Project description:Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R 2 = 0.88; support vector regression, MAE = 4.42 years, R 2 = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R 2 = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.

Dataset Information

Improving brain age prediction models: incorporation of amyloid status in Alzheimer's disease.

Publications

Improving brain age prediction models: incorporation of amyloid status in Alzheimer's disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets