Dataset Information

Cognitive biomarker prioritization in Alzheimer's Disease using brain morphometric data.

ABSTRACT:

Background

Cognitive assessments represent the most common clinical routine for the diagnosis of Alzheimer's Disease (AD). Given a large number of cognitive assessment tools and time-limited office visits, it is important to determine a proper set of cognitive tests for different subjects. Most current studies create guidelines of cognitive test selection for a targeted population, but they are not customized for each individual subject. In this manuscript, we develop a machine learning paradigm enabling personalized cognitive assessments prioritization.

Method

We adapt a newly developed learning-to-rank approach [Formula: see text] to implement our paradigm. This method learns the latent scoring function that pushes the most effective cognitive assessments onto the top of the prioritization list. We also extend [Formula: see text] to better separate the most effective cognitive assessments and the less effective ones.

Results

Our empirical study on the ADNI data shows that the proposed paradigm outperforms the state-of-the-art baselines on identifying and prioritizing individual-specific cognitive biomarkers. We conduct experiments in cross validation and level-out validation settings. In the two settings, our paradigm significantly outperforms the best baselines with improvement as much as 22.1% and 19.7%, respectively, on prioritizing cognitive features.

Conclusions

The proposed paradigm achieves superior performance on prioritizing cognitive biomarkers. The cognitive biomarkers prioritized on top have great potentials to facilitate personalized diagnosis, disease subtyping, and ultimately precision medicine in AD.

SUBMITTER: Peng B

PROVIDER: S-EPMC7709267 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Cognitive biomarker prioritization in Alzheimer's Disease using brain morphometric data.

Peng Bo B Yao Xiaohui X Risacher Shannon L SL Saykin Andrew J AJ Shen Li L Ning Xia X

BMC medical informatics and decision making 20201202 1

<h4>Background</h4>Cognitive assessments represent the most common clinical routine for the diagnosis of Alzheimer's Disease (AD). Given a large number of cognitive assessment tools and time-limited office visits, it is important to determine a proper set of cognitive tests for different subjects. Most current studies create guidelines of cognitive test selection for a targeted population, but they are not customized for each individual subject. In this manuscript, we develop a machine learning ...[more]

PMID: 33267852

Similar Datasets

Project description:A definitive diagnosis of Alzheimer's disease (AD), even in the presence of co-morbid neuropathology (occurring in > 50% of AD cases), is a significant unmet medical need that has obstructed the discovery of effective AD therapeutics. An AD-biomarker, the Morphometric Imaging (MI) assay on cultured skin fibroblasts, was used in a double-blind, allcomers (ages 55-90) trial of 3 patient cohorts: AD dementia patients, N = 25, all autopsy confirmed, non-AD dementia patients, N = 21-all autopsy or genetically confirmed; and non-demented control (AHC) patients N = 27. Fibroblasts cells isolated from 3-mm skin punch biopsies were cultured on a 3-D Matrigel matrix with movement dynamics quantified by image analysis. From counts of all aggregates (N) in a pre-defined field image and measures of the average area (A) of aggregates per image, the number-to-area ratios in a natural logarithmic form Ln(A/N) were determined for all patient samples. AD cell lines formed fewer large aggregates (cells clustered together) than non-AD or AHC cell lines. The cut-off value of Ln(A/N) = 6.98 was determined from the biomarker values of non-demented apparently healthy control (AHC) cases. Unequivocal validation by autopsy, genetics, and/or dementia criteria was possible for all 73 patient samples. The samples were collected from multiple centers-four US centers and one center in Japan. The study found no effect of center-to-center variation in fibroblast isolation, cell growth, or cell aggregation values (Ln(A/N)). The autopsy-confirmed MI Biomarker distinguished AD from non-AD dementia (non-ADD) patients and correctly diagnosed AD even in the presence of other co-morbid pathologies at autopsy (True Positive = 25, False Negative = 0, False Positive = 0, True Negative = 21, and Accuracy = 100%. Sensitivity and specificity were calculated as 100% (95% CI = 84 to 100.00%). From these findings, the MI assay appears to detect AD with great accuracy-even with abundant co-morbidity.

Project description:Multiple biomarkers can capture different facets of Alzheimer's disease. However, statistical models of biomarkers to predict outcomes in Alzheimer's rarely model nonlinear interactions between these measures. Here, we used Gaussian Processes to address this, modelling nonlinear interactions to predict progression from mild cognitive impairment (MCI) to Alzheimer's over 3 years, using Alzheimer's Disease Neuroimaging Initiative (ADNI) data. Measures included: demographics, APOE4 genotype, CSF (amyloid-β42, total tau, phosphorylated tau), [18F ]florbetapir, hippocampal volume and brain-age. We examined: (a) the independent value of each biomarker; and (b) whether modelling nonlinear interactions between biomarkers improved predictions. Each measured added complementary information when predicting conversion to Alzheimer's. A linear model classifying stable from progressive MCI explained over half the variance (R2 = 0.51, p < .001); the strongest independently contributing biomarker was hippocampal volume (R2 = 0.13). When comparing sensitivity of different models to progressive MCI (independent biomarker models, additive models, nonlinear interaction models), we observed a significant improvement (p < .001) for various two-way interaction models. The best performing model included an interaction between amyloid-β-PET and P-tau, while accounting for hippocampal volume (sensitivity = 0.77, AUC = 0.826). Closely related biomarkers contributed uniquely to predict conversion to Alzheimer's. Nonlinear biomarker interactions were also implicated, and results showed that although for some patients adding additional biomarkers may add little value (i.e., when hippocampal volume is high), for others (i.e., with low hippocampal volume) further invasive and expensive examination may be warranted. Our framework enables visualisation of these interactions, in individual patient biomarker 'space', providing information for personalised or stratified healthcare or clinical trial design.

Dataset Information

Cognitive biomarker prioritization in Alzheimer's Disease using brain morphometric data.

Background

Method

Results

Conclusions

Publications

Cognitive biomarker prioritization in Alzheimer's Disease using brain morphometric data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets