An emphasis in ongoing Alzheimer's disease (AD) research is identifying those biomarkers which best predict future cognitive decline at the various stages of disease progression. These biomarkers can then serve as early markers for diagnosis, and for selection of subjects into clinical trials. Recent results suggest that the identification of such discriminative biomarkers is possible by adapting machine learning methods for this problem: but studies have primarily used modalities in isolation so far. The sensitivity/specificity offered by these methods is unsatisfactory for more clinically relevant questions: which MCI patients will convert to AD? Answering such questions requires new methods that leverage all data sources (e.g., imaging modalities, CSF measures) in conjunction. This project focuses on how data from multiple biomarkers should be optimally aggregated to best predict future cognitive decline, and how these models can improve clinical trials for AD. Hypothesis: Significant improvements in sensitivity and specificity for discriminating AD, MCI, and healthy controls at the level of individual subjects are possible by making use of multiple modalities (together with longitudinal data) simultaneously. Further, these methods will significantly improve sample size estimates in clinical trials, and help derive customized outcomes for evaluating new treatment procedures.
Specific Aims : (1) To develop new image-based machine learning algorithms that can take advantage of multiple modalities simultaneously within a unified framework. (2) To provide a software and extensively evaluate these methods on the ADNI and BLSA datasets, to assess the sensitivity/specificity attainable by truly multi-modal analysis methods. (3) To interface multi-modal classification methods with AD clinical trials: (a) by developing comprehensive sample size estimates needed to observe specific outcomes, and using these methods to derive customized outcomes for an ongoing R01-funded observational/prospective study here at the Wisconsin ADRC. Methods: We will develop new multi-modal machine learning methods that will optimally exploit all data sources simultaneously. Our models will also incorporate longitudinal data, and exploit interaction between modalities at different stages of the disease. This will be used to derive a Multi-Modal Disease Marker (MMDM) (Aim 1). The algorithms will be evaluated on large-scale well-characterized datasets and provided as software tools (Aim 2). We will use these models to improve AD clinical trials in two ways: by sample enrichment and customized outcomes that provide maximum statistical power to detect treatment effects (Aim 3). Significance: This project capitalizes on the Wisconsin ADRC's expertise in machine learning, statistical clinical trial design, imaging, and clinical diagnosis of AD and pre-AD conditions. This project will be the first to implement a multi-modal machine learning metric specifically designed to speed up clinical trials so that potential therapies can be evaluated and an effective treatment arrived at as quickly as possible.

Public Health Relevance

This project will develop novel methods and software systems for highly accurate and automated identification of patterns related to Alzheimer's disease. The techniques will take advantage of the aggregate information from an individual's brain images from multiple imaging modalities such as structural images (e.g., Magnetic Resonance) and functional images (e.g., Positron Emission Tomography), as well as cognitive and demographic information. The software, as a result of successful completion of this project, will provide invaluable assistance in AD diagnosis (and predicting cognitive decline) at the level of individual subjects, as well as allow clinical experiments to be more effective in evaluating which drugs and treatments are effective for such neurological disorders.

Agency
National Institute of Health (NIH)
Type
Research Project (R01)
Project #
5R01AG040396-03
Application #
8704341
Study Section
Special Emphasis Panel (ZRG1)
Program Officer
Ryan, Laurie M
Project Start
Project End
Budget Start
Budget End
Support Year
3
Fiscal Year
2014
Total Cost
Indirect Cost
Name
University of Wisconsin Madison
Department
Biostatistics & Other Math Sci
Type
Schools of Medicine
DUNS #
City
Madison
State
WI
Country
United States
Zip Code
53715
Kim, Hyunwoo J; Smith, Brandon M; Adluru, Nagesh et al. (2016) Abundant Inverse Regression using Sufficient Reduction and its Applications. Comput Vis ECCV 9907:570-584
Hwang, Seong Jae; Adluru, Nagesh; Collins, Maxwell D et al. (2016) Coupled Harmonic Bases for Longitudinal Characterization of Brain Networks. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2016:2517-2525
Kim, Won Hwa; Hwang, Seong Jae; Adluru, Nagesh et al. (2016) Adaptive Signal Recovery on Graphs via Harmonic Analysis for Experimental Design in Neuroimaging. Comput Vis ECCV 9910:188-205
Kim, Won Hwa; Ravi, Sathya N; Johnson, Sterling C et al. (2015) On Statistical Analysis of Neuroimages with Imperfect Registration. Proc IEEE Int Conf Comput Vis 2015:666-674
Hwang, Seong Jae; Collins, Maxwell D; Ravi, Sathya N et al. (2015) A Projection free method for Generalized Eigenvalue Problem with a nonsmooth Regularizer. Proc IEEE Int Conf Comput Vis 2015:1841-1849
Xut, Jia; Mukherjee, Lopamudra; Li, Yin et al. (2015) Gaze-enabled Egocentric Video Summarization via Constrained Submodular Maximization. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2015:2235-2244
Kim, Won Hwa; Singh, Vikas; Chung, Moo K et al. (2015) MULTI-RESOLUTION STATISTICAL ANALYSIS ON GRAPH STRUCTURED DATA IN NEUROIMAGING. Proc IEEE Int Symp Biomed Imaging 2015:1548-1551
Kim, Won Hwa; Adluru, Nagesh; Chung, Moo K et al. (2015) Multi-resolution statistical analysis of brain connectivity graphs in preclinical Alzheimer's disease. Neuroimage 118:103-17
Kim, Won Hwa; Bendlin, Barbara B; Chung, Moo K et al. (2015) Statistical Inference Models for Image Datasets with Systematic Variations. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2015:4795-4803
Kim, Hyunwoo J; Xu, Jia; Vemuri, Baba C et al. (2015) Manifold-valued Dirichlet Processes. Proc Int Conf Mach Learn 2015:1199-1208

Showing the most recent 10 out of 28 publications