SOCR Data AD BiomedBigMetadata

From Socr

(Difference between revisions)
Jump to: navigation, search
IvoDinov (Talk | contribs)
(Created page with '== SOCR Data - Modeling and Analysis of Clinical, Genetic and Imaging Data of Alzheimer’s Disease == ==Summary== These data include massive heterogeneous clinical, genetic…')
Newer edit →

Revision as of 00:29, 7 December 2012

Contents

SOCR Data - Modeling and Analysis of Clinical, Genetic and Imaging Data of Alzheimer’s Disease

Summary

These data include massive heterogeneous clinical, genetic and imaging data of Alzheimer’s disease.

Background

There are megabytes of health-related metadata some of which is incomplete, irrelevant or difficult to establish homologies between different variables or subjects. In this dataset, missing values are denoted by (“.”).

The goal is to interrogate the data using exploratory and quantitative data analysis methods and look for patterns, trends or relations that may provide cues to the diagnosis, cognitive state or prognosis of these subjects (patients and control). Specifically, one may investigate the following:

  • Identify clusters of data that agrees with specific phenotypes (e.g., Diagnosis/Dx) or traits (e.g., NPI scores).
  • Reduce the dimensionality of the data and identify linear sub-spaces that contain large between subject variations or expose common traits.
  • Plan the integration of imaging biomarkers with these clinical and demographic data. The new Pipeline mechanism for Study-Designs enables the integrated analysis of imaging and meta-data (more information on the pipeline is available here).

Although SOCR Tools may be useful for some of this analysis, most of the interesting analyses may require the use of graphical Pipeline workflows, R, Matlab, C/C++/Java and other computational libraries/tools can be compiled as stand-alone execs and wrapped in XML as Pipeline modules, http://ucla.in/TI94HR). This allows openly sharing of the complete protocols (pipeline.xml.pipe files) for the entire community to replicate, revise, validate, and cite.


Classroom use of this data set

Interactions between Groups and NIPS scores

This data set can be used to illustrate (multivariate, logistic) regression analyses, non-parametric tests, classification/clustering approaches, and diverse array of exploratory data analyses.

Data Description

...


Data Table

References

  • ...



Translate this page:

(default)

Deutsch

Español

Français

Italiano

Português

日本語

България

الامارات العربية المتحدة

Suomi

इस भाषा में

Norge

한국어

中文

繁体中文

Русский

Nederlands

Ελληνικά

Hrvatska

Česká republika

Danmark

Polska

România

Sverige

Personal tools