AUTHOR=Sharma Ankita , Shukla Deepika , Goel Tripti , Mandal Pravat Kumar 

TITLE=BHARAT: An Integrated Big Data Analytic Model for Early Diagnostic Biomarker of Alzheimer's Disease

JOURNAL=Frontiers in Neurology

VOLUME=Volume 10 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2019.00009

DOI=10.3389/fneur.2019.00009

ISSN=1664-2295

ABSTRACT=Alzheimer’s disease (AD) is a devastating neurodegenerative brain disorder affecting cognitive ability of millions of people worldwide. Progressive and relentless efforts are in war footing for therapeutic development by understanding involving non-invasive imaging modalities for the causal molecular process of AD, involving non-invasive imaging modalities. Currently available structural, functional and MR spectroscopic studies are being used to aid in effective AD diagnosis. The ‘Big Data’ of multi-modal AD informatics can be unified to analyze, address and advance AD research. We present a Hadoop based big data framework integrating non-invasive magnetic resonance imaging (MRI), MR spectroscopy (MRS) as well as neuropsychological test outcomes to identify early diagnostic biomarkers for early prediction of AD. The big data framework for AD incorporating the 3V’s (volume, variety, velocity) involves technological advancement inwith advanced data mining, machine learning and statistical modeling algorithms. Large volume of longitudinal information from non-invasive imaging modalities with colligated parametric variety and speed for both data acquisition and processing as velocity complete the fundamental necessity of big data framework in for early AD diagnosis research. Brain Structuralstructural, neurochemical and behavioral features are extracted for MRI, MRS and neuropsychological score data respectively. Afterwards Subsequently feature selection, ensemble based classification are proposed and their outputs are fused based on combination rule for final accurate classification and validation from clinician. Furthermore, results are verified from clinician. Multi-modalities based decision framework (BHARAT) for classification of early AD disease will immensely help in finding reliable early diagnostic marker for AD will be. immensely helpful