Alzheimer’s disease is a neurodegenerative disorder affecting elderly people and no cure is available till date. Photo: iStock
Alzheimer’s disease is a neurodegenerative disorder affecting elderly people and no cure is available till date. Photo: iStock

Scientists develop data framework for early detection of Alzheimer’s disease

NBRC scientists have proposed a big data framework that provides an integration of various modalities at one platform. The proposed framework facilitates to normalize and preprocess raw MRI, MRS and neuropsychological data into a suitable format that can be used for further processing

New Delhi: Scientists at National Brain Research Centre (NBRC) have developed a Big data framework (BHARAT) using brain’s structural, neurochemical and behavioral features extracted from MRI for early detection of Alzheimer’s disease.

Alzheimer’s disease is a neurodegenerative disorder affecting elderly people and no cure is available till date.

“Progressive and relentless efforts are in war footing for therapeutic development by understanding involving non-invasive imaging modalities for the causal molecular process of Alzheimer’s disease. We have come up with a big data analytics named as BHARAT," said Pravat K. Mandal, Scientist and Senior Professor at Neuroimaging and Neurospectroscopy Laboratory, NBRC.

Big data collections are combination of multi-modal dataset which are individually manageable but as a group they are huge to handle seamlessly and accurately using a single machine.

Multi-modal imaging techniques such as MRI, magnetic resonance spectroscopy (MRS), functional MRI (fMRI), positron emission tomography (PET), are being used extensively to identify early diagnostic biomarkers for Alzheimer’s disease. Scientists say that behavioural information derived from various neuropsychological tests are also useful to aid in Alzheimer’s disease diagnosis .

“The heterogeneous and diverse data generated worldwide from imaging, spectroscopy and neuropsychology necessitate a common platform for coherent multi-modal data processing and analysis scheme for the identification of distinctive diagnostic features specific to Alzheimer’s disease,"’Said Mandal.

NBRC scientists have proposed a big data framework that provides an integration of various modalities at one platform. The proposed framework facilitates to normalize and pre-process raw MRI, MRS and neuropsychological data into a suitable format that can be used for further processing.

“With the growth in data generation, machine learning faces the challenge of efficiently processing and learning from big data. In this context, the development of advance tools involving big data analytics (BDA) is need of the hour for handling enormous volume of diverse data, which is growing with extraordinary velocity," said Mandal.

In the proposed framework, the pre-processed big data will be managed and stored and used for diagnosis.

“We would like to emphasize that big data analytics for early diagnostics from various modalities at present is just based on MRI images of patients. The neurochemical like antioxidant glutathione depletion analysis from brain hippocamal regions are extremely sensitive and specific with more than high 92% sensitivity and 94% specificity. This perspective bring these novel features to be included which are close to the disease process and present a realistic approach," Madnal said.

“Large-scale data analysis using brain imaging, metabolic and neuropsychological score provide information about disease progression and identify early diagnostic biomarker. . Hence conceptualization of BIG analytics using three critical information is an important step and it will likely to give a contribution in development of working BDA framework, where medical physicists, clinicians, engineers will work hand in hand to help an effective tool for early diagnosis or prediction of Alzheimer’s disease," said Mandal.

Asked about novelty of the big data analytics “BHARAT", Mandal indicated that this multi-model big data scheme is the first in the scientific literature where neurochemical, structural and behavioral features, are considered for seamless processing in our big data platform. He also said that artificial intelligence is also in place in our updated new scheme. It may likely help us to identify the causal process for Alzheimer’s disease, which can direct the research community for more focused direction for therapeutic development and subsequent clinical trial.

Close