The National Brain Research Center (NBRC) at Gurgaon is dedicated to research in the frontier areas of neuroscience and brain function in health and disease. Research areas include cells, molecules, systems, behavior, and computational neuroscience. Dr Pravat Mandal, Director in-charge NBRC and honorary professor of neuroscience and mental health Melbourne, Australia, talks about BHARAT, the novel platform that can help an early detection of Alzheimer’s Disease and what should be imbibed to prevent memory loss and mild cognitive impairment. Edited excerpts:
Please brief about Bharat—the multi model big data platform that can be used to predict Alzheimer’s. Why did you decide to develop this?
BHARAT is an integrated big data analytical (BDA) model for early diagnostic biomarkers of Alzheimer’s disease (AD). To date, AD pathogenesis and effective diagnostic intervention remain unclear. However, it is believed that the available solution is to control its progression from mild cognitive impairment (MCI) to AD.
Early diagnostic biomarkers originating from the combined analysis of the information derived from multi-modal data (magnetic resonance imaging (MRI), MR spectroscopy (MRS) and neuropsychological) can provide insights to the actual cause of AD. This will finally lead to therapeutic interventions to be followed by clinical trials.
To identify diagnostic AD biomarkers for a large amount of diversified data (specifically for Indian population) with the help of accurate feature extraction and classification, a new multi-modal BDA system framework in the form of BHARAT was proposed. The platform is designed for collecting, storing, organizing, and analyzing the multi-modal neuroimaging of big data.
How does the platform function?
The platform uses a Hadoop-based big data computing framework integrating non-invasive MRI, MRS as well as neuropsychological test outcomes to identify early diagnostic biomarkers of AD. The framework facilitates accommodation of a massive amount of heterogeneous data followed by data-specific pre-processing, analysis of processed data outcomes, and inference of diagnostic results. It has four components: Data Normalization, Data Management, Data Storage, and Data Processing. Diagnostic results are provided as final outcomes and will be further verified from the clinician.
How many people have got tested so far?
We have a total of 500 data from AD and MCI patients and 70 Parkinson patients’ data so far. We have 600 data on healthy old people and 800 data on healthy young people as control subjects.
What were the main challenges in building such a kind of data? How is it different from other platforms used for detecting the disease?
The major big data challenges in AD research are:
• Large data size: A major challenge of big data research in AD is to collect, store and standardize the large size of diversified and complex heterogeneous data from distributed sources for further processing and to analyze them at a high velocity. The captured distributed data from different data sources require common and standardized data acquisition protocols, data quality check, data nomenclature, and data sharing standards for further processing.
• Feature extraction: High dimensionality is a common characteristic of big data, especially when using multi-modalities. Feature extraction is used to reduce the dimensionality of data, extracting information that is useful for classification. To date, limited literature is available on extracting features from multiple modalities. Feature selection for the reduction of dimensionality can be achieved using principal component analysis and other similar techniques.
• Classification: Selecting the classifiers for specific modality is also a challenging task. Hence, validation for a proper benchmark classifier is essential.
• Noise and missing values: Sometimes, MRI images, and MRS signals are noisy or contain artifacts. Quality checks should be performed to identify, evaluate, and discard the data from the analysis pipeline. Also, neuropsychological data may contain some missing values. Inclusion of noisy data and missing values may lead to inaccurate models or may lead to overfitting.
• Security: Another challenge at a global level for AD research exists for data sharing and security. Data sharing standards should be strictly followed at every level.
The proposed novel scheme is a first step toward observation of a new research direction by combining the anatomical, metabolic and cognitive changes, which can provide better understanding of the early onset and progression of AD.
What is the main nutrient whose deficiency in the brain can cause the disease? What should one do prevent a memory loss?
There is no single omnipotent cerebrum food that can guarantee a sharp mind as you age. Researchers are studying the role of various nutrients that play a major role in brain functioning. Nutritionists emphasize that the most important strategy is to follow a healthy diet and healthy lifestyle.
The major nutrients required for brain functioning are synthesised de novo by organisms. However, studies have revealed that some dietary nutrients like long-chain omega 3 fatty acids, magnesium, calcium, fibre, vitamins B1, B9, B12, D and E can boost brain health.
At our lab, we have studied the role of neurochemical-like antioxidant glutathione (GSH) levels using MRS technique. We observed variations of GSH levels in the hippocampus to understand how brain dysfunction progresses, by contrasting normal brains to those with MCI and late onset stage AD. Our findings demonstrated significant GSH depletion was linked with a decline in cognitive function.
Can stress lead to Alzheimer’s? What are the early symptoms of the disease?Stress can be one of the factors. However, the major cause of the disease is still unknown. Typical symptoms of AD are a decline in cognitive function (memory, thinking and learning) and difficulty performing everyday activities. Unfortunately, current medical treatments only provide temporary symptomatic relief.
Even though the disease was discovered 113 years ago by Dr. Alois Alzheimer, the cause of AD is yet to be determined. Alzheimer’s is a common cause of dementia in those over 65 years of age but people as young as 48 have been diagnosed with MCI. In AD brain, oxidative stress and development of development of senile plaques made of amyloid-beta peptides have been observed by various researchers.
Here at the NBRC, NINS Lab, located in the foothills of Aravalli Hill in northern India, we are working toward unravelling the mysterious molecular causes associated with AD using state-of-the-art Magnetic Resonance Spectroscopy (MRS). We have completed extensive research to define early associated variations in brain regions sensitive to the effects of AD, and in the process, have revealed the role of washed-out glutathione levels (GSH) in the transition from healthy old to MCI patients.Glutathione is a major antioxidant responsible for the protection of the brain from reactive oxygen species (ROS), which are produced when oxygen is metabolised by the brain. A clinical trial involving GSH supplementation on MCI patients is going to start soon.