Related Experiment Video
Updated: Jan 1, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Quantitative metabolic biomarker analysis of mild cognitive impairment in eastern U.P. and Bihar population
Vineeta Singh1, Vijaya Nath Mishra1, Guru Dayal Prajapati2
1Department of Neurology, Institute of Medical Sciences, Banaras Hindu University, Varanasi, 221005, UP, India.
Abstract:
Mild cognitive impairment (MCI) is a transition phase between healthy individuals and Alzheimer's disease (AD). Therefore, diagnosis of MCI at early stage will help to delay or prevent its progression to disease. In the present study, we aim to identify the metabolic biomarkers, which can help in the diagnosis of MCI. We have screened 2000 elderly individuals from north India, out of which 200 were identified as MCI. We continued our study on 10 MCI individuals who regularly participated in the follow-up. The age and gender matched 10 healthy individuals were taken as control. These control and MCI individuals were subjected to neuropsychological examination such as Hindi mental state examination (HMSE) and Montreal cognitive assessment (MOCA) followed by 1H Nuclear Magnetic Resonance (NMR) analysis. Remarkable changes were noted between control and MCI individuals at metabolic level. In silico study showed the involvement of eight metabolites in MCI. We found higher level of lactate, N-acetyl aspartate, histidine and lower level of formate, choline, alanine, creatinine and glucose in blood plasma of MCI individuals compared to control. Further, In silico study showed that choline might be directly associated with MCI or AD. Such In silico study with quantitative metabolite analysis of plasma could be used as diagnostic biomarkers for the identification of MCI.

