• Users Online: 240
  • Print this page
  • Email this page
REVIEW ARTICLE
Year : 2022  |  Volume : 1  |  Issue : 2  |  Page : 105-114

Current Understanding of Alzheimer's Disease on Biomarkers, Magnetic Resonance Imaging Modalities, and Diagnosis, Prevention, and Treatment Approach


1 Department of Computer Engineering, Government Engineering College, Rajkot; Department of Electronics and Communication, G. H. Patel College of Engineering and Technology, Anand, Gujarat, India
2 Department of Electronics and Communication, G. H. Patel College of Engineering and Technology, Anand, Gujarat, India

Correspondence Address:
Prof. Chintan Revashnakar Varnagar
Computer Engineering Department, Government Engineering College Rajkot, Gujarat
India
Login to access the Email id

Source of Support: None, Conflict of Interest: None


DOI: 10.4103/jpdtsm.jpdtsm_32_22

Rights and Permissions

Alzheimer's disease (AD), a neurodegenerative disorder in which Activities of Daily Living (ADL) are hampered and steep decline in gross cognitive function is observed, in the early stage of life. AD is characterized by progressive loss and damage to the structure and/or function of neuronal cell, resulting in death of neurons, however, etiology and pathophysiology of the disease are not known in its entirety. The purpose of this article is to understand, analyze, evaluate, and synthesize information in order to provide conclusive, decisive, and actionable information on (1) microscopic features and known etiology, pathophysiology, genes involved, and protein misfolding observed in AD; (2) selection and use of prominent magnetic resonance imaging (MRI) modalities and allied biomarkers to detect and diagnose AD by application of AI techniques; (3) role of preventive intervention (diet and lifestyle) in reducing risk of developing AD, to act on modifiable and correctable risk factors of AD, to manage AD and treatment strategies of AD through the use of pharmacology and therapeutic drugs. Deep learning-based techniques have proven capabilities to learn features automatically to discriminate class effectively. We proposed a method that incorporates features (biomarkers) derived from the structural MRI modality, clinical assessment tools, and personal and demographic quantifiable parameters into a convolution neural network. and further boosted the ensemble-based learning algorithm to improve prediction accuracy. An ensemble-based learning algorithm is then used to integrate weights to improve prediction accuracy.


[FULL TEXT] [PDF]*
Print this article     Email this article
 Next article
 Previous article
 Table of Contents

 Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
 Related articles
 Citation Manager
 Access Statistics
 Reader Comments
 Email Alert *
 Add to My List *
 * Requires registration (Free)
 

 Article Access Statistics
    Viewed76    
    Printed10    
    Emailed0    
    PDF Downloaded7    
    Comments [Add]    

Recommend this journal