Predicting Progression from Mild Cognitive Impairment to Alzheimer’s Disease Using Deep Learning Approach

Authors

  • Devansh Gupta B.E. Student, Department of Information Science and Engineering, Dayananda Sagar Academy of Technology, Management, Bengaluru, India
  • Prajwal Poojary B.E. Student, Department of Information Science and Engineering, Dayananda Sagar Academy of Technology, Management, Bengaluru, India
  • Vikash Kumar B.E. Student, Department of Information Science and Engineering, Dayananda Sagar Academy of Technology, Management, Bengaluru, India
  • Dhruva Kumar B.E. Student, Department of Information Science and Engineering, Dayananda Sagar Academy of Technology, Management, Bengaluru, India
  • M. Kusuma Professor, Department of Information Science and Engineering, Dayananda Sagar Academy of Technology, Management, Bengaluru, India

Keywords:

medium mental disorders, autoregressive, biomarker

Abstract

Mild Cognitive Impairment is the first stage of Alzheimer's disease (AD). For effective treatment of AD, it is important to identify MCI patients who are at high risk of developing AD over time. In this study, automated modeling of many Alzheimer's predictions was made to capture their evolution over time. Models are trained using three different longitudinal data systems. These models are then used to measure biomarker readings for each experimental study. Finally, a standard SVM category is used to diagnose MCI patients at risk of developing AD in the coming years. The proposed models are fully tested for their predictive capabilities using both cognitive points and MRI-based measures. In the 5 separate split verification settings, our proposed method yielded the highest AUC 88.93% (Accuracy = 84.29%) and 88.13% (Accuracy = 83.26%) 1 year and 2 years prior to conversion prediction of AD, respectively, in very broad areas. use ADNI data. Significant conclusions of this study are: 1. Clinical changes in MRI- based interventions can be better predicted than cognitive points, 2. Multiple predictive models bring better predictability of transformation than single biomarker models, of the previous term 4. Neuropsychology schools alone can provide better predictability of long-term change.

Downloads

Download data is not yet available.

Downloads

Published

26-06-2022

How to Cite

[1]
D. Gupta, P. Poojary, V. Kumar, D. Kumar, and M. Kusuma, “Predicting Progression from Mild Cognitive Impairment to Alzheimer’s Disease Using Deep Learning Approach”, IJRESM, vol. 5, no. 6, pp. 241–243, Jun. 2022.

Issue

Section

Articles

Most read articles by the same author(s)