Machine Learning for E/MEG-Based Identification of Alzheimer's Disease

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

The combination of machine learning (ML) techniques and neuromarkers/biomarkers for improved prognosis of Alzheimer’s diseases (AD) and mild cognitive impairment (MCI) has received increasing attentions in the community. The first part of this chapter is devoted to reviewing the recently emerged ML algorithms for dementia diagnosis, based on electroencephalography (EEG) and magnetoencephalography (MEG) modalities. In particular, the ML approaches are systematically categorized by the types of neuromarkers employed. The second part of the chapter is dedicated to a case study based investigation, to highlight the differences between these two modalities in the well-recognized resting status data collection scenario. A number of the most recent reports on MCI/AD detections during resting state using EEG/MEG are documented to show the up-to-date performance. It is noticed that the MEG modality may be particularly effective for MCI detection, a high classification accuracy of more than 98% was reported recently; whereas the EEG seems to be performing well in classifying AD and healthy subjects, which also reached around 98% of the accuracy. A number of influential factors have also been raised and suggested for careful considerations while evaluating the ML-based diagnosis systems in the real-world scenarios.
Original languageEnglish
Title of host publicationMachine Learning in Medicine
EditorsAyman El-Baz, Jasjit Suri
Place of PublicationBoca Raton
PublisherTaylor & Francis Group
Chapter8
Number of pages14
Edition1st
ISBN (Electronic)9781315101323
DOIs
Publication statusPublished - 4 Aug 2021

Keywords

  • Alzheimer's disease,
  • artificial intelligence,
  • machine learning,
  • magnetoencephalograph,,
  • neuromarkers,
  • data analytics

Fingerprint

Dive into the research topics of 'Machine Learning for E/MEG-Based Identification of Alzheimer's Disease'. Together they form a unique fingerprint.

Cite this