Multiresolution analysis for early diagnosis of Alzheimer's disease

Genevieve Jacques, Jennifer L. Frymiare, John Kounios, Christopher Clark, Robi Polikar

Research output: Contribution to journalConference articlepeer-review

17 Scopus citations

Abstract

Early diagnosis of Alzheimer's disease is a major concern due to large portions of the elderly population it affects and the lack of a standard and effective diagnosis procedure that is available to community healthcare providers. Several studies have been performed using wavelets or other signal processing methods to analyze EEG signals in an attempt to find a biomarker for Alzheimer's disease, which showed varying degrees of success. To date, in part due to lack of a large study cohort, the results of these studies remain largely inconclusive. In this paper, we describe a new effort using multiresolution wavelet analysis on event related potentials of the EEG to investigate whether such a link can be established. Several factors sets this study apart from similar prior efforts: We use a larger cohort, compare different mother wavelets, rather then using one generic wavelet, and most importantly, we specifically target early diagnosis of the disease. Our multi-year effort will include a total of 80 patients, whose ERPs will be analyzed with several different wavelets and automated classifiers. We present some preliminary, yet very promising, results on analysis of EEGs of the first 28 patients analyzed thus far using two types of wavelets.

Original languageEnglish (US)
Pages (from-to)251-254
Number of pages4
JournalAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume26 I
StatePublished - Dec 1 2004
EventConference Proceedings - 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2004 - San Francisco, CA, United States
Duration: Sep 1 2004Sep 5 2004

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint

Dive into the research topics of 'Multiresolution analysis for early diagnosis of Alzheimer's disease'. Together they form a unique fingerprint.

Cite this