Validity of the quantitative EEG statistical pattern recognition method in diagnosing Alzheimer's disease

Dement Geriatr Cogn Disord. 2011;31(3):195-201. doi: 10.1159/000324878. Epub 2011 Mar 24.

Abstract

Aims: To evaluate the use of quantitative EEG (qEEG) statistical pattern recognition in diagnosing Alzheimer's disease (AD).

Methods: qEEG was performed on 104 patients referred to a memory clinic. The qEEG results were compared to the clinical diagnosis made without access to the EEG results.

Results: Of 30 patients with a clinical diagnosis of AD, 22 were test positive. Of the 74 patients without AD, 34 were test negative. The qEEG result was found to correlate with atrophy of the medial temporal lobe demonstrated on cerebral MRI (p = 0.002) and with scores on neuropsychological tests.

Conclusion: The qEEG was poor at diagnosing AD, as it produced many false-positive results.

Publication types

  • Research Support, Non-U.S. Gov't
  • Validation Study

MeSH terms

  • Aged
  • Alzheimer Disease / diagnosis*
  • Alzheimer Disease / physiopathology
  • Databases, Factual
  • Dementia / classification
  • Dementia / diagnosis*
  • Dementia / physiopathology
  • Diagnosis, Computer-Assisted / methods*
  • Diagnosis, Computer-Assisted / standards
  • Electroencephalography / methods*
  • Female
  • Humans
  • Male
  • Middle Aged
  • Pattern Recognition, Automated / methods*
  • ROC Curve
  • Sensitivity and Specificity