DOI: 10.1002/alz.074448 ISSN: 1552-5260

Alpha Asymmetry as biomarker for Mild Cognitive Impairment

Jaekang Shin, Sanguk Park, Taegyun Jeong, Ukeob Park, Daekeun Kim, Young Chul Youn, Do‐Young Kang, Kyung Won Park, Sangjin Kim, Hyuntae Park, Young‐Min Lee, Chang‐Sung Seo, Seung Wan Kang
  • Psychiatry and Mental health
  • Cellular and Molecular Neuroscience
  • Geriatrics and Gerontology
  • Neurology (clinical)
  • Developmental Neuroscience
  • Health Policy
  • Epidemiology



Early screening of dementia at its pre‐clinical stage is crucial, seeing as how deteriorated cognitive functions can be recovered through appropriate medicinal practices. The pre‐clinical stage, which we refer to as mild cognitive impairment (MCI) is known to affect the alpha rhythm of the brain activity. Hence, our study aims to establish quantitative EEG (qEEG)‐based alpha asymmetry biomarker that aids the diagnoses of MCI.


The qEEG dataset were composed of age‐ and sex‐ matched subjects (N = 634, 317 healthy control (HC), 317 MCI), acquired in accordance with the 10‐20 system and under resting state with their eyes being closed. Subjects were recruited by Chung‐Ang University (153 HC, 111 MCI), iMediSync(164 HC, 76 MCI), Dong‐a Medical Center(84 MCI) and Pusan Medical Center(46 MCI).

The features were classified into four types: the absolute and relative region alpha power (AAP/RAP) of six regions (Prefrontal, Frontal, Temporal, Central, Parietal, Occipital); alpha power asymmetry (APA) between regions that align in anterior‐posterior and lateral planes; occipital alpha peak frequency (OPF) that analyzes peak frequencies.

In order to highlight the alpha variability, EEG signals were bandpass filtered (6.5‐12Hz). Filtered signal at each channel was categorized into slow (6.5‐8Hz), middle (8‐10Hz) and fast alpha (10‐12Hz). The mean and standard deviation of their FFT were computed through moving time window. Henceforth, the feature set were used to train machine learning algorithms. Data were split into 8(training N = 507) to 2(test N = 127) ratio. 101 subjects were randomly selected and used as validation set. The algorithm that exhibited the best classification performance were determined through 5‐fold cross validation (CV) results.


Support vector machine (SVM) showed the best 5‐fold CV results – 84.61% average accuracy, 74.02% sensitivity, 95.25% specificity, 94.15% precision and F1‐Score of 0.8273. The RAP decreased for all regions and OPF were slower in MCI group when compared to HC. APA patterns of the right intra‐hemisphere exhibited most significant differences.


This study illustrates the potential of APA as a biomarker for MCI. Current applications of APA are confined to emotional‐related studies, such as depressive disorder. The reported cases of MCI‐associated depression also uphold the validity of APA as a biomarker for MCI.

More from our Archive