Alzheimer’s Disease Dementia Classification Through Residual Network and QEEG Image representations

Abstract

AbstractBackgroundOur everyday actions and decisions involve a complex coordination of various cognitive functions. Severe deterioration of such functions, commonly referred to as dementia, adversely affects quality of our lives. However, through early screening of the disease at its pre‐clinical stage and appropriate treatment, they can be reverted. Current diagnostic criteria for dementia utilize questionnaire‐based cognitive function assessments, such as the mini‐mental state examination. However, it is statistically less robust, where further tests such as positron emission tomography are required for accurate diagnosis. This is laborious, expensive and expose patients to harmful radiation. Therefore, we propose a quantitative electroencephalography (QEEG) based approach that distinguishes Alzheimer’s disease dementia (ADD) from a non‐ADD group that include mild cognitive impairment and subjective cognitive decline data.Method19 channel EEG data employed in the present study were clinically acquired from Chung‐Ang university hospital, in eyes‐closed resting state. Artefacts were eliminated through independent component analysis and bad epoch rejection. Through spectral analysis, the powers of a frequency spectrum (1‐45Hz) were computed with 0.25Hz resolution. Henceforth, the Z‐score of each value were calculated through iMediSync’s age‐ and sex‐differentiated normative database and were mapped into a rectangular arrangement in accordance with channel locations on the scalp. The rearranged Z‐score matrices were visualized, clearly exhibiting both spectral and spatial information. Gamma spectrum (30‐45Hz) was excluded due to its vulnerability to contaminations induced by external noises and muscle movements. The final dataset (N = 732; 137 ADD, 595 non‐ADD) was established, where the 75% of non‐ADD were first excluded as test data due to data imbalance. The remaining data were split into 2 to 8 ratio for testing (N = 503; 27 ADD; 476 non‐ADD) and training (N = 229; 110 ADD; 119 non‐ADD).ResultThe final 18‐layer Residual network model showed test accuracy at 88.5% with ADD sensitivity at 88.9% and specificity at 88.4%. Explainable artificial intelligence algorithm was utilized for the inference and verification of classification criteria.ConclusionThe outstanding classification results of the established model upholds QEEG utility in the distinguishment of dementia from its pre‐clinical stages. Continuous refinement will bolster its potential in the diagnosis several other neurological diseases.