Abstract
With the number of dementia patients worldwide projected to approach 115 million by 2050, the development of simple early diagnosis tools to prepare for the rapid increase in the number of dementia patients is expected. Therefore, we are developing a dementia screening tool using a character input type BCI (Brain-Computer Interface). Our research group has already observed cognitive decline from an increase in Spelling-Error Distance Value (SEDV), but we did not find a statistically significant difference between the group with cognitively unimpaired participants (CU group) and the group with mild cognitive impairment (MCI group), which is necessary for early diagnosis. In this study, we focused on Tsallis entropy and coherence to identify EEG features that explain CU group, MCI group, and Alzheimer's disease patients (AD group). The data from 55 participants were analyzed. The MMSE, a measure of neuropsychological testing, was 28.20, 27.38, and 22.04 for the CU, MCI, and AD groups. The results showed that Tsallis entropy decreased and coherence increased with cognitive decline. Significant differences (p<0.1 and p<0.05) were confirmed in multiple comparisons between the CU and MCI groups for both indices, indicating that progression from CU to MCI was predictable.
