We characterized prion disease by comparing brain functional connectivity network (BFCN), which were constructed by 16-ch scalp-recorded electroencephalograms (EEGs). The connectivity between each pair of nodes (electrodes) were computed by synchronization likelihood (SL). The BFCN was applied to graph theory to discriminate prion disease patients from healthy elderlies and dementia groups.

We propose a non-invasive and cost-effective method to automatically detect dementia by utilizing solely speech audio data. We extract paralinguistic features for a short speech segment and use Gated Convolutional Neural Networks (GCNN) to classify it into dementia or healthy. We evaluate our method on the Pitt Corpus and on our own dataset, the PROMPT Database. Our method yields the accuracy of 73.1% on the Pitt Corpus using an average of 114 seconds of speech data. In the PROMPT Database, our method yields the accuracy of 74.7% using 4 seconds of speech data and it improves to 80.8% when we use all the patient's speech data. Furthermore, we evaluate our method on a three-class classification problem in which we included the Mild Cognitive Impairment (MCI) class and achieved the accuracy of 60.6% with 40 seconds of speech data.

Aging is progressing in our country. Cerebral disease poses a serious problem. Viewing this problem objectively, we can say that support of aging and cerebral disease patients is a useful research theme. To the present, we have done rank evaluation of cerebral disease using synthetic face picture images. This study assesses cognitive ability and expression control ability for intoxication, which is known to impair thinking, cognition, and memory ability. We also examine correspondence of intoxication to cerebral disease. Measurement of cognitive ability corresponds to observation of an internal condition; the measurement of expression control ability corresponds to observation of an external condition. In measurement of cognitive ability, we simulated early stage symptoms of vascular dementia in the second stage of BAC. Also, decreased cognitive ability occurs from the first stage of BAC on face recognition to figure and language. Moreover, face test results show significant difference between decrease in the first stage of BAC and one in the second stage of BAC. These results indicate the possibility of rank evaluation and early stage detection of vascular dementia using a face picture image. From measurement of expression control ability, we obtained the result that we can judge whether a subject has reached second stage of BAC by observing an expression's strength of smile. The second stage of BAC shows symptoms similar to those of vascular dementia. We found the possibility that smile is valid as one externally-observable index for detection of cerebral disease.

With the advent of an aging society, the incidence of Alzheimer-type dementia (hereinafter referred to as AD for convenience) has drastically increased. Compared with classic cerebrovascular dementia, AD requires different therapeutic modalities. Despite such differences, it is difficult to establish a differential diagnosis of AD and cerebrovascular dementia. In the present paper, we analyze the neuropsychological symptoms and signs associated with AD, such as visual cognitive dysfunction, with particular attention to head and eye coordination. The subjects were allowed to gaze at targets disposed 1 m away and at a visual angle of 25 and 50 in order to compare healthy volunteers and patients with senile dementias such as multi-infarct dementia (MID). As a consequence, patients with AD presented clinical manifestations not seen in patients with other senile dementias; that is, (1) an increase in stepwise eye movement, (2) anisotropy in the velocity of right-directional and left-directional eye movements, (3) a decrease in the velocity of head movements (4) incomplete gaze, and (5) decreased head share.