Generate summary for article using Artificial Intelligence tools
| Id | 590 | |
| Author | Tanaka H., Adachi H., Ukita N., Ikeda M., Kazui H., Kudo T., Nakamura S. | |
| Title | Detecting Dementia Through Interactive Computer Avatars | |
| Reference | Tanaka H., Adachi H., Ukita N., Ikeda M., Kazui H., Kudo T., Nakamura S.; Detecting Dementia Through Interactive Computer Avatars ;IEEE Journal of Translational Engineering in Health and Medicine vol:5 issue: page: |
|
| Link to article | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85030643595&doi=10.1109%2fJTEHM.2017.2752152&partnerID=40&md5=8a0585c2546f38970b76f1173c0a2375 |
|
| Abstract | This paper proposes a new approach to automatically detect dementia. Even though some works have detected dementia from speech and language attributes, most have applied detection using picture descriptions, narratives, and cognitive tasks. In this paper, we propose a new computer avatar with spoken dialog functionalities that produces spoken queries based on the mini-mental state examination, the Wechsler memory scale-revised, and other related neuropsychological questions. We recorded the interactive data of spoken dialogues from 29 participants (14 dementia and 15 healthy controls) and extracted various audiovisual features. We tried to predict dementia using audiovisual features and two machine learning algorithms (support vector machines and logistic regression). Here, we show that the support vector machines outperformed logistic regression, and by using the extracted features they classified the participants into two groups with 0.93 detection performance, as measured by the areas under the receiver operating characteristic curve. We also newly identified some contributing features, e.g., gap before speaking, the variations of fundamental frequency, voice quality, and the ratio of smiling. We concluded that our system has the potential to detect dementia through spoken dialog systems and that the system can assist health care workers. In addition, these findings could help medical personnel detect signs of dementia. © 2013 IEEE. |
We recorded the interactive data of spoken dialogues from 29 participants and extracted various audiovisual features. Here, we show that the support vector machines outperformed logistic regression, and by using the extracted features they classified the participants into two groups with 0,93 detection performance, as measured by the areas under the receiver operating characteristic curve. For the skills of comprehending communicative emotions deteriorating emotion-recognition ability rather than deterioration of general cognition inuences the indifferent and awkward interpersonal behaviors of people with Alzheimers disease and frontotemporal dementia . Four were removed from the experiment because two in the dementia group had not been diagnosed with dementia yet and two in the healthy controls obtained MMSE scores of and which are below the cut-off scored The dementia group participants were diagnosed as having mild cognitive impairment or dementia by certied psychiatrists at the Osaka University Hospital. In this experiment we used selected audiovisual features as input of the classiers which were trained to predict the dementia group and healthy control labels with default parameters.
MESOC has received funding
from Horizon 2020 - the EU Framework Programme
for Research and Innovation (2014-2020) -
under Grant Agreement n°870935.
We take your privacy seriously and WE DO NOT process any personal data or any information that reveals personal identity or information that can be linked to such information to identify directly or indirectly.
2021 © CD