Never miss a great news story!
Get instant notifications from Economic Times
AllowNot now


You can switch off notifications anytime using browser settings.

Panache

Portfolio

Loading...
Select Portfolio and Asset Combination for Display on Market Band
Select Portfolio
Select Asset Class
Show More
Download ET MARKETS APP

Get ET Markets in your own language

DOWNLOAD THE APP NOW

+91

CHOOSE LANGUAGE

ENG

  • ENG - English
  • HIN - हिन्दी
  • GUJ - ગુજરાતી
  • MAR - मराठी
  • BEN - বাংলা
  • KAN - ಕನ್ನಡ
  • ORI - ଓଡିଆ
  • TEL - తెలుగు
  • TAM - தமிழ்
Drag according to your convenience
ET NOW RADIO
ET NOW
TIMES NOW

This machine-learning technique can detect dementia with 90 per cent accuracy

IANS|
Updated: Sep 14, 2018, 06.28 PM IST
0Comments
Dementia
TOKYO: A team of Japanese researchers have developed a novel machine-learning technique that can with 90 per cent accuracy detect dementia from conversations between humans and avatars on a computer.

In the technique, a machine learns characteristics of sounds of elderly people who answered easy questions from avatars on a computer.

By combining the features of dementia, such as delay in response to questions from avatars depending on the content of questions, intonation, articulation rate of the voice, and the percentage of nouns and verbs in utterance, the computer could distinguish the condition with 90 per cent accuracy, the researcher from Osaka University and Nara Institute of Science and Technology said.

Stress Patch, Solar Supercapacitor & More: Tech For Well-Being Is The Next Big Thing

of 7
Next
Prev
Play Slideshow

The World Of Wearables

9 Aug, 2018
From a stress-detecting patch to AI that mimics the human brain, the technology of the future is geared towards health solutions.
Next


"If this technology is further developed, it will become possible to know whether or not an elderly individual is in the early stages of dementia through conversation with computer avatars at home on a daily basis," said Takashi Kudo from Osaka.

"It will encourage them to seek medical help, leading to early diagnosis,"Kudo added.

The study was published in the IEEE Journal of Translational Engineering in Health and Medicine.

The researchers proposed machine learning algorithms for detecting signs of dementia in its early stages, developing a dementia detection system using interactive computer avatars.

They created a model for machine learning based on features of speech, language, and faces from recorded dialogues with elderly participants.

Through machine learning, a computer was able to distinguish individuals with dementia from healthy controls at a rate of 90 per cent in six questions (two-three minutes per question), the findings showed.


0Comments
Want stories like this in your inbox? Sign up for the daily ET Panache newsletter.

You can also follow us on Facebook, Twitter and LinkedIn.

Also Read

Here's why dementia symptoms peak in winter and spring

Is abstinence to alcohol bad? Teetotallers more prone to dementia

Good news: Now, dementia can be predicted 10 years in advance

Suffered a stroke in the past? You are 70% more likely to get dementia

Comments
Add Your Comments
Commenting feature is disabled in your country/region.

Loading
Please wait...