Computer avatars play a part in dementia detection

September 13, 2018, Osaka University
Figure 1. Human-Avatar Dialogue System. Figure 1. Human-Avatar Dialogue System: (a)Introduction “What’s your name?”(b) Gaze measurement(c) Reading test(d) Fixed question “What’s the date today?”(e) Random question “How is your appetite?”(f) Story recall test “Please memorize the story I'm going to read.” Credit: Osaka University

Diagnosis of dementia is made via cognitive function tests such as the Mini-Mental State Examination (MMSE) and medical imaging systems at hospitals, a fairly large system for the purpose. As the population ages, an increasing number of people are developing dementia. Thus, easy-to-use dementia detection tests are sought after. In previous studies, diagnoses were made mainly using neuropsychological questions, so habituation to the same questions lowered performance in detecting dementia.

A joint group of researchers from Osaka University and Nara Institute of Science and Technology demonstrated that it was possible to detect from conversations in human-agent interaction. This technique has been realized through machine-learning: a machine learns characteristics of sounds of elderly people who answered easy questions from avatars on a .

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 , a computer came to able to distinguish individuals with dementia from healthy controls at a rate of 90 percent in 6 questions (2-3 minutes per question).

The team prepared fixed questions based on and random questions not based on specific tests, recording interactive data of spoken dialogues with avatars from 12 participants (individuals diagnosed with dementia by a psychiatrist according to the diagnosis criteria Diagnostic and Statistical Manual of Mental Disorders (DSM)-IV) and 12 healthy controls. They extracted speech, language, and image features from the recorded data, creating a model for detecting dementia and enabling a computer to learn for itself to detect dementia.

As a result, the computer was able to distinguish between healthy controls and individuals with dementia with an accuracy of 92%. It was found that dementia could be distinguished with high accuracy by combining 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.

Senior author Takashi Kudo says, "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. It will encourage them to seek medical help, leading to early diagnosis."

Explore further: VAT score improves predictive value of MMSE for dementia

More information: Hiroki Tanaka et al. Detecting Dementia Through Interactive Computer Avatars, IEEE Journal of Translational Engineering in Health and Medicine (2017). DOI: 10.1109/JTEHM.2017.2752152

Related Stories

VAT score improves predictive value of MMSE for dementia

August 17, 2018
(HealthDay)—Administering the Visual Association Test (VAT) improves the predictive value of the Mini-Mental State Examination (MMSE) score for dementia, according to a study published in a recent issue of the Annals of ...

Dementia could be detected via routinely collected data, new research shows

July 18, 2018
Improving dementia care through increased and timely diagnosis is an NHS priority, yet around half of those living with dementia live with the condition unaware.

Dementia increases the risk of 30-day readmission to the hospital after discharge

February 23, 2018
About 25 percent of older adults admitted to hospitals have dementia and are at increased risk for serious problems like in-hospital falls and delirium (the medical term for an abrupt, rapid change in mental function). As ...

Lupus linked with increased risk of dementia

November 8, 2017
A new International Journal of Geriatric Psychiatry study indicates that the risk of dementia may be elevated in individuals with systemic lupus erythematosus (SLE), an autoimmune disease affecting a range of systems including ...

TBI is associated with increased dementia risk for decades after injury

January 30, 2018
Traumatic brain injuries increase the risk of a dementia diagnosis for more than 30 years after a trauma, though the risk of dementia decreases over time, according to a new study published this week in PLOS Medicine by Anna ...

Age, marital status, BMI and sleep associated with risk for dementia

May 8, 2018
Could your age, marital status, BMI (body mass index) and amount of sleep impact your risk for dementia?

Recommended for you

Study clarifies ApoE4's role in dementia

September 20, 2018
ApoE4, a protein linked to both Alzheimer's disease and a form of dementia caused by damage of blood vessels in the brain, increases the risk of cognitive impairment by reducing the number and responsiveness of blood vessels ...

Machine learning IDs markers to help predict Alzheimer's

September 19, 2018
Nearly 50 million people worldwide have Alzheimer's disease or another form of dementia. These irreversible brain disorders slowly cause memory loss and destroy thinking skills, eventually to such an extent that self-care ...

Discovery could explain failed clinical trials for Alzheimer's, and provide a solution

September 19, 2018
Researchers at King's College London have discovered a vicious feedback loop underlying brain degeneration in Alzheimer's disease which may explain why so many drug trials have failed. The study also identifies a clinically ...

Air pollution may be linked to heightened dementia risk

September 18, 2018
Air pollution may be linked to a heightened risk of developing dementia, finds a London-based observational study, published in the online journal BMJ Open. The associations found couldn't be explained by factors known to ...

A new approach for finding Alzheimer's treatments

September 11, 2018
Considering what little progress has been made finding drugs to treat Alzheimer's disease, Maikel Rheinstädter decided to come at the problem from a totally different angle—perhaps the solution lay not with the peptide ...

Study prevents cognitive decline in older blacks with memory loss

September 10, 2018
With nearly twice the rate of dementia as whites, blacks are at a higher risk for developing diseases like Alzheimer's, but there has been little research on how to reduce this racial health disparity. A new study in black ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.