Remember meForgot password?
    Log in with Twitter

article imageArtificial intelligence used to detect early signs of dementia

By Tim Sandle     Sep 23, 2018 in Science
Researchers have developed an artificial intelligence test which can detect the early signs of dementia. The aim is to use the test in the clinical setting to help to detect cases early so that appropriate treatment can be given.
The new artificial intelligence computer test asks a patient a series of questions via the use of an interactive on-screen avatar. The system reviews the answers and then differentiates between people based on an interpretation of any suggested cognitive problems. The assessment was for clinical dementia rather than the type of forgetfulness that is not a natural aspect of ageing.
The computer tests have been designed by scientists based at from Osaka University and Nara Institute of Science and Technology. The aim of the research was to develop an alternative to medical imaging, which is the conventional method of picking up the disease. The downside of medical imaging is that the disease needs to have progressed and the time taken for this is relatively lengthy, an issue in societies where cases of dementia are rising.
The Japanese devised artificial intelligence, PharmaPhorum reports, will ask some fixed questions and also different questions to different patients and also pitch different questions to the same patient, in cases where the patient is making successive visits. This latter function is designed to reduce the chances of someone becoming too familiar with the questions and second guessing them. The questions are based on the internationally recognised criteria contained in the Diagnostic and Statistical Manual of Mental Disorders.
For example:
(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.
The types of information assessed by the artificial intelligence includes delays in responses, intonation, the percentage of verbs and nouns used, voice articulation and recall. Also looked at is the ‘gaze’ of the patient, in terms of how attentive they are. These algorithms were developed based on an assessment of features of speech, language, and faces taken from recorded dialogues with elderly participants. Some of the participants had dementia, at various stages, and some did not.
In trials, the artificial intelligence has successfully learnt how to differentiate for dementia without need to be programmed, at a rate of 90 percent success based on asking just six questions. The typical time taken for the assessment was just two to three minutes.
Commenting on this, lead researcher Takashi Kudo stated, as quoted by European Pharmaceutical review: “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 conversations with computer avatars at home on a daily basis.”
The test has been reported to the journal IEEE Journal of Translational Engineering in Health and Medicine. The research is titled “Detecting Dementia through Interactive Computer Avatars.”
More about Artificial intelligence, Dementia, Neuroscience
More news from