A new machine learning model to isolate the effects of age in predicting dementia

July 27, 2018 by Ingrid Fadelli, Medical Xpress feature
Expository histogram plots for the ages of people in the impaired and control groups. Credit: Frank Rudzicz et al.

Researchers at Toronto-based company WinterLight Labs have recently devised a machine learning method of predicting dementia that prioritizes particular variables when analyzing data, which could help to isolate the effects of potentially confounding factors.

Alzheimer's disease and other types of are a major worldwide challenge, leading to the death of one out of three seniors in the U.S. alone. While the causes of these diseases have not yet been fully grasped, they can have detrimental effects on speech, memory, orientation and other important cognitive abilities.

WinterLight Labs is developing AI-based tools that could help detect and monitor Alzheimer's disease, aphasia, dementia, and other conditions that affect humans' cognitive abilities. The company has achieved very promising results, developing tools that can classify subtypes of aphasia with up to 100 percent accuracy and dementia with over 82 percent accuracy.

Their machine learning algorithms predict cognitive impairments and their severity by analyzing human speech and identifying distinctive patterns that are generally associated with dementia or other disorders. For instance, individuals affected by Alzheimer's tend to describe things more simply, using more pronouns than nouns, and taking longer pauses between words. However, detectable changes in speech or cognition are not always due to dementia or other cognitive impairments; they can also be a mere result of aging.

"We have been working with automatic, language-based assessment of dementia using artificial intelligence for several years," said Frank Rudzicz, president of WinterLight Labs, associate professor at the University of Toronto, and faculty member of the Vector Institute, in an interview with Tech Xplore. "In this time, it has been increasingly important for us to identify changes to cognition that happen relatively early, so it became important to account for the effect of age on language, since age has a large effect on language generally."

In their recent study, Rudzicz and his colleagues used fair representation learning to devise a method that could help to prioritize certain factors over others when predicting dementia. Their method uses neural network classifiers that learn low-dimensional representations reflecting the impacts of dementia, which do not contain age-related information.

"We generally use several deep neural networks (including auto-encoders), although we introduce a new metric for measuring fairness and experiment with four models, including one motivated by categorical generative adversarial networks," Rudzicz explained.

The researchers tested their classifiers on two publicly available datasets, DementiaBank and Famous People, which include voice recordings and transcripts of people with dementia and others with no cognitive impairments. They found that their classifiers performed better than baseline deep neural network classifiers, disentangling results from age while compromising as little accuracy as 2.56 percent on DementiaBank and 2.25 percent on Famous People.

"Although we usually use age as an important covariate for predicting dementia, this paper shows that we can separate out those effects when predicting dementia," Rudzicz said. "This approach generalizes to other situations where multiple covariates may work together to give us our observed data, but where we're primarily interested in one of them."

In other words, despite the focus on age within the context of dementia prediction, the models developed by Rudzicz and his colleagues could be applied to other cases in which researchers wish to isolate confounding variables.

"Part of the motivations behind our study come from recent discussions that confounding variables really confuse decision making (both of people and of AI), so we wanted to systematically and automatically get rid of their impacts," Zining Zhu, software engineer at WinterLight Labs told TechXplore. "This paper is about applying fair learning to isolating age effects, but it could be useful to remove effects of other factors as well, especially those lying in the causal chains between 'what we see' and 'what really happens'."

The researchers will now continue to explore ways of accurately detecting cognitive diseases, isolating the effects of age or other confounding variables.

"We still have a lot of work to do on disentangling the effects of age from the effects of pathological cognitive change, and this will likely continue," Rudzicz said. "We are interested in more interventional approaches, for example, and deeper integration with the healthcare system."

Explore further: Scientists discover new computerized linguistic approach to detect Alzheimer's disease

More information: Isolating effects of age with fair representation learning when assessing dementia, arXiv:180/.07217v1 [csLG]. arxiv.org/abs/1807.07217

Facts and Figures, Alzheimer's Association. www.alz.org/alzheimers-dementia/facts-figures

Related Stories

Scientists discover new computerized linguistic approach to detect Alzheimer's disease

December 8, 2015
Researchers have discovered how to diagnose Alzheimer's disease with more than 82 per cent accuracy by evaluating the interplay between four linguistic factors; and developing automated technology to detect these impairments.

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.

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?

Review links albuminuria to cognitive impairment, dementia

February 13, 2017
(HealthDay)—Albuminuria is associated with cognitive impairment, dementia, and cognitive decline, according to a review published online Feb. 2 in the Journal of the American Geriatrics Society.

Anti-epileptic drugs increase risk of Alzheimer's and dementia

April 9, 2018
The use of anti-epileptic drugs is associated with an increased risk of Alzheimer's disease and dementia, according to a new study from the University of Eastern Finland and the German Center for Neurodegenerative Diseases, ...

Women's wellness: Hormone therapy and Alzheimer's disease

November 9, 2017
Introducing hormone treatment for women in early stages of menopause might help decrease their risk of dementia or Alzheimer's disease.

Recommended for you

Amyloid pathology transmission in lab mice and historic medical treatments

December 13, 2018
A UCL-led study has confirmed that some vials of a hormone used in discontinued medical treatments contained seeds of a protein implicated in Alzheimer's disease, and are able to seed amyloid pathology in mice.

Study links slowed brainwaves to early signs of dementia

December 13, 2018
To turn back the clock on Alzheimer's disease, many researchers are seeking ways to effectively diagnose the neurodegenerative disorder earlier.

New discoveries predict ability to forecast dementia from single molecule

December 11, 2018
Scientists who recently identified the molecular start of Alzheimer's disease have used that finding to determine that it should be possible to forecast which type of dementia will develop over time—a form of personalized ...

Researchers classify Alzheimer's patients in six subgroups

December 5, 2018
Researchers studying Alzheimer's disease have created an approach to classify patients with Alzheimer's disease, a finding that may open the door for personalized treatments.

Neuroscientists pinpoint genes tied to dementia

December 3, 2018
A UCLA-led research team has identified genetic processes involved in the neurodegeneration that occurs in dementia—an important step on the path toward developing therapies that could slow or halt the course of the disease. ...

Detecting signs of neurodegeneration earlier and more accurately

November 30, 2018
Signs of neurodegenerative diseases, appearing years before the emergence of clinical manifestations, can be detected during the examination of medical samples by means of fluorescence microscopy by using new sensitive and ...


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.