Using artificial intelligence, scientists have discovered a way to detect a person’s risk of developing Alzheimer’s in the next 6 years; The idea is to launch an app with the function
In the United States, researchers at Boston University (BU) have developed a new way to detect the early signs of Alzheimer’s disease based on the way a person speaks. The possible diagnosis of this type of dementia is made with a Artificial intelligence (AI) algorithm..
- Click and follow Canaltech on WhatsApp
- Brain Map Generated With AI To Uncover Origin Of Alzheimer’s And Autism
The instrument Alzheimer’s Diagnosisin the validation phase, does not analyze obvious characteristics of speech, such as speed. The focus is on the content and the way a person speaks, including the words chosen and how they are used (structured) in sentences.
Published in the magazine Alzheimer’s and DementiaThe study reveals that the AI achieved a 78.5% accuracy rate in identifying a person’s risk of developing Alzheimer’s within a six-year window.
However, the tool has only been tested on people who already have mild cognitive impairment (MCI), which is likely to worsen or remain stable. This means that people without guidance are unable to use AI.
Signs of Alzheimer’s in Language
In the study, researchers relied on 166 recordings of people, between 63 and 97 years old, with mild cognitive impairment of memory. After six years of this interview, 90 developed dementia, such as Alzheimer’s, while the other 76 remained stable.
Using machine learning, US scientists trained the model to detect connections between language and disease progression in these “early” patients. Factors such as age and gender were also considered.
Then the AI tool was used to evaluate the risk of Alzheimer’s in a new group of volunteers, where the success rate was obtained. In fact, what the authors obtained is closer to a predictive score, in which individuals with higher scores run greater risks.
“You can think of the score as a probability. The probability that someone will remain stable or progress to dementia. [nos próximos anos]”, explains in a note Ioannis Paschalidis, professor of computer science and engineering at BU and author of the study.
One of the interesting points of the study is that the recordings are of low quality and full of background noise, but regardless they can help identify patients at risk.
Using Artificial Intelligence in Diagnosis
The team’s next step is to adapt this new AI tool so that it can be used through a mobile phone app, available to patients at high risk of Alzheimer’s.
“If you can predict what is going to happen, you will have more opportunities and a window of time to intervene with drugs and at least try to maintain the stability of the condition and prevent the transition to more severe forms of dementia,” Professor Paschalidis stresses.
This isn’t the first time scientists have used artificial intelligence to find ways to diagnose Alzheimer’s. Previously, Other research has examined patterns of glucose use in the brains of patients who potentially may have dementia.. The technique is also in the validation phase.
Source: Alzheimer’s and Dementia, Boston University
Trends on Canaltech:
- AstraZeneca ‘admits’ rare side effect of Covid-19 vaccine
- The 50 Funniest Google Assistant Jokes
- Sony Ends Blank CD and DVD Production, Lays Off 250 People
- Magalu’s New Lu used AI and Unreal Engine 5 to become more realistic
- How much do hybrid car batteries cost in Brazil?
Source: Terra
Rose James is a Gossipify movie and series reviewer known for her in-depth analysis and unique perspective on the latest releases. With a background in film studies, she provides engaging and informative reviews, and keeps readers up to date with industry trends and emerging talents.
