Researchers use artificial intelligence to help diagnose autism, study says

Researchers are proposing using artificial intelligence technology to help diagnose autism spectrum disorder.

In a latest article published in Scientific Reports, researchers from Brazil, France and Germany reportedly used magnetic resonance imaging to train a machine learning algorithm. 

The work – in which the "quantitative diagnostic method" is proposed – was based on brain imaging data for 500 people, with more than 240 that had been diagnosed with autism. 

WHAT IS ARTIFICIAL INTELLIGENCE (AI)?

Machine learning techniques were applied to the data.

"We began developing their methodology by collecting functional magnetic resonance imaging [fMRI] and electroencephalogram [EEG] data," Francisco Rodrigues, the last author of the article and a professor at the University of São Paulo’s Institute of Mathematics and Computer Science, explained in a statement. 

AS AI SHOWS UP IN DOCTORS' OFFICES, MOST PATIENTS ARE GIVING PERMISSION AS EXPERTS ADVISE CAUTION

São Paulo University on November 15, 2015, in São Paulo, Brazil. (Frédéric Soltan/Corbis via Getty Images)

"We compared maps of people with and without ASD and found that diagnosis was possible using this methodology," he added.

The machine learning algorithm was fed with the maps, and the system was able to determine which brain alterations were associated with autism with above 95% mean accuracy. 

While previous research proposes methods for diagnosing autism based on machine learning, the article notes it often uses a single statistical parameter that is not brain network organization. 

Autism is a developmental disability caused by differences in the brain. (iStock)

CALIFORNIA MAN WITH SEVERE AUTISM BEATS RUBIK'S CUBE WORLD RECORD: 'EXUBERANCE IN THEIR HEARTS'

Analyzing the fMRI data showed changes in certain brain regions associated with cognitive, emotional, learning and memory processes, and the cortical networks of autism patients showed more segregation, less distribution of information and less connectivity compared to controls.

"Until a few years ago, little was known about the alterations that lead to the symptoms of ASD. Now, however, brain alterations in ASD patients are known to be associated with certain behaviors, although anatomical research shows that the alterations are hard to see, making diagnosis of mild ASD much harder. Their study is an important step in the development of novel methodologies that can help us obtain a deeper understanding of this neurodivergence," Rodrigues said.

The Centers for Disease Control and Prevention headquarters in Atlanta, Georgia, on March 14, 2020. (Elijah Nouvelage/Bloomberg via Getty Images)

The methodology is under development and will take years to implement, according to the São Paulo Research Foundation, which supported the research.

CLICK HERE TO GET THE FOX NEWS APP

About one in 36 children has been identified with autism spectrum disorder, according to the Centers for Disease Control and Prevention. 

Diagnosing the developmental disability can be difficult because there is no medical test, like a blood test, to do so. 

Julia Musto is a reporter for Fox News and Fox Business Digital. 

How Crying Can Help You, Here Is What A Study Says

It may be good to cry out loud. (Photo: Getty Images)

They say that there's no sense in crying over spilled milk. But what do they know? Crying can get you another glass of milk if you do it loud enough. Plus, crying may serve a real physiologic purpose, according to a study published recently in Emotion, meaning the journal and not in an Emo-kind of way.

For the study, three researchers from the University of Queensland (Leah S. Sharman, Genevieve A. Dingle, and Eric J. Vanman) and one from Tilberg University (Ad J. J. M. Vingerhoets) recruited 197 female undergraduate students. They said that they choose all women rather than including men because pilot testing of sad videos had revealed that more women than men cried or at least more women revealed that they were crying. This did not account for the men who cried inside or used some bro-language or high fives to hide the crying.

The research team then showed each of the study participants either a video that are supposed to make them feel sad (sad videos) or a video that was not supposed to elicit any emotion (neutral videos) like something from a documentary or a ted talk. Each video lasted for close to 18 minutes. After the video, the researchers noted whether or not each participant had cried while watching the video. Ultimately, 65 participants watched the neutral video, 71 watched the sad video and cried during it, and 61 watched the sad video and did not cry. Presumably, no one cried during the neutral video. But then again, actor Bryce Dallas Howard was able to cry when Conan O'Brien talked about Home Depot in this Conan clip:

Then, each participant underwent a Cold Pressor Stress Test (CPT), which involved placing the participant's left hand, up to the wrist, in cold 0° to 5°C water. Unless you are the Iceman or Killer Frost, this is supposed to be painful. The research team measured how long each participant could stay in this position until pulling her hand out of the water. During the study, the research team continuously measured each participant's heart rate and respiratory rate and periodically measured cortisol levels from saliva samples. Cortisol is a stress-hormone that's produced by the body.

Also, at four points during the study, participants answered questions from the Positive and Negative Affect Scale short form (PANAS). These questions asked the degree to which the participant was experiencing ten different emotions and to rank each on a five-point scale that ranged from a one (very slightly or not at all) to a five (extremely).

When it came to cortisol levels and how long the participants could keep their hands submerged in the cold water, the study ended up finding not much difference between the neutral video watchers, the sad video non-criers, and the sad video criers. So if you are about to dunk yourself in cold water or take a cold shower, it may not help to cry first.

But here's a difference that the study found. Are you ready? Take a deep breath. The difference was breathing rates. While watching the videos, the non-criers tended to have elevations in their breathing rates, whereas, by contrast, the criers tended to maintain their initial breathing rates. In other words, tearing up could have helped participants better control their breathing rates. This provides further evidence that crying may help you better regulate arousal, serving as an emotional release.

Another interesting finding was that right before crying, participants tended to experience decreases in their heart rates, seemingly in anticipation of the crying. Once the crying began, their heart rates then tended to creep back up but not above where their heart rates had been before everything began. This may be further evidence that crying has a beneficial regulatory effect on your physiology.

So perhaps next time you start crying you can tell people that you are regulating your physiology. You've probably heard of people saying that they had a good cry and feel better after they've let the tears flow. It can be important to find reasonable ways to periodically release your emotions. Otherwise, you may end up bottling everything up like a hot air balloon that can explode when you least expect it.

Moreover, crying can be a way of communicating. It's really the only way that babies can express their needs before they learn how to say things like "why you throwing shade on me," or "I'm not Gucci." Crying can help communicate to others that you need more sympathy, comfort, or help. Of course, this can be misused. You don't want to cry every time your order at a restaurant doesn't come out right. And of course, there is the whole concept of crocodile tears: people crying to get something when they don't really mean it.

Crying can also be a way of communicating with yourself. Even when you cry alone, you may be telling yourself about your own state because, like many people, you could be terrible at practicing your own emotions and situation. Tears could be your body's way of saying, "hey, take a break," or "something's not right," or "take care of yourself." Tearing up can then be a way of your body literally crying out to you.

Your body is a complex system. Crying can be complex. Your tears can flow when you are very sad, very angry, or even very happy. Better understanding what causes us to cry and what happens as a result could help us better handle their emotions and stress.

Are You a Terrible Writer? ChatGPT Can Help, Study Finds

AI has gotten a lot of attention lately, especially services like ChatGPT, which can be used for everything from finding a good recipe to writing a blog post. A new study shows that it also might be a powerful tool in helping bad writers Excellerate their skills.

In a study published this week in Science, two MIT researchers examined whether ChatGPT could be used to reduce gaps in writing ability between employees. The duo recruited 453 data analysts, marketers, and college-educated professionals and asked them to perform two different writing tasks normally associated with their jobs—writing press releases or a short report, for instance.

Half of the participants were given the option of using ChapGPT to help them complete the second of the two tasks. Afterward, their work was graded by other professionals who worked in the same field on a scale of one to seven, with seven being the best result.

Overall, the participants who used ChatGPT did better than those who didn’t. ChatGPT users took 40% less time to complete their task than their counterparts, and their completed work scored 18% higher in evaluations than the work of those who didn’t use it.

The researchers note that while ChatGPT is powerful, it can also introduce errors, so people who use it to write for them will need to double-check that everything written by the AI tool is correct.

That said, the workers who participated in the study said they were more likely to use the tool in the future. "Workers exposed to ChatGPT during the experiment were 2 times as likely to report using it in their real job 2 weeks after the experiment and 1.6 times as likely 2 months after the experiment," the study found.

Sign up for What's New Now to get their top stories delivered to your inbox every morning.

This newsletter may contain advertising, deals, or affiliate links. Subscribing to a newsletter indicates your consent to their Terms of Use and Privacy Policy. You may unsubscribe from the newsletters at any time.