Connect with us
captura481 captura481


AI for the early detection of autism in children



An interdisciplinary team, led by computer science researchers at USC, is creating a faster, more reliable, and more accessible system to help doctors screen children for developmental disorders like autism and ADHD.

For children with autism spectrum disorder (ASD), receiving an early diagnosis can make a big difference in improving behavior, skills, and language development. But despite being one of the most common developmental disabilities, it is not that easy to diagnose.

Artificial intelligence to assess developmental disorders in children

There are no laboratory tests or a single identified genetic cause; instead, physicians observe the child’s behavior and conduct structured interviews with the child’s caregivers based on questionnaires. But these questionnaires are long, complicated, and not foolproof.

“When trying to discern and stratify a complex condition like autism spectrum disorder, knowing what questions to ask and in what order becomes challenging”, He said USC University Professor Shrikanth Narayanan, Professor of Engineering and professor of electrical and computer engineering, computer science, linguistics, psychology, pediatrics, and otolaryngology.

“As such, this system is difficult to administer and can produce false positives, or mistake ASD for other comorbid conditions, such as attention deficit hyperactivity disorder (ADHD).”.

As a result, many children do not receive the treatments they need at a critical time.

An interdisciplinary team led by computer science researchers at USC, in collaboration with clinical experts and autism researchers, hopes to improve this by creating a faster, more reliable, and more accessible system for detecting ASD in children. The AI-based method takes the form of a computer-based adaptive test, powered by machine learning, that helps clinicians decide which questions to ask next in real time based on past responses from caregivers.

“We wanted to maximize the diagnostic power of the interview by initiating the doctor with an algorithm that can be more curious if necessary, but we will also try not to ask more questions than you need.”said the study’s lead author, Victor Ardulov, a doctoral student in computer science advised by Narayanan. “By training the algorithm in this way, you are optimizing it to be as effective as possible with the information collected so far.”.

In addition to Narayanan and Ardulov, the study co-authors published in Nature Research Scientific Reports are Victor Martinez and Krishna Somandepalli, both recent PhD graduates from USC; autism researchers Shuting Zheng, Emma Salzman, and Somer Bishop of the University of California, San Francisco; and Catherine Lord of the University of California, Los Angeles.

In the study, the research team of computer scientists and clinical psychologists specifically looked at differentiating between ASD and ADHD in school-age children. ASD and ADHD are neurodevelopmental disorders, which are often misdiagnosed for each other: behaviors exhibited by a child due to ADHD, such as impulsivity or social discomfort, can resemble autism, and vice versa.

As such, children may be flagged as at risk for conditions they may not have, which could delay proper evaluation, diagnosis, and intervention. In fact, autism can be overdiagnosed in up to 9% of children, according to a study by the Centers for Disease Control and Prevention and the University of Washington.

To help reach a diagnosis, the professional assesses the child’s communication skills and social behaviors by collecting a medical history and asking open-ended questions of caregivers. The questions cover, for example, specific repetitive behaviors or rituals, which could be hallmarks of autism.

At the end of the process, an algorithm helps the practitioner calculate a score, which is used as part of the diagnosis. But the questions asked do not change according to the responses of the interviewee, which can lead to overlapping of information and redundancy.

“This idea that we have all this data, and we process all the numbers at the end, is not really a good diagnostic process.”Ardulov said. “Diagnostics is more like playing a game of 20 questions: what is the next thing I can ask that helps me make the diagnosis more effectively?”

Instead, the researchers’ new method acts as a smart flow chart, adapting based on the respondent’s previous responses and recommending which item to ask next as more data about the child becomes available.

For example, if the child is able to carry on a conversation, it can be assumed that he has verbal communication skills. “So our model might suggest asking about speech first and then deciding whether to ask about conversational skills based on response, effectively balancing query minimization, while maximizing collected information.”Ardulov said.

They used Q-learning, a reinforcement learning training method based on rewarding desired behaviors and punishing unwanted ones, to suggest what elements to follow to differentiate between disorders and make an accurate diagnosis.

“Instead of just processing the answers at the end, we said: here’s the next best question to ask during the process.”Ardulov said. As a result, our models are better at making predictions when presented with less information.

The test is not intended to replace a qualified physician’s diagnosis, the researchers said, but to help them make the diagnosis more quickly and accurately.

“This research has the potential to allow clinicians to go through the diagnostic process more effectively, either in a more timely manner or by relieving some of the cognitive strain, which has been shown to reduce the effect of exhaustion.”Ardulov said.

“It could also help clinicians classify patients more efficiently and reach more people by acting as an app-based home screening method.”.

Although there is still work to be done before this technology is ready for clinical use, Narayanan said it is a promising proof of concept for adaptive interfaces in diagnosing social communication disorders, and possibly more.

“Such an approach is truly significant because of its applicability not only within TEAs,” Narayanan said. “It could also help diagnose many mental and behavioral health conditions throughout life and worldwide, including anxiety disorder, depression, addiction and dementia, which rely on similar procedures to understand and treat them.”


Click to comment

Leave a Reply

Your email address will not be published.


Budget video cards will become useless. Ryzen 7000 Mobile Processors May Get Ultra-Performing iGPU, 3D V-Cache Boosted



Budget video cards will become useless Ryzen 7000 Mobile Processors

Phoenix generation Ryzen 7000 mobile processors are credited with incredibly powerful iGPUs. But these APUs may turn out to be even more interesting than previously thought.

Budget video cards will become useless.  Ryzen 7000 Mobile Processors May Get Ultra-Performing iGPU, 3D V-Cache Boosted

Recall that these will be processors based on the Zen 4 architecture. The iGPU of the top models will supposedly have 1536 stream processors, which is twice as much as the Ryzen 7 6800U. This alone is enough to take iGPU performance to a whole new level. But lately, rumors have attributed to the new products a graphics core based on the RDNA 3 architecture. In this case, the performance gain will obviously be much more than twofold.

Now, an insider who has accurately described data about AMD video cards and processors many times has said that mobile Ryzen 7000 can also get a 3D V-Cache chip. This is allegedly indicated by information directly from the factory.

However, it is not clear whether this cache will work with the CPU or with the GPU. In the second case, it will be almost the same as Infinity Cache for Radeon RX 6000 video cards. And this will significantly increase the performance of the graphics core. True, it seems that such APUs will only be in the Ryzen 7000HX line.

But, if all these rumors and leaks are true, the same source’s recent claim that the Ryzen 7000’s iGPU could be comparable to the mobile 60W GeForce RTX 3060 doesn’t sound so fantastic anymore.

Continue Reading


Another port of Intel. XeSS technology will not appear in Dolmen on May 20



Another port of Intel XeSS technology will not appear in

Only yesterday we learned that Intel XeSS technology will become available in the first game on May 20, as the developers denied this information.

Another port of Intel.  XeSS technology will not appear in Dolmen on May 20

More specifically, they themselves initially stated that their game Dolmen would support XeSS, and would receive that support with the Day 1 patch on May 20th. But now the studio Massive Work Studio, responsible for the game, wrote that Intel XeSS in Dolmen will appear in the summer. Exactly when is not known, but it does not exactly match previous statements.

Considering that Intel itself promises to finally release desktop Arc graphics cards also in the summer, everything fits together. True, the adapters will initially be exclusive to China, and at first they will be available only as part of finished PCs.

Be that as it may, now at least there will be no strange situation when XeSS technology would become available, and Intel video cards with its support would be absent on the market.

Most likely, the developers of Dolmen really planned to release everything on May 20, since Intel originally planned to release video cards before the summer. But then Intel’s plans changed, so Massive Work Studio had to adjust.

Continue Reading


Elon Musk knocks down the price? He does not want to complete the deal to buy Twitter without an audit, which is impossible



Elon Musk knocks down the price He does not want

Elon Musk’s purchase of the social network Twitter is getting more and more interesting. The other day, the billionaire said that the number of fake and spam accounts on Twitter can exceed 90% of the number of daily active users, but in general he leans towards 20%.

Elon Musk knocks down the price?  He does not want to complete the deal to buy Twitter without an audit, which is impossible

Musk has already said he wants to audit, so he put the deal on hold for now. However, there appear to be problems with the audit procedure.

Twitter CEO Parag Agrawal wrote that it is unlikely that an external audit could be carried out.

Unfortunately, we do not believe that this particular assessment can be done externally, given the urgent need to use both public and private information (which we cannot share). Outwardly, it is even impossible to know which accounts are counted as daily active.

Agrawal also said that Twitter is actively fighting spam accounts, blocking more than half a million accounts daily. He reiterated that the company has been counting such accounts for many years, and the rate has always been less than 5%.

Musk said that the CEO of Twitter publicly refused to provide evidence of such indicators, which is why the deal cannot move towards completion.

It is not yet clear how this story will end, but it is likely that all this will allow Musk to buy Twitter for significantly less than the original $ 44 billion. Perhaps from the very beginning, Musk had such a tactic, and now he adheres to it.

Continue Reading

Most Popular