Home » Can AI detect ADHD with near perfect accuracy?

Can AI detect ADHD with near perfect accuracy?

via Psychiatry and Behavioral Health Learning Network


Exploration Highlights


  • A new study led by a University at Buffalo researcher has identified how specific communication among different brain regions, known as brain connectivity, can serve as a biomarker for attention deficit hyperactivity disorder (ADHD).
  • The research relied on a deep architecture using machine-learning classifiers to identify with 99% accuracy those adults who had received a childhood diagnosis of ADHD many years earlier.
  • “This suggests that brain connectivity is a stable biomarker for ADHD, at least into childhood”
  • The findings have implications for not only detecting ADHD, a common but diagnostically slippery disorder that’s difficult to identify, but can also help clinicians target treatments by understanding where patients sit on a broad-spanning continuum.
  • “Because certain pharmaceuticals react with certain pathways, understanding the different types of ADHD can help inform decisions about one medication versus others,” said McNorgan, an expert in neuroimaging and computational modeling.
  • Attention deficit disorder is the most commonly diagnosed psychological disorder among school-aged children, but multiple subtypes complicate a clinical definition of ADHD.
  • A clinical diagnosis of ADHD in a patient can change when that same patient returns for a subsequent evaluation.
  • The brain connectivity signature of ADHD appears to be more stable.
  • Focused analysis of individual runs achieved 91% percent diagnostic accuracy, while the collective analysis came close to 99%.
  • “It’s by far the highest accuracy rate I’ve seen reported anywhere – it is leagues beyond anything that has come before it, and well beyond anything that has been achieved with a behavioral assessment,” said McNorgan. “Many factors likely contributed towards our superior classification performance.”
  • Deep learning networks are well-suited for detecting conditional relationships, which are nonlinear.
  • These sorts of relationships are problematic for the most commonly-used techniques, but not for deep-learning classifiers.
  • “This approach by differentiating both of these dimensions provides a mechanism for sub-classifying people with ADHD in ways that can allow for targeted treatments,” said McNorgan. “We can see where people are on the continuum.”
  • Because different brain networks are implicated in people at either ends of the continuum, this method opens the door for developing therapies that focus on specific brain networks, he added.

Original Article: Study: Detecting ADHD with near perfect accuracy

More from: University at Buffalo on Innovation2


Go deeper with the LATEST Bing News on:


Go deeper with the LATEST Bing News on:

Detecting ADHD
  • Study: Signs of early Alzheimer's disease may be spotted in brain stem
    on September 23, 2021 at 11:13 am

    Certain changes in a part of the brain stem, visible in scans, might be a potential early indicator of Alzheimer's disease, a new study suggests.

  • Environmental Causes of ADHD: Is It Nature or Nurture?
    on September 23, 2021 at 6:42 am

    When it comes to attention deficit hyperactivity disorder (ADHD), you may wonder whether nature or nurture plays the largest role in causing it. For example, say more than one of your children has ...

  • MSU researches studying MRIs to detect mental illnesses in babies
    on September 21, 2021 at 2:14 pm

    The National Institute of Health awarded a$ 5.5 million grant to Michigan State University researchers to conduct a new international study. A team of MSU ...

  • From watches to apps: Connected tech for better health care
    on September 21, 2021 at 5:48 am

    A look at the latest apps, smart watches, and more for better health. In 2007, Steve Jobs changed the world—and medical care—by introducing the iPhone. The iPad followed in 2010, and the Apple Watch ...

  • Psychology Today
    on September 20, 2021 at 1:21 pm

    Smells are extremely effective at triggering memories. Among the five senses, smells tend to rank last in terms of popularity, but a 2021 study at Northwestern University found that our sense of smell ...

  • Psychology Today
    on September 17, 2021 at 4:49 pm

    Heart disease remains a quiet killer. And issues like blockages or irregular heartbeats aren’t something you can detect on your own. Especially if you (like me) have or lost a parent to heart ...

  • Multigenerational study finds links between ADHD, dementia risk
    on September 15, 2021 at 6:32 am

    Parents and grandparents of people with ADHD have a higher risk of Alzheimer's and dementia than people with no ADHD in their family, Swedish researchers said.

  • AerHome Makes People Smarter about the Air in their Homes
    on September 14, 2021 at 1:26 pm

    Air pollution is bad for our health and can be especially problematic for infants and young children contributing to asthma, autism, obesity, diabetes, ADHD and other mental health issues. In fact, ...

  • Attention deficit disorders news
    on September 10, 2021 at 10:28 pm

    Half of adults aged 20-39 with attention deficit hyperactivity disorder (ADHD) have had a substance use disorder (SUD) in their lifetime according to new research published online ahead of print ...

  • “We will all reap the rewards”: Why workplaces need to better encourage neurodiverse individuals
    on September 8, 2021 at 5:14 pm

    James has been diagnosed with attention deficit hyperactivity disorder (ADHD). These conditions mean ... a logical and analytical approach to detecting irregularities; pattern-matching skills ...



Add Comment

Click here to post a comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.