WHY THIS MATTERS IN BRIEF
Artificial Intelligence is helping doctors diagnose more and more syndromes that were previously hard to diagnose.
Artificial Intelligence (AI) is increasingly becoming a powerful new tool in the fight to properly identify, diagnose, and then treat a wide range of health problems, from the onset of dementia, depression, and PTSD, through to the diagnosis of many diseases, including eye disease, genetic diseases, heart disease, lung cancer, and even pancreatic and skin cancer with just a smartphone. And now, in yet another breakthrough a team of researchers from Cincinnati Children’s Hospital Medical Center in the US have used AI to predict Attention Deficit Hyperactivity Disorder (ADHD) in patients by having it analyse Magnetic Resonance Imaging (MRI) scans. According to a new paper published in the journal Radiology: Artificial Intelligence, their technique could also be used to spot other neurological conditions.
Health care professionals have increasingly been relying on MRI scans to understand ADHD, a brain disorder that often causes patients to be restless, and makes it more difficult for them to pay attention. More than eight percent of children in the US have been diagnosed with the condition according to The American Psychiatric Association (APA).
Research suggests that a breakdown in the connections between the different regions of the brain, the so-called connectome, causes ADHD. MRI scans are able to spot any disruption in this network — but recogniSing the patterns that could indicate a case of ADHD is much more difficult.
The researchers developed a method using a deep learning model that can analyse multiple connectome maps from different regions of the brain. Their model “improved ADHD detection performance considerably” while analysing a data set of 973 participants according to the paper.
“This model can be generalised to other neurological deficiencies,” said senior author Lili He in a statement. “We already use it to predict cognitive deficiency in pre-term infants. We scan them soon after birth to predict neuro-developmental outcomes at two years of age.”