A novel precision medicine approach augmented by artificial intelligence (AI) has formed the basis for the first biomedical screening and intervention tool for autism, reporting a new study from Northwestern University, Ben Gurion University, Harvard University, and Massachusetts. Institute of Technology.
It is believed to be the first of its kind in precision medicine.
“The first autism subtype is defined based on symptoms only – autistic disorder, Asperger syndrome, etc. – and they can be difficult to distinguish because it is actually a spectrum of symptoms,” study co-first author Dr. Yuan Luo, Associate Professor of Preventive Medicine: Health and Biomedical Informatics at Northwestern University Feinberg School of Medicine.
“The autism subtype characterized by abnormal levels identified in this study is the first multidisciplinary evidence-based subtype with distinct molecular features and an underlying cause.”
Luo is also the Chief AI Officer at the Northwestern University Clinical and Translational Sciences Institute and the Institute of Augmented Intelligence in Medicine. He is also a member of the McCormick School of Engineering.
According to the Centers for Disease Control and Prevention, autism affects an estimated 1 in 54 children in the United States. Boys are four times more likely than girls. Most children are diagnosed after the age of 4, although autism can be diagnosed at the age of 2, depending on the symptoms.
The subtype of the disorder studied by Luo and coworkers is known as dyslipidemia-associated autism, which occurs in the U.S. Represents 6.55% of all diagnosed autism spectrum disorders.
“Our study is the first precision medicine approach to overlay an array of research and health care data — including genetic mutation data, sexually distinct gene expression patterns, animal model data, electronic health record data, and health insurance claim data — and then Includes using AI -Henced precision medicine approaches to try to define one of the world’s most complex underlying disorders, ”Luo said.
This idea is similar to today’s digital maps. To get a true representation of the real world, the team etched different layers of information on top of each other.
“This discovery was like finding a needle in a histac, because there are thousands of variants in hundreds of genes thought to reduce autism, each mutating into less than 1% of the families of the disorder. We created a complex map. , And then needed to develop a magnifier to zoom in, ”Luo said.
To produce that magnifier, the research team identified groups of gene exons that function together during brain development. He then used a state-of-the-art AI algorithmic graph clustering technique on gene expression data. Exons are parts of genes that contain information coding for proteins. Proteins do most of the work in our cells and organs, or in this case, the brain.
“The map and magnification approach shows a common way of using multiple data models to reduce autism and has the potential to inform targeted clinical trials for many other genetically complex diseases,” Luo said .
Using the tool, the research team also identified a strong association of dyslipidemia of parents with autism spectrum disorder in their children.
He subsequently altered the blood lipid profile in infants and later diagnosed with autism spectrum disorder. These findings prompted the team to pursue subsequent studies, including clinical trials aimed at promoting early screening and early intervention for autism.
A multidisciplinary precision medicine approach identifies an autism subtype characterized by dyslipidemia
The promise of precision medicine lies in data diversity. More than the sheer size of biomedical data, it is a layer of several data models, offering complementary approaches that are thought to enable the identification of patient subgroups with shared pathophysiology.
In the present study, we use autism to test this assumption. By combining health claims, electronic health records, family whole-release sequences, and neurodevelopmental gene expression patterns, we identified a subgroup of dyslipidemia-related autism patients.
Neuroscience News posts science research news from laboratories, universities, hospitals, and news departments around the world. Science articles can cover neuroscience, psychology, AI, robotics, neurology, brain cancer, mental health, machine learning, autism, Parkinson’s, Alzheimer’s, brain research, depression, and other topics related to cognitive science.
