2024-09-02 15:13:32
What can be discovered in the causes of autism. A multi-university research team led by Gustavo K. Rohde, a professor of engineering at the University of Virginia, has developed a powerful system to identify genetic markers of autism in brain images with an accuracy of 89-95%.
Their findings suggest that doctors may one day detect, classify and treat autism and related neurological conditions with this method without having to wait for behavioral interventions, leading to earlier treatments. “Autism is traditionally diagnosed based on behavior, but it has a strong genetic basis. A genetic approach can change its understanding and treatment,” the researchers wrote in a paper published June 12. in the journal Science Advances.
Rohde, a professor of biomedical, electrical and computer science, collaborated with researchers at the University of California, San Francisco and the Johns Hopkins University School of Medicine, including Shinjini Kundu, Rohde’s former doctoral student. and first author of the study.
While working in Rohde’s lab, Kundu, now a physician at Johns Hopkins Hospital, helped develop a an innovative computer modeling technique called movement-based morphometry or TBM, which is at the heart of the group’s path.
Using a new mathematical model of the brain, their program reveals patterns of brain structure that predict differences in certain regions of an individual’s genetic codea phenomenon called “copy number variations,” in which segments of DNA are deleted or duplicated. These differences are linked to autism.
TBM allows researchers to distinguish normal biological differences in brain structure from those associated with deletions or duplications. “Some genetic differences are known to be associated with autism, but their connection to brain morphology, in other words, how different types of brain tissue such as gray or white matter are arranged in our brain, he doesn’t know very well,” Rohde said. . “Discovering how CNVs relate to brain tissue morphology is an important first step to understand the basic theory of autism.
How TBM cracks the code
Movement-based morphometrics differs from other mechanical image analysis models because it depends on mass transport, ie the movement of materials such as proteins, nutrients and gases into and out of cells and tissues. “Morphometry” refers to the measurement and measurement of biological shapes created by these processes.
“Many machine learning methods have little or no relationship to the biophysical processes that characterize the data. But Rohde’s method uses mathematical equations to extract rich information from medical images, creating new images for visualization and further analysis.
Then, using different mathematical methods, the system analyzes the information associated with autism-related CNV variants from other “normal” genetic variants that do not lead to neurological diseases or disorders, what researchers call it “confounding sources of variability.” Previously, these resources prevented researchers from understanding the “gene-brain-behavior” relationship, limiting healthcare providers to behavior-based studies and treatments.
If we use more appropriate mathematical models to extract such information, we can reach important findings from this large amount of data. According to Forbes magazine, 90% of medical data is in the form of images, but there are no proper ways to write them. Rohde believes the TBM is the master key. “Important discoveries can be made from such a large amount of data if we use more appropriate mathematical models.”
#generic #code #deciphered #hope #early #diagnosis