Translator: Bolysbek Dana
Editor: Akhmetova Aigerim
Author: Aldiyarbek Nurlan
Although major depression is usually easy to diagnose, a better understanding of the neural networks associated with depression can improve treatment strategies. Such machine learning algorithms can be applied to data on brain activity in people with depression to find similar associations. However, most research focuses only on certain subtypes of depression, or does not account for differences in brain imaging protocols between health care institutions.
To solve these problems, Yamashita and his colleagues used machine learning to analyze data from the brain networks of 713 people, 149 of whom suffered from major depression. This data was collected using a technique called resting-state functional MRI (rs-fMRI), which detects brain activity and creates images that show coordinated activity, or "functional connections" between different parts of the brain. Imaging was performed in different institutions using different protocols.
The machine-learning method identified key functional connections in the imaging data that could serve as a brain network signature for major depression. Indeed, when the researchers applied that new signature to rs-fMRI data collected at different institutions from 521 other people, they achieved 70 percent accuracy in identifying which of those new people had major depressive disorder.
The researchers hope that their new brain network signature, which can be applied to a variety of imaging protocols, could serve as a basis for discovering brain network patterns associated with depression subtypes and identifying relationships between depression and other disorders. A better understanding of brain network connections in major depression could help match patients to effective treatments and inform development of new treatments.
Source: https://www.sciencedaily.com/releases/2020/12/201207142315.htm
