A new study analyzes MRI data from patients with depression and social anxiety to help advance the treatment and understanding of these disorders.
The development of artificial intelligence it advances by leaps and bounds, becoming one of the key technologies this year and ahead of 2018. AI is able to predict the success of a startup or the risk of diabetes thanks to tools such as machine learning.
Machine learning is the only area that has been proven to work within AI, as he told us in an interview Martin, CEO of BigML. How does this technology work? “Machine learning is a set of algorithms capable of analyzing data in multiple dimensions from which a pattern is drawn and then predictions can be made. It allows us to study volumes of data that our brain is unable to analyze efficiently, ” the expert argued.
Machine learning for personalized diagnostics
In this scenario, machine learning is very useful in medicine. In fact, artificial intelligence applied to machine learning may be able to predict depression in patients. When it comes to fighting the disease, doctors establish patterns with common symptoms, but each patient needs a personalized treatment. This is where artificial intelligence comes into play.
A study published in Psychiatry Research it showed that it is possible to identify which patients would be depressive through magnetic resonance images and their subsequent analysis through machine learning. On the other hand, the Emory University (USA) also conducted another study that used magnetic resonance imaging analysis to establish patterns of brain activity when the patient is under treatment.
Differences and similarities using MRI
There are similarities and clinical links between depression and anxiety, it has shown a recent study presented at the annual meeting of the Radiological Society of North America (RSNA). They even share a considerable amount of clinical symptoms, although there has been little direct comparison of the structure of the brain, according to the doctor Youjin Zhao from Sichuan University in Chengdu (China).
Zhao and his co-author, Dr. Su Lui, have worked together to better observe structural differences and similarities in the brain using MRI, and, through their analysis, have been able to observe brain abnormalities in gray matter and assess the thickness of the cortex.
The study used images of 37 patients with depressive disorder, 24 with anxiety disorder and 41 healthy people. Their findings provide preliminary evidence of common and specific gray matter changes in patients with both disorders. “Future studies with larger sample sizes, combined with machine learning analysis, can further help the diagnostic and prognostic value of structural MRI,” the study’s author said in a statement.
The differences are still noticeable. Within the patients, the team observed abnormalities in the gray matter of the dorsal attention networks and salience of the brain. In addition, they observed varied cortical thicknesses that ” may reflect a compensatory mechanism related to inflammation or other aspects of pathophysiology,” Zhao said. In this sense, a greater cortical thickness “could be the result of both continuous coping efforts and patients ‘ attempts to regulate”.
Further research and exploration into the physiology of these disorders will lead to applicable therapies, although additional longitudinal work on larger samples is required to draw more robust conclusions.
AI is a field that never ceases to amaze us and, for the moment, the application of machine learning in disorders such as depression shows hopeful results.
