How machine learning applied on fMRI could improve the prognosis of the post-traumatic stress disorder: A systematic review.
Aida Peyvandi, Alessandro Pigoni, Andrea Anastasi et al.
✦ AI-curated · Sources linked
In 30 seconds
This systematic review examined functional brain differences in individuals with post-traumatic stress disorder (PTSD) compared to healthy controls, utilizing machine learning techniques. The analysis included 19 studies and found that the default mode and salience networks were key in classifying PTSD participants. Additionally, the left amygdala and hippocampus association was crucial for identifying PTSD severity.
Key findings
- Default mode and salience networks were key in classifying PTSD participants from both trauma-exposed and non-exposed healthy controls.
- Middle frontal gyrus and sensory motor area were involved in distinguishing PTSD from trauma-exposed healthy controls.
- The association between left amygdala and hippocampus was crucial for identifying PTSD severity.
Why it matters
Understanding the functional brain differences in PTSD can enhance diagnostic accuracy and potentially lead to better prognostic tools. This knowledge may help identify individuals at higher risk for developing PTSD after trauma exposure.
What to keep in mind
The review faced limitations due to the non-homogeneous characteristics of the included studies, affecting the ability to draw comprehensive conclusions.