New Imaging Algorithm May Help Doctors Differentiate Unipolar and Bipolar Depression
New research published in the latest edition of JAMA Psychiatry may help medical professionals distinguish patients with unipolar and bipolar depression by specific structural brain differences.
According to the report from the University of Munster, Germany, differences in the grey and white matter volumes in the amygdala, hippocampus, and anterior cingulate gyrus (ACG) distinguished individuals with the conditions with 70% accuracy.
“These regions are known to be important for emotion processing and regulation”, observed the researchers led by Udo Danlowski.
The study recruited 58 patients diagnosed with bipolar depression, 58 who had been diagnosed with unipolar depression, and 58 age and gender matched mentally healthy control participants. When the researchers tested pattern recognition algorithms on structural brain imaging of the participants (undertaken at either a US or German location), they obtained a classification accuracy for unipolar versus bipolar depression of up to 65.5% at the US site and 75.9% for the German site.
When they created the algorithms at one site and tested them at the other, they obtained an accuracy of up to 63.8% for testing in the US group and 69.0% for testing in the German group.
“Although a performance of less than 70% accuracy may not be regarded as substantial enough to justify a clinical application, it must be emphasized that, to our knowledge, this is the first use of pattern classification algorithms with classifiers trained on a reference sample to data from an independent sample measured on a different scanner platform”, say Dannlowski and colleagues.
The researchers noted that patients with bipolar depression appeared to have notably less grey matter than those diagnosed with unipolar depression in four areas of the brain including the hippocampus, amygdala, putamen, insula, and the temporal pole. In comparison, patients diagnosed with unipolar depression had less grey matter only in the ACGl which is thought to be in line with previous research and significant an “inability to regulate automatic negative self-referential processing and accompanied feelings.”