Brain Structure Images Can Help Personalize Mental Health Treatment

Glowing Brain Slice Over Blue Background to symbolize mental health brain scans.
Credit: dani3315/Getty Images

A study led by University of Birmingham researchers shows that magnetic resonance imaging (MRI) scans of the brain can show which patients are more likely to experience poor outcomes from psychosis and depression.

The team believes their research, which makes use of machine learning, can help clinicians treat patients more effectively and in a more targeted manner.

“Only 20% of people with psychosis and 25% of people with depression achieve full remission and response to pharmacological treatment, with the remainder achieving partial response or response without remission,” write Paris Alexandros Lalousis, a graduate student and researcher at the University of Birmingham, and colleagues in the journal Biological Psychiatry.

“Biologically-driven illness models, able to relate to those at highest risk of poor outcome and chronicity may allow new and targeted treatments to be delivered early. However, recognizing patients on a path to chronic disability, at an early stage, is still difficult in both psychosis and depression.”

The machine learning algorithm developed by the researchers was initially trained on brain volumetric image data from MRI scans of 577 individuals, 155 patients with recent onset psychosis, 147 with recent onset depression and 275 healthy controls. An external validation sample of over 400 individuals from the same three groups was then used to confirm accuracy.

The researchers found that there were two clusters that most patients fell into. “One cluster had widespread grey matter volume deficits, more positive, negative, and functional deficits (impaired cluster) and one cluster revealed a more preserved neuroanatomical signature and more ‘core’ depressive symptomatology (preserved cluster),” explain the authors.

A second algorithm correctly predicted outcomes at 9 months for the two clusters and those in the ‘impaired’ cluster had worse outcomes than those in the ‘preserved’ cluster.

Notably, both clusters included patients initially diagnosed with depression and psychosis, perhaps calling into question the way these disorders are currently diagnosed.

“A significant number of patients with depression, who may be perceived as having a less severe illness and better prognostic outlook than patients with psychosis, were ascribed to the impaired phenotype, suggesting that they are on a path towards poor outcome,” write the authors.”

“Conversely, a significant number of patients with psychosis were not assigned to the impaired group, and therefore potentially have an identifiable early signature of good prognosis, which was further indicated by the fact that predicting 9-month symptomatic outcomes in that group was more accurate than traditional diagnostic groupings.”

To further validate their findings the researchers looked for the same clusters in groups in large cohort studies in Germany and the U.S. and found they could also be used to accurately predict outcomes. These cohorts included patients who were not recently diagnosed and the team found that the longer the duration of illness the more likely the patients were to fall into the ‘impaired’ group.

“That really adds to the evidence that structural MRI scans may be able to offer useful diagnostic information to help guide targeted treatment decisions,” said first author Lalousis, in a press statement.

This site uses Akismet to reduce spam. Learn how your comment data is processed.