Talk Therapy Vs. Medication For Depression: Brain Scans Reveal Connectivity Predicts Best Depression Treatment We all have different coping mechanisms to ward away the blues; those with depression often rely on a combination of treatments — talk therapy and medication. However, depression is not one-size-fits-all, and neither is treatment. Now, researchers at Emory University in Atlanta, Georgia, believe brain scans may predict the best treatment for patients based on their brain's functional connectivity. "Using these scans, we may be able to match a patient to the treatment that is most likely to help them, while avoiding treatments unlikely to provide benefit," said Dr. Helen Mayberg, lead author of the study and Professor of Psychiatry, Neurology and Radiology and the Dorothy C. Fuqua Chair in Psychiatric Imaging and Therapeutics at Emory University School of Medicine, in a statement. Talk Therapy Vs. Antidepressants: Brain Scans And Functional Connectivity In the study, published in the American Journal of Psychiatry, MRI scans were able to identify the degree of functional connectivity — the connectivity between brain regions that share functional properties — between the subcallosal cingulate cortex — an important emotional processing center — and three other areas of the brain is linked to how well treatment works for particular patients. People who displayed more connectivity between the brain regions were more likely to have success with 15 50-minute talk therapy sessions after 12 weeks. Meanwhile, those with negative or absent connectivity recovered from depression with an antidepressant — escitalopram (10–20 mg/day) and duloxetine (30–60 mg/day) for the same duration. Previous research has shown that different patients respond to different treatments, so each should be taken on a case-by-case basis. In the study, depressed adults without a history of abuse recovered better with combined talk therapy and an antidepressant (Serzone) than either treatment alone. But, for those who had a history of childhood trauma, about half achieved remission from talk therapy, but only a third responded to an antidepressant alone. The combination of psychotherapy and a drug was not significantly better than psychotherapy alone. The researchers proposed the history of trauma in early life is linked with the shrinking of the hippocampus, the region of the brain critical to memory and learning. Those who are depressed with a smaller hippocampus may show improvement with talk therapy because it involves active learning. Antidepressants cannot achieve this effect. Doctors should remain cautious; treatment comes in many forms, and what works for one patient may not work for another. Brain scans can help determine what's the best course of action for a patient. Personalized treatment is more dependent on identifying the specific biological characteristics in patients, than using their symptoms or treatment preferences as a guide. Brain scans may predict the best depression treatment for patients based on their brain's functional connectivity. "Ultimately our studies show that clinical characteristics, such as age, gender, etc., and even patients’ preferences regarding treatment, are not as good at identifying likely treatment outcomes as the brain measurement," said Mayberg. Currently, the treatment guidelines for major depression suggest a patient's preference for either talk therapy or medication be considered when selecting a main treatment. Yet, Mayberg and her colleagues found patients' treatment preferences were weakly linked with outcomes, meaning they did not lead to improvement. Machine Learning Algorithm For Depression Diagnosis Brain scans can revolutionize the way we diagnose depression. A new study in Psychiatry Research: Neuroimaging explains a machine learning algorithm has been trained to detect the risk of depression from brain scan data. Researchers at The University of Texas at Austin trained an AI algorithm with sample data from previous brain scans to split scans of people into either healthy or depressed patients. This was based on their similarity to patterns identified in pre-loaded training scans. The machine learning algorithm predicted depression in 75 percent of cases. These studies suggest we're learning to classify depression from non-depressed people, and how depression is represented in the brain. Source
