New deep brain stimulation device combined with powerful artificial intelligence could improve treatment of drug-resistant depression. Using a new deep brain stimulation (DBS) device capable of recording brain signals, researchers have identified a pattern of brain activity, or "biomarker," associated with signs of clinical recovery from drug-resistant depression. The findings from this small study are an important step toward using brain data to understand how patients respond to DBS treatments.
The research was published in the journal Nature and was supported by the National Institutes of Health's Brain Research through Advancing Innovative Neurotechnologies (BRAIN Initiative) initiative.
Clinical applications of DBS
Although this approach is still in the experimental stage, clinical studies have shown that DBS can be used safely and effectively to treat cases of depression where symptoms have not improved despite antidepressant medication, a condition known as drug-resistant depression. Patients undergoing DBS undergo surgery to implant a thin metal electrode into a specific area of the brain to generate electrical impulses to regulate brain activity. Exactly how DBS improves symptoms in people with depression is poorly understood, making it difficult for researchers to objectively track patients' responses to treatment and make adjustments as needed.
The small study enrolled 10 adults with treatment-resistant depression, who all received DBS for six months. Each participant initially received the same dose of stimulation, and then the stimulation level was increased one or two times. The researchers then used artificial intelligence (AI) tools to analyze brain data collected from six patients and observed a common brain activity signature, or biomarker, that correlated with patients' self-reported symptoms of depression or stable symptoms of recovery. In one patient, the researchers discovered the biomarker and, through retrospective analysis, predicted that the patient would return to a major depressive episode four weeks before a clinical interview revealed that he was at risk for recurrence.
Improving DBS treatment
"This study shows that new technologies and data-driven approaches can improve DBS treatment of major depressive disorder, which can be debilitating," said Dr. John Ngai, BRAIN Program Director. "It is collaborations like the one the BRAIN Initiative enables that bring promising therapies closer to clinical use.
In this study, patients received DBS therapy that targeted the subcingulate cortex (SCC), a brain region that regulates emotional behavior and is associated with sadness. DBS of the cingulate cortex is an emerging therapy that can provide long-term and stable relief of depressive symptoms. However, treating depression with DBS remains challenging because each patient's path to stable recovery is different. Clinicians must also rely on subjective self-reports in patient interviews and psychiatric rating scales to track symptoms, which can fluctuate over time. This makes it difficult to differentiate between normal mood changes and more serious conditions that require adjustments to stimulation. Additionally, changes in symptoms after DBS treatment may take weeks or months to appear, making it difficult to tell how effective the treatment is.
"This biomarker demonstrates that brain signals can be used to help understand a patient's response to DBS treatment and adjust treatment accordingly," said Joshua A. Gordon, MD, director of the National Institute of Mental Health at the NIH. "These findings mark a major step forward in translating therapies into practice."
Patient response and role of technology
The patients in the study responded well to DBS treatment; after 6 months, 90% of the patients' depressive symptoms improved significantly, and 70% of the patients were in remission or no longer depressed. Such a high response rate provides us with a unique opportunity to look back and study how each patient's brain responds differently to stimulation during treatment.
Christopher Rozelle, the Julian T. Hightower Chair in Electrical and Computer Engineering and a Ph.D. in electrical and computer engineering at the Georgia Institute of Technology in Atlanta, and his colleagues used a technique called explainable artificial intelligence to understand these subtle changes in brain activity. The algorithm uses brain data to distinguish between depressive states and stable recovery states, and can explain which changes in activity in the brain are the main drivers of this shift. Importantly, the biomarker also distinguished between normal, day-to-day transient mood changes and persistently worsening symptoms. This algorithm could provide clinicians with early warning signs that a patient is progressing toward a highly depressed state and requires DBS adjustments and additional clinical care.
Further insights and next steps
"Nine of the 10 patients in the study improved, which provides an excellent opportunity to use new technology to track patients' recovery trajectories," said Helen Mayberg, MD, co-first author of the study and director of the Nash Family Center for Advanced Circuit Therapy at Mount Sinai in New York City. "Our goal is to identify an objective neural signal that can help clinicians decide when or not to make DBS adjustments." "
"Our study shows that with a scalable procedure and informed clinical management using single electrodes in the same brain region, we can get patients better," said Dr. Rozelle, co-senior author of the study. "This study also gives us an excellent scientific platform to understand differences between patients, which is key to treating complex psychiatric disorders like drug-resistant depression."
Next, the team analyzed MRI brain scan data taken from the patients before surgery. The results showed structural and functional abnormalities in the specific brain networks targeted by DBS therapy. More severe white matter defects are associated with longer recovery times.
The researchers also used artificial intelligence tools to analyze changes in facial expressions extracted from videos of participant interviews. In a clinical setting, a patient's facial expressions can reflect the severity of their depressive symptoms, and psychiatrists are likely to detect such changes during routine clinical assessments. They found that individual patients' expression patterns matched their transition from illness to stable recovery. This could serve as an additional tool and new behavioral marker to track recovery from DBS treatment. More research is needed to determine whether video analysis can reliably predict current and future disease states.
The observed facial expression changes and anatomical defects were both correlated with cognitive status captured by the biomarker, supporting the use of this biomarker in the management of DBS therapy for depression.
The research team, which includes Mayberg, M.D., Rozell, M.D., and Patricio Riva-Posse, M.D., of Emory University School of Medicine in Atlanta, is currently confirming their findings in a second cohort of patients at Mount Sinai Hospital. Future research will continue to explore the antidepressant effects of DBS, using next-generation equipment to study the neural basis of momentary changes in mood.
According to the research team, this study marks a significant advance in early DBS treatment for a variety of mental disorders, including major depression, obsessive-compulsive disorder, post-traumatic stress disorder, bulimia and substance use disorders. Other DBS studies have identified brain biomarkers of chronic pain, but ways to use brain data to successfully treat patients are still being developed.