Artificial Intelligence (AI) may increasingly determine which course of treatment is best for patients struggling with depression as well as apart of a new generation of “biology-based, objective strategies” to treat psychiatric disorders. UT Southwestern recently completed a clinical trial using, in part, AI, to better understand mood disorders such as depression. Among other insights, the trial demonstrated that physicians can use computational tools to guide treatment choices for depression.
With the results of the clinical trial published in Nature Biotechnology, the study results are deemed more successful than the investigative team could image reported lead investigator Dr. Madhukar Trivedi, a UT Southwestern psychiatrist. Dr. Trivedi believes the breakthrough will enable care to “move past the guessing game of choosing depression treatments and alter the mindset of how the disease should be diagnosed and treated.”
A Growing Problem
According to data from the National Health and Nutrition Examination Survey, antidepressant use in the U.S. has increased nearly 65% over a decade and a half – from 7.7% in 1999-2002 to 12.7% in 2011-2014. UT Southwestern researchers report that the expanded use of medications make it more critical to further understand the underpinnings of depression and ensure patients are prescribed an effective therapy.
With 300 participants with depression in this 4-month clinical trial, each either received a placebo or SSRI (selective serotonin reuptake inhibitor) the most common type of antidepressant. SSRIs have been scrutinized due to side effects and inefficiency in many patients as reported by UT Southwestern. Lead investigator Trivedi had already studied ways to improve how depression is diagnosed and treated. The UT Southwestern study team set used an electroencephalogram (EEG) to measure the electrical activity in the patient’s cortex prior to treatment and as a means to collect sufficient amount of data to develop a machine learning algorithm to predict which patients would benefit from medication within two months.
The study team found that the AI accurately predicted outcomes, with some patients being less certain to respond to an antidepressant and hence more likely to positively respond to other interventions—from brain stimulation to therapeutic approaches. These findings were replicated across three more patient groups for validation.
The investigators are planning on developing an interface for the tool, known as VitalSign6 thus establishing it as a part of a standard workflow, such as being used alongside EEGs and with other potential means of measuring brain activity—and ultimately file a New Drug Application (IND) for Food and Drug Administration (FDA) approval.
UT Southwestern and Stanford have both filed a patent for the AI tool.
Madhukar Trivedi, UT Southwestern
Amit Etkin, Stanford
Call to Action: The university professors/investigators will patent the underlying AI tool in the quest to commercialize this product. TrialSite News will monitor.