Neural signature identifies people likely to respond to antidepressant medication
Research published in Nature Biotechnology indicates that new machine learning techniques can identify complex patterns in a person's brain activity that correlate with meaningful clinical outcomes.
Research published in Nature Biotechnology indicates that new machine learning techniques can identify complex patterns in a person's brain activity that correlate with meaningful clinical outcomes. Investigators were able to identify a neural signature that predicts whether individuals with depression are likely to benefit from sertraline, a commonly prescribed antidepressant. Senior author Amit Etkin, MD, PhD, a professor of psychiatry and behavioral sciences at Stanford University and CEO of Alto Neuroscience, observes: "Our findings are exciting because they reflect progress made toward this clinical goal, and they also show the potential of bringing sophisticated data analytic methods to psychiatry." The investigators created a new machine learning algorithm for analyzing electroencephalography (EEG) data called SELSER (Sparse EEG Latent SpacE Regression). SELSER was used to analyze data from the NIMH-funded Establishing Moderators and Biosignatures of Antidepressant Response in Clinic Care study. Investigators applied SELSER to participants' pre-treatment EEG data, assessing whether the machine learning approach could lead to a model that predicted participants' depressive symptoms after treatment. SELSER was able to reliably predict individual patient responses to sertraline based on brain alpha waves. This EEG-based model performed better than standard models that use either EEG data or other types of individual-level data, such as symptom severity and demographic characteristics.