LAUSR

Objective: Major depressive disorder (MDD) is a persistent psychiatric condition, and the leading cause of disability, affecting up to 5% of the population worldwide. Antidepressant medications (ADMs) are often the first-line treatment for MDD, but it may take the clinician months of “trial and error” to find an effective ADM for a particular patient. Therefore, identification of predictive biomarkers that can be used to accurately determine the effectiveness of a specific treatment for an individual patient is extremely valuable. Method: Using resting EEG data, we develop a machine learning algorithm (MLA) that searches for connectivity patterns within an individual's EEG signal that are predictive of the probability of responding to the antidepressant Sertraline or Placebo. The MLA has two steps: 1) Directed phase lag index (DPLI), a measure of phase synchronization between brain regions, that is not sensitive to volume conduction is applied to resting-state EEG data, 2) the resulting DPLI matrix is searched for a pattern set of features that can be used to successfully predict the response to Sertraline or Placebo. Results: Our MLA predicted response to Sertraline (N = 105) or Placebo (N = 119) with more than 80% accuracy. Conclusion: Our findings suggest that feature patterns selected from a DPLI matrix may be predictive of response to Sertraline and to Placebo. Significance: The proposed MLA may provide an inexpensive, non-invasive, and readily available tool that clinicians may use to enhance treatment effectiveness, accelerate time to recovery, reduce personal suffering, and decrease treatment costs.