Utilizing Electroencephalography to Predict Anhedonia Response to Antidepressant Treatment

• Applicant: Andreas Strube, Ph.D.
• Subject Area: Biological Psychiatry ; Human Cognitive and Systems Neuroscience ; Cognitive, Systems and Behavioural Neurobiology
• Term: since 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 531626241

The project aims to enhance the accuracy of predicting treatment response in individuals diagnosed with Major Depressive Disorder (MDD) using computational psychiatry and machine learning techniques based on electroencephalography (EEG) measures. The EEG data will be analyzed to identify objective markers related to brain activity and connectivity that can differentiate between individuals who are likely to respond positively to antidepressant medications and those who are not. The project will focus on two commonly used antidepressant medications, Sertraline (a selective serotonin reuptake inhibitor, or SSRI) and Bupropion (an atypical antidepressant), to evaluate if there are specific EEG markers associated with treatment response to each medication, and whether these markers differ between the two medications. This could provide valuable insights into the mechanisms of action of these medications and help clinicians make informed decisions about which medication may be more effective for a particular individual. Anhedonia, the inability to experience pleasure, is a core symptom of MDD and is often resistant to treatment. The project aims to better understand the role of anhedonia in treatment response by investigating its relationship with EEG measures. Specifically, the project will explore whether EEG markers related to reward processing and emotional regulation are associated with anhedonia and whether these markers can predict treatment response in individuals with MDD who experience anhedonia. This could contribute to a deeper understanding of the neurobiological mechanisms underlying anhedonia and provide potential targets for intervention. Advanced machine learning algorithms will be utilized to analyze the complex EEG data and identify patterns or markers that can accurately predict treatment response. These algorithms will allow for the processing of large amounts of data and identification of hidden patterns that may not be apparent through traditional statistical analyses. By developing and validating robust machine learning models, the project aims to create a predictive tool that can be used in clinical practice to inform treatment decisions and improve patient outcomes. The findings of the project will be shared with the scientific community through publications and presentations at conferences. The goal is to contribute to the field of psychiatry and advance the understanding of the neurobiological mechanisms underlying treatment response in individuals with MDD.

• DFG Programme: WBP Fellowship
• International Connection: USA
• Host: Professor Diego Pizzagalli, Ph.D.