A retrospective study of profiling response to antidepressant drugs - CAN-BIND Integrated biological markers for the prediction of treatment response in depression

PI

• PI - Prof. Jonathan Rabinowitz, PhD (Elie Wiesel Professor, Bar-Ilan University)
• Sarah F. Feldman, MD, MPH, MSc

‍DESCRIPTION

Developing a Comprehensive Prediction Model for Antidepressant Response in MDD

This study aims to develop a machine learning-based classification model to predict antidepressant treatment response in patients with major depressive disorder (MDD). The model will incorporate a wide range of patient data, including demographics, clinical assessments, medical conditions, clinical rating scales, questionnaires, medical care information, behavioral measures, neurocognitive testing, and genomic, genetic, and proteomic profiles. The performance of the model will be evaluated using different response definitions, including the MADRS and QIDS scores. Additionally, the study will investigate potential biomarkers associated with treatment response, treatment resistance, and optimal dosage. Finally, correlations between clinical and molecular features will be explored to gain further insights into the underlying mechanisms of MDD and treatment response.

‍

PARTICIPANTS

CAN BIND 1st phase Cohort - 309 patients (206 MDD and 103 control).