Abstract: Described herein are systems and methods for predicting response to treatment for a neurological or psychiatric disorder. The systems may include machine learning and run LDA and/or Lasso Regression methods that use psychometric inventories and other forms of patient data such as patient characteristics, treatment history, clinical history, biometric data, neuroimaging data, or a combination thereof, as inputs to generate a predictive model that separates responders from non-responders. The methods may include prediction of response to initial treatment by obtaining baseline, pretreatment data collected through psychometric inventories as well as other forms of patient data.