Personalized Response and Dropout Prediction for Anxiety Treatment Using Machine Learning
- Resource Type
- Authors
- Malgaroli, Matteo; Hofmann, Stefan; Simon, Naomi; Moskow, Danielle; Ghosh, Satrajit; Gabrieli, John; Hoeppner, Susanne; Hoge, Elizabeth; Bui, Eric; Rosenfield, David; Gomez, Angelina; Barthel, Abigail; Khalsa, Sat
- Source
- Subject
- Medicine and Health Sciences
- Language
Our aim for this study is to understand the individual factors what can be used to predict who is most likely to respond to or drop out of treatment for Generalized Anxiety Disorder. We will use supervised machine learning methods to assess the extent to which baseline individual and treatment characteristics can predict dropout, and which are the most important risk factors. The study will be focusing on a secondary analysis from a randomized control trial for GAD (doi:10.1001/jamapsychiatry.2020.2496)