A wavelet-based technique to predict treatment outcome for Major Depressive Disorder
Share
Study at a glance
- Area
- Depression & Mood
- Study type
- Observational study
- Authors
- Mumtaz W, Xia L, Mohd Yasin MA, Azhar Ali SS, Malik AS
- Journal
- PLOS ONE
- Year
- 2017
- Participants
- 64 (34 MDD, 30 controls)
- Population
- Adults
- Protocol
- Pretreatment EEG with wavelet analysis
- Equipment
- BrainMaster Discovery
Key findings
- 87.5% accuracy, 95% sensitivity, 80% specificity
- Frontal and temporal delta and theta features were most predictive
A machine-learning study using pretreatment EEG to predict which patients with major depression would respond to SSRI antidepressants. Wavelet features from frontal and temporal delta and theta activity predicted outcome with about 88% accuracy, better than other time-frequency methods.