Abstract
Predicting treatment response for major depressive disorder can provide a tremendous benefit for our overstretched health care system by reducing number of treatments and time to remission, thereby decreasing morbidity. The present study used neural and performance predictors during a cognitive control task to predict treatment response (% change in Hamilton Depression Rating Scale pre- to post-treatment). Forty-nine individuals diagnosed with major depressive disorder were enrolled with intent to treat in the open-label study; 36 completed treatment, had useable data, and were included in most data analyses. Participants included in the data analysis sample received treatment with escitalopram (n = 22) or duloxetine (n = 14) for 10 weeks. Functional MRI and performance during a Parametric Go/No-go test were used to predict per cent reduction in Hamilton Depression Rating Scale scores after treatment. Haemodynamic response function-based contrasts and task-related independent components analysis (subset of sample: n= 29) were predictors. Independent components analysis component beta weights and haemodynamic response function modelling activation during Commission errors in the rostral and dorsal anterior cingulate, mid-cingulate, dorsomedial prefrontal cortex, and lateral orbital frontal cortex predicted treatment response. In addition, more commission errors on the task predicted better treatment response. Together in a regression model, independent component analysis, haemodynamic response function-modelled, and performance measures predicted treatment response with 90% accuracy (compared to 74% accuracy with clinical features alone), with 84% accuracy in 5-fold, leave-one-out cross-validation. Convergence between performance markers and functional magnetic resonance imaging, including novel independent component analysis techniques, achieved high accuracy in prediction of treatment response for major depressive disorder. The strong link to a task paradigm provided by use of independent component analysis is a potential breakthrough that can inform ways in which prediction models can be integrated for use in clinical and experimental medicine studies.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 472-486 |
| Number of pages | 15 |
| Journal | Brain |
| Volume | 140 |
| Issue number | 2 |
| DOIs | |
| State | Published - Feb 2017 |
Funding
We thank Forest Pharmaceuticals for the escitalopram (Lexapro) provided for treatment of 19 MDD participants. The remaining escitalopram and duloxetine was provided by the Michigan Clinical Research Center. Forest Pharmaceuticals had no other role in the design, execution, analysis, or preparation of this manuscript. There are no other potential or real conflicts of interest. We thank research assistants who were instrumental in the recruitment of participants and collection of this data, including Kortni K. Meyers and Kathleen E. Hazlett. We thank graduate assistants and postdoctoral fellows who aided in diagnostic interviews and data collection, including Michael L. Brinkman, Michael T. Ransom, Sara J. Walker, and Erica L. Dawson, and Virginia Murphy, R.N., who assisted in recruitment, diagnosis and treatment. We thank the University of Michigan fMRI Laboratory for Assistance in data quality and collection of functional MRI images, and the Michigan Clinical Research Unit staff (MO1 RR00042) for assistance in completion of physical examinations. This publication was funded by the Brain and Behavior Research Foundation (NARSAD award to SAL) and the National Institute of Mental Health (NIMH) (R01MH050030, PI: JKZ; P01MH042251, PI: JKZ; and K23MH074459, PI: SAL). Its contents are solely the responsibility of the authors and do not necessarily represent the official views of NIMH or the National Institutes of Health.
Keywords
- Duloxetine
- Escitalopram
- Functional MRI
- Independent components analysis
- Major depressive disorder
ASJC Scopus subject areas
- General Medicine