Suppressed activity of the rostral anterior cingulate cortex as a biomarker for depression remission.

Christopher G Davey,Alec Jamieson,Micah Cearns,Ben J Harrison

doi:10.1017/s0033291721004323

Christopher G Davey, Alec Jamieson + Show 2 more

Open Access

https://doi.org/10.1017/s0033291721004323

Copy DOI

Abstract

Suppression of the rostral anterior cingulate cortex (rACC) has shown promise as a prognostic biomarker for depression. We aimed to use machine learning to characterise its ability to predict depression remission. Data were obtained from 81 15- to 25-year-olds with a major depressive disorder who had participated in the YoDA-C trial, in which they had been randomised to receive cognitive behavioural therapy plus either fluoxetine or placebo. Prior to commencing treatment patients performed a functional magnetic resonance imaging (fMRI) task to assess rACC suppression. Support vector machines were trained on the fMRI data using nested cross-validation, and were similarly trained on clinical data. We further tested our fMRI model on data from the YoDA-A trial, in which participants had completed the same fMRI paradigm. Thirty-six of 81 (44%) participants in the YoDA-C trial achieved remission. Our fMRI model was able to predict remission status (AUC = 0.777 [95% confidence interval (CI) 0.638-0.916], balanced accuracy = 67%, negative predictive value = 74%, p < 0.0001). Clinical models failed to predict remission status at better than chance levels. Testing the model on the alternative YoDA-A dataset confirmed its ability to predict remission (AUC = 0.776, balanced accuracy = 64%, negative predictive value = 70%, p < 0.0001). We confirm that rACC activity acts as a prognostic biomarker for depression. The machine learning model can identify patients who are likely to have difficult-to-treat depression, which might direct the earlier provision of enhanced support and more intensive therapies.

Highlights

It is anticipated that brain imaging technologies will one day help the mental health clinician choose the treatment that is most likely to benefit the patient before them
Our hypothesis was that weaker suppression of the rostral anterior cingulate cortex (rACC) during task performance would predict failure to remit to treatment at the individual level, irrespective of which of the five treatments the participant had received across the two trials
The support vector machine (SVM) for the functional magnetic resonance imaging (fMRI) model of rACC activity suppression achieved a moderate and statistically significant level of outer cross-validated accuracy [test area under the curve (AUC) = 0.777, p =

Summary

Introduction

It is anticipated that brain imaging technologies will one day help the mental health clinician choose the treatment that is most likely to benefit the patient before them. Prognostic biomarker status of rACC activity (i.e. whether it predicts response to a particular treatment or the overall likelihood of improvement) This can only occur in studies that include multiple treatments, and preferably where participants have been randomised to them. Our hypothesis was that weaker suppression of the rACC during task performance would predict failure to remit to treatment at the individual level, irrespective of which of the five treatments the participant had received across the two trials. We anticipated that this ability to predict outcome using brain imaging data would be superior to prediction using only clinical and behavioural variables. Our aim was to characterise the performance of rACC activity suppression as a prognostic biomarker, and to determine whether its accuracy was sufficient for clinical utility

Participants

Results

Discussion