SMRI Biomarkers Predict Electroconvulsive Treatment Outcomes: Accuracy with Independent Data Sets

Neuropsychopharmacology. 2018 Apr;43(5):1078-1087. doi: 10.1038/npp.2017.165. Epub 2017 Jul 31.


Owing to the rapid and robust clinical effects, electroconvulsive therapy (ECT) represents an optimal model to develop and test treatment predictors for major depressive disorders (MDDs), whereas imaging markers can be informative in identifying MDD patients who will respond to a specific antidepressant treatment or not. Here we aim to predict post-ECT depressive rating changes and remission status using pre-ECT gray matter (GM) in 38 MDD patients and validate in two independent data sets. Six GM regions including the right hippocampus/parahippocampus, right orbitofrontal gyrus, right inferior temporal gyrus (ITG), left postcentral gyrus/precuneus, left supplementary motor area, and left lingual gyrus were identified as predictors of ECT response, achieving accuracy of 89, 90 and 86% for remission prediction in three independent, age-matched data sets, respectively. For MDD patients, GM density increases only in the left supplementary motor cortex and left postcentral gyrus/precuneus after ECT. These results suggest that treatment-predictive and treatment-responsive regions may be anatomically different but functionally related in the context of ECT response. To the best of our knowledge, this is the first attempt to quantitatively identify and validate the ECT treatment biomarkers using multi-site GM data. We address a major clinical challenge and provide potential opportunities for more effective and timely interventions for electroconvulsive treatment.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't
  • Validation Study

MeSH terms

  • Adult
  • Aged
  • Aged, 80 and over
  • Biomarkers
  • Datasets as Topic*
  • Depressive Disorder, Major / diagnostic imaging*
  • Electroconvulsive Therapy*
  • Female
  • Gray Matter / diagnostic imaging*
  • Humans
  • Hypertrophy / diagnostic imaging*
  • Magnetic Resonance Imaging
  • Male
  • Middle Aged
  • Neuroimaging
  • Predictive Value of Tests*
  • Treatment Outcome


  • Biomarkers