Skip to main navigation Skip to search Skip to main content

Personalized prediction of transcranial magnetic stimulation clinical response in patients with treatment-refractory depression using neuroimaging biomarkers and machine learning

  • H.J. Hopman*
  • , S.M.S. Chan
  • , W.C.W. Chu
  • , H. Lu
  • , C.-Y. Tse
  • , S.W.H. Chau
  • , L.C.W. Lam
  • , A.D.P. Mak
  • , S.F.W. Neggers
  • *Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

Abstract

Background: Functional connectivity between the left dorsolateral prefrontal cortex (DLPFC) and subgenual cingulate (sgACC) may serve as a biomarker for transcranial magnetic stimulation (rTMS) treatment response. The first aim was to establish whether this finding is veridical or artifactually induced by the pre-processing method. Furthermore, alternative biomarkers were identified and the clinical utility for personalized medicine was examined. 
Methods: Resting-state fMRI data were collected in medication-refractory depressed patients (n = 70, 16 males) before undergoing neuronavigated left DLPFC rTMS. Seed-based analyses were performed with and without global signal regression pre-processing to identify biomarkers of short-term and long-term treatment response. Receiver Operating Characteristic curve and supervised machine learning analyses were applied to assess the clinical utility of these biomarkers for the classification of categorical rTMS response. 
Results: Regardless of the pre-processing method, DLPFC-sgACC connectivity was not associated with treatment outcome. Instead, poorer connectivity between the sgACC and three clusters (peak locations: frontal pole, superior parietal lobule, occipital cortex) and DLPFC-central opercular cortex were observed in long-term nonresponders. The identified connections could serve as acceptable to excellent markers. Combining the features using supervised machine learning reached accuracy rates of 95.35% (CI=82.94–100.00) and 88.89% (CI=63.96–100.00) in the cross-validation and test dataset, respectively. 
Limitations: The sample size was moderate, and features for machine learning were based on group differences. 
Conclusions: Long-term nonresponders showed greater disrupted connectivity in regions involving the central executive network. Our findings may aid the development of personalized medicine for medication-refractory depression.
Original languageEnglish
Pages (from-to)261-271
JournalJournal of Affective Disorders
Volume290
Online published16 May 2021
DOIs
Publication statusPublished - 1 Jul 2021

Research Keywords

  • Biomarkers
  • Depression
  • Dorsolateral prefrontal cortex
  • Subgenual anterior cingulate cortex
  • Transcranial magnetic stimulation
  • Treatment response

RGC Funding Information

  • RGC-funded

Policy Impact

  • Cited in Policy Documents

Fingerprint

Dive into the research topics of 'Personalized prediction of transcranial magnetic stimulation clinical response in patients with treatment-refractory depression using neuroimaging biomarkers and machine learning'. Together they form a unique fingerprint.

Cite this