Limits of decoding mental states with fMRI

Rami Jabakhanji, Andrew D. Vigotsky, Jannis Bielefeld, Lejian Huang, Marwan N. Baliki, Giandomenico Iannetti, A. Vania Apkarian*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

A growing number of studies claim to decode mental states using multi-voxel decoders of brain activity. It has been proposed that the fixed, fine-grained, multi-voxel patterns in these decoders are necessary for discriminating between and identifying mental states. Here, we present evidence that the efficacy of these decoders might be overstated. Across various tasks, decoder patterns were spatially imprecise, as decoder performance was unaffected by spatial smoothing; 90% redundant, as selecting a random 10% of a decoder's constituent voxels recovered full decoder performance; and performed similarly to brain activity maps used as decoders. We distinguish decoder performance in discriminating between mental states from performance in identifying a given mental state, and show that even when discrimination performance is adequate, identification can be poor. Finally, we demonstrate that simple and intuitive similarity metrics explain 91% and 62% of discrimination performance within- and across-subjects, respectively. These findings indicate that currently used across-subject decoders of mental states are superfluous and inappropriate for decision-making.

Original languageEnglish (US)
Pages (from-to)101-122
Number of pages22
JournalCortex
Volume149
DOIs
StatePublished - Apr 2022

Keywords

  • Cognitive neuroscience
  • Decoding
  • Mental states
  • Multivoxel pattern analysis

ASJC Scopus subject areas

  • Neuropsychology and Physiological Psychology
  • Experimental and Cognitive Psychology
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Limits of decoding mental states with fMRI'. Together they form a unique fingerprint.

Cite this