Classifying the Valence of Autobiographical Memories from fMRI Data

TL;DR

This study demonstrates that machine learning applied to fMRI data can reliably classify the emotional valence of autobiographical memories across different individuals, with high accuracy and neurophysiologically relevant brain regions.

Contribution

It introduces a feature selection and boosting pipeline that improves cross-participant classification accuracy and identifies brain regions involved in memory valence.

Findings

81% accuracy within participants

62% accuracy across participants

Brain regions align with neurophysiological theories

Abstract

We show that fMRI analysis using machine learning tools are sufficient to distinguish valence (i.e., positive or negative) of freely retrieved autobiographical memories in a cross-participant setting. Our methodology uses feature selection (ReliefF) in combination with boosting methods, both applied directly to data represented in voxel space. In previous work using the same data set, Nawa and Ando showed that whole-brain based classification could achieve above-chance classification accuracy only when both training and testing data came from the same individual. In a cross-participant setting, classification results were not statistically significant. Additionally, on average the classification accuracy obtained when using ReliefF is substantially higher than previous results - 81% for the within-participant classification, and 62% for the cross-participant classification. Furthermore, since features are defined in voxel space, it is possible to show brain maps indicating the regions of that are most relevant in determining the results of the classification. Interestingly, the voxels that were selected using the proposed computational pipeline seem to be consistent with current neurophysiological theories regarding the brain regions actively involved in autobiographical memory processes.