Causal and anti-causal learning in pattern recognition for neuroimaging

TL;DR

This paper emphasizes the importance of causal inference in neuroimaging pattern recognition, arguing that distinguishing between causal and anti-causal features enhances interpretability beyond traditional encoding and decoding models.

Contribution

It introduces a theoretical framework linking causal inference to neuroimaging models, highlighting the limitations of existing encoding-decoding distinctions.

Findings

Causal and anti-causal features have different interpretative meanings.

Causal inference improves neuroimaging model interpretation.

Theoretical justification for causal considerations in neuroimaging analysis.

Abstract

Pattern recognition in neuroimaging distinguishes between two types of models: encoding- and decoding models. This distinction is based on the insight that brain state features, that are found to be relevant in an experimental paradigm, carry a different meaning in encoding- than in decoding models. In this paper, we argue that this distinction is not sufficient: Relevant features in encoding- and decoding models carry a different meaning depending on whether they represent causal- or anti-causal relations. We provide a theoretical justification for this argument and conclude that causal inference is essential for interpretation in neuroimaging.