Neuroimaging-based prediction of mental traits: Road to utopia or Orwell?

Abstract

Predicting individual mental traits and behavioral dispositions from brain imaging data through machine-learning approaches is becoming a rapidly evolving field in neuroscience. Beyond scientific and clinical applications, such approaches also hold the potential to gain substantial influence in fields such as human resource management, education, or criminal law. Although several challenges render real-life applications of such tools difficult, future conflicts of individual, economic, and public interests are preprogrammed, given the prospect of improved personalized predictions across many domains. In this Perspective paper, we thus argue for the need to engage in a discussion on the ethical, legal, and societal implications of the emergent possibilities for brain-based predictions and outline some of the aspects for this discourse.

Fig 1. Schematic sketch of a pipeline for building brain-based prediction models for individual traits.

To be read clockwise starting at the top left. Parcellated brain hemispheres (top right panel) reproduced from [7] under a CC BY 4.0 license (https://creativecommons.org/licenses/by/4.0/), depicting results reported in [8].