Brain Predictability Toolbox

Résumé fourni par la source

Abstract The Brain Predictability toolbox (BPt) is a Python-based library with a unified framework of machine learning (ML) tools designed to work with both tabulated data (e.g., brain-derived, psychiatric, behavioral, and physiological variables) and neuroimaging specific data (e.g., brain volumes and surfaces). The toolbox is designed primarily for ‘population’-based predictive neuroimaging; that is to say, machine learning performed across data from multiple participants rather than many data points from a single or small set of participants. The BPt package is suitable for investigating a wide range of neuroimaging-based ML questions. This chapter is a brief introduction to general principles of the toolbox, followed by a specific example of usage.