Machine learning provides novel neurophysiological features that predict performance to inhibit automated responses.

Neurophysiological features like event-related potentials (ERPs) have long been used to identify different cognitive sub-processes that may contribute to task performance. It has however remained unclear whether "classical" ERPs are truly the best reflection or even causal to observable variations in behavior. Here, we used a data-driven strategy to extract features from neurophysiological data of n = 240 healthy young individuals who performed a Go/Nogo task and used machine learning methods in combination with source localization to identify the best predictors of inter-individual performance variations. Both Nogo-N2 and Nogo-P3 yielded predictions close to chance level, but a feature in between those two processes, associated with motor cortex activity (BA4), predicted group membership with up to ~68%. We further found two Nogo-associated features in the theta and alpha bands, that predicted behavioral performance with up to ~78%. Notably, the theta band feature contributed most to the prediction and occurred at the same time as the predictive ERP feature. Our approach provides a rigorous test for established neurophysiological correlates of response inhibition and suggests that other processes, which occur in between the Nogo-N2 and P3, might be of equal, if not even greater, importance.