Since MTPA selects a subset of timepoints, we can map those back onto the stimulus to reverse-engineer which elements evoked predictive neural patterns. Features predicting overwhelm aligned with emotional moments, while predicting need for a new/different challenge aligned with social moments. 6/8

One of my fav parts of the study was developing Multi-Timepoint Pattern Analysis (MTPA). MTPA can be viewed as a temporal analog to MVPA, but instead of a spatial searchlight it uses a “temporal searchlight” to select a subset of features. Check out another recent paper for more: bit.ly/4qeUEBq. 5/8

We scanned business executives’ brains as they watched a video of others discussing their attitudes toward work. ML models were able to predict who felt overwhelmed using the TPJ and who was in need of a new/different challenge in their career using the dmPFC with ~73-79% accuracy. 3/8

Excited to share our new paper out in PNAS: “Neural predictors of hidden, persistent psychological states at work.” Full paper at bit.ly/47oaGRR

We brought portable fNIRS into the field to predict the subjective work-related “lenses” of business leaders. Check out the thread below for more! 1/8