Predicting Pain Perception from fMRI Data

In study 1, we used a machine-learning–based regression technique, LASSO-PCR (least absolute shrinkage and selection operator-regularized principal components regression),^{10 (link)} to predict pain reports from the fMRI activity. We selected relevant brain areas a priori using the NeuroSynth meta-analytic databasei^{11 (link)} (see the Supplementary Appendix) and averaged the brain activity for each intensity level within each participant.^{12 (link)–14 (link)} We used the signal values from the voxels, each of which measured 3 mm³, in the a priori map to predict continuous pain ratings, using leave-one-participant-out cross-validation⁴ (see the Supplementary Appendix). The result was a spatial pattern of regression weights across brain regions, which was prospectively applied to fMRI activity maps obtained from new participants. Application of the signature to an activity map (e.g., a map obtained during thermal stimulation) yielded a scalar response value, which constituted the predicted pain for that condition.
We used permutation tests to obtain unbiased estimates of accuracy and bootstrap tests to determine which brain areas made reliable contributions to prediction (Fig. 1). Stimulation did not elicit head movement, and head-movement estimates did not predict pain (for a description of head-movement analyses, see the Supplementary Appendix).