Group-regularized individual prediction: theory and application to pain

Martin A. Lindquist, Anjali Krishnan, Marina López-Solà, Marieke Jepma, Choong Wan Woo, Leonie Koban, Luke J. Chang, Elizabeth A. Reynolds Losin, Hedwig Eisenbarth, Yoni K. Ashar, Elizabeth Delk, Tor D. Wager, Mathieu Roy, Lauren Y. Atlas, Elizabeth A. Reynolds Losin, Anjali Krishnan, Liane Schmidt, Liane Schmidt

Research output: Contribution to journalArticle

23 Scopus citations

Abstract

Multivariate pattern analysis (MVPA) has become an important tool for identifying brain representations of psychological processes and clinical outcomes using fMRI and related methods. Such methods can be used to predict or ‘decode’ psychological states in individual subjects. Single-subject MVPA approaches, however, are limited by the amount and quality of individual-subject data. In spite of higher spatial resolution, predictive accuracy from single-subject data often does not exceed what can be accomplished using coarser, group-level maps, because single-subject patterns are trained on limited amounts of often-noisy data. Here, we present a method that combines population-level priors, in the form of biomarker patterns developed on prior samples, with single-subject MVPA maps to improve single-subject prediction. Theoretical results and simulations motivate a weighting based on the relative variances of biomarker-based prediction—based on population-level predictive maps from prior groups—and individual-subject, cross-validated prediction. Empirical results predicting pain using brain activity on a trial-by-trial basis (single-trial prediction) across 6 studies (N = 180 participants) confirm the theoretical predictions. Regularization based on a population-level biomarker—in this case, the Neurologic Pain Signature (NPS)—improved single-subject prediction accuracy compared with idiographic maps based on the individuals' data alone. The regularization scheme that we propose, which we term group-regularized individual prediction (GRIP), can be applied broadly to within-person MVPA-based prediction. We also show how GRIP can be used to evaluate data quality and provide benchmarks for the appropriateness of population-level maps like the NPS for a given individual or study.

Original languageEnglish (US)
Pages (from-to)274-287
Number of pages14
JournalNeuroImage
Volume145
DOIs
StatePublished - Jan 15 2017

Keywords

  • Empirical Bayes
  • MVPA
  • Machine learning
  • Mega-analysis
  • Meta-analysis
  • Pain
  • Prediction
  • Shrinkage
  • Statistical learning
  • fMRI

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Fingerprint Dive into the research topics of 'Group-regularized individual prediction: theory and application to pain'. Together they form a unique fingerprint.

  • Cite this

    Lindquist, M. A., Krishnan, A., López-Solà, M., Jepma, M., Woo, C. W., Koban, L., Chang, L. J., Reynolds Losin, E. A., Eisenbarth, H., Ashar, Y. K., Delk, E., Wager, T. D., Roy, M., Atlas, L. Y., Reynolds Losin, E. A., Krishnan, A., Schmidt, L., & Schmidt, L. (2017). Group-regularized individual prediction: theory and application to pain. NeuroImage, 145, 274-287. https://doi.org/10.1016/j.neuroimage.2015.10.074