Computational neuroimaging strategies for single patient predictions

K E Stephan, F Schlagenhauf, Q J M Huys, S Raman, E A Aponte, K H Brodersen, L Rigoux, R J Moran, J Daunizeau, R J Dolan, K J Friston, A Heinz

Research output: Contribution to journalArticle (Academic Journal)peer-review

105 Citations (Scopus)
480 Downloads (Pure)


Neuroimaging increasingly exploits machine learning techniques in an attempt to achieve clinically relevant single-subject predictions. An alternative to machine learning, which tries to establish predictive links between features of the observed data and clinical variables, is the deployment of computational models for inferring on the (patho)physiological and cognitive mechanisms that generate behavioural and neuroimaging responses. This paper discusses the rationale behind a computational approach to neuroimaging-based single-subject inference, focusing on its potential for characterising disease mechanisms in individual subjects and mapping these characterisations to clinical predictions. Following an overview of two main approaches - Bayesian model selection and generative embedding - which can link computational models to individual predictions, we review how these methods accommodate heterogeneity in psychiatric and neurological spectrum disorders, help avoid erroneous interpretations of neuroimaging data, and establish a link between a mechanistic, model-based approach and the statistical perspectives afforded by machine learning.

Original languageEnglish
Pages (from-to)180-199
Number of pages20
Issue numberB
Publication statusPublished - 22 Jun 2016


  • Generative model
  • fMRI
  • EEG
  • Bayesian
  • Model selection
  • Model comparison
  • Model evidence
  • Generative embedding
  • Classification
  • Clustering
  • Computational psychiatry
  • Translational neuromodeling


Dive into the research topics of 'Computational neuroimaging strategies for single patient predictions'. Together they form a unique fingerprint.

Cite this