Header

UZH-Logo

Maintenance Infos

Computational neuroimaging strategies for single patient predictions


Stephan, K E; Schlagenhauf, F; Huys, Q J M; Raman, S; Aponte, E A; Brodersen, K H; Rigoux, L; Moran, R J; Daunizeau, J; Dolan, R J; Friston, K J; Heinz, A (2017). Computational neuroimaging strategies for single patient predictions. NeuroImage, 145(B):180-199.

Abstract

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.

Abstract

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.

Statistics

Citations

Dimensions.ai Metrics
93 citations in Web of Science®
101 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

140 downloads since deposited on 20 Jun 2017
7 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > Institute of Biomedical Engineering
Dewey Decimal Classification:170 Ethics
610 Medicine & health
Scopus Subject Areas:Life Sciences > Neurology
Life Sciences > Cognitive Neuroscience
Language:English
Date:January 2017
Deposited On:20 Jun 2017 06:31
Last Modified:26 Jan 2022 12:35
Publisher:Elsevier
ISSN:1053-8119
OA Status:Hybrid
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1016/j.neuroimage.2016.06.038
PubMed ID:27346545
  • Content: Published Version
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)