Literature DB >> 27141854

A hierarchical model for integrating unsupervised generative embedding and empirical Bayes.

Sudhir Raman1, Lorenz Deserno2, Florian Schlagenhauf3, Klaas Enno Stephan4.   

Abstract

BACKGROUND: Generative models of neuroimaging data, such as dynamic causal models (DCMs), are commonly used for inferring effective connectivity from individual subject data. Recently introduced "generative embedding" approaches have used DCM-based connectivity parameters for supervised classification of individual patients or to find unknown subgroups in heterogeneous groups using unsupervised clustering methods. NEW
METHOD: We present a novel framework which combines DCMs with finite mixture models into a single hierarchical model. This approach unifies the inference of connectivity parameters in individual subjects with inference on population structure, i.e. the existence of subgroups defined by model parameters, and allows for empirical Bayesian estimates of a subject's connectivity based on subgroup-specific prior distributions. We introduce a Markov chain Monte Carlo sampling method for inversion of this hierarchical generative model.
RESULTS: This paper formally introduces the idea behind our novel concept and demonstrates the face validity of the model in application to both simulated data as well as an empirical fMRI dataset from healthy controls and patients with schizophrenia. COMPARISON WITH EXISTING METHOD(S): The analysis of our empirical fMRI data demonstrates that our approach results in superior model evidence than the conventional non-hierarchical inversion of DCMs.
CONCLUSIONS: In this paper, we have presented a novel unified framework to jointly infer the effective connectivity parameters in DCMs for multiple subjects and, at the same time, discover connectivity-defined cluster structure of the whole population, using a mixture model approach.
Copyright © 2016 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Clustering; DCM; Dynamic causal modelling; MCMC; Markov chain Monte Carlo sampling; Mixture model; Psychiatric spectrum diseases; Schizophrenia

Mesh:

Year:  2016        PMID: 27141854     DOI: 10.1016/j.jneumeth.2016.04.022

Source DB:  PubMed          Journal:  J Neurosci Methods        ISSN: 0165-0270            Impact factor:   2.390


  6 in total

1.  Markov chain Monte Carlo methods for hierarchical clustering of dynamic causal models.

Authors:  Yu Yao; Klaas E Stephan
Journal:  Hum Brain Mapp       Date:  2021-04-07       Impact factor: 5.038

2.  Allostatic Self-efficacy: A Metacognitive Theory of Dyshomeostasis-Induced Fatigue and Depression.

Authors:  Klaas E Stephan; Zina M Manjaly; Christoph D Mathys; Lilian A E Weber; Saee Paliwal; Tim Gard; Marc Tittgemeyer; Stephen M Fleming; Helene Haker; Anil K Seth; Frederike H Petzschner
Journal:  Front Hum Neurosci       Date:  2016-11-15       Impact factor: 3.169

3.  Hierarchical Bayesian inference for concurrent model fitting and comparison for group studies.

Authors:  Payam Piray; Amir Dezfouli; Tom Heskes; Michael J Frank; Nathaniel D Daw
Journal:  PLoS Comput Biol       Date:  2019-06-18       Impact factor: 4.475

4.  A guide to group effective connectivity analysis, part 2: Second level analysis with PEB.

Authors:  Peter Zeidman; Amirhossein Jafarian; Mohamed L Seghier; Vladimir Litvak; Hayriye Cagnan; Cathy J Price; Karl J Friston
Journal:  Neuroimage       Date:  2019-06-18       Impact factor: 6.556

Review 5.  TAPAS: An Open-Source Software Package for Translational Neuromodeling and Computational Psychiatry.

Authors:  Stefan Frässle; Eduardo A Aponte; Saskia Bollmann; Kay H Brodersen; Cao T Do; Olivia K Harrison; Samuel J Harrison; Jakob Heinzle; Sandra Iglesias; Lars Kasper; Ekaterina I Lomakina; Christoph Mathys; Matthias Müller-Schrader; Inês Pereira; Frederike H Petzschner; Sudhir Raman; Dario Schöbi; Birte Toussaint; Lilian A Weber; Yu Yao; Klaas E Stephan
Journal:  Front Psychiatry       Date:  2021-06-02       Impact factor: 4.157

Review 6.  An introduction to thermodynamic integration and application to dynamic causal models.

Authors:  Eduardo A Aponte; Yu Yao; Sudhir Raman; Stefan Frässle; Jakob Heinzle; Will D Penny; Klaas E Stephan
Journal:  Cogn Neurodyn       Date:  2021-07-25       Impact factor: 5.082

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.