Hostname: page-component-cd9895bd7-gvvz8 Total loading time: 0 Render date: 2024-12-25T06:09:37.863Z Has data issue: false hasContentIssue false

Using Multimodal MRI Data to Classify Patients with First Episode Psychosis

Published online by Cambridge University Press:  15 April 2020

P. Brambilla
Affiliation:
Psychiatry, Udine Hospital, Udine, Italy
P. Denis
Affiliation:
neuroimaging, irccs e medea, bosisio parini, Italy
C. Umberto
Affiliation:
informatics, university of verona, verona, Italy
P. Cinzia
Affiliation:
psychiatry, university of verona, verona, Italy
B. Marcella
Affiliation:
psychiatry, university of verona, verona, Italy
M. Veronica
Affiliation:
psychiatry, university of verona, verona, Italy
R. Gianluca
Affiliation:
psychiatry, university of verona, verona, Italy
L. Antonio
Affiliation:
psychiatry, university of verona, verona, Italy
T. Sarah
Affiliation:
psychiatry, university of verona, verona, Italy
D. Katia
Affiliation:
psychiatry, university of verona, verona, Italy
M. Vittorio
Affiliation:
informatics, university of verona, verona, Italy
R. Mirella
Affiliation:
psychiatry, university of verona, verona, Italy

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.
Introduction

currently, most of the classification studies of psychosis focused on chronic patients and employed single machine learning approaches. To overcome these limitations, we here compare, to our best knowledge for the first time, different classification methods of First Episode Psychosis (FEP) using multimodal imaging data exploited on several cortical and subcortical structures and white matter fiber bundles.

Methods

23 FEP patients and 23 age-, gender-, and race-matched healthy participants were included in the study. An innovative multivariate approach based on Multiple Kernel Learning (MKL) methods was implemented on structural MRI (sMRI) and diffusion tensor imaging (DTI).

Results

MKL provides the best classification performances in comparison with the more widely used Support Vector Machine, enabling the definition of a reliable automatic decisional system based on the integration of multimodal imaging information. Our results show a discrimination accuracy greater than 90% between healthy subjects and patients with FEP. Regions with an accuracy greater than 70% on different imaging sources and measures were middle and superior frontal gyrus, parahippocampal gyrus, uncinate fascicles and cingulum.

Conclusions

this study shows that multivariate machine learning approaches integrating multimodal and multisource imaging data can classify FEP patients with high accuracy. Interestingly, specific grey matter structures and white matter bundles reach high classification reliability when using different imaging modalities and indices, potentially outlining a prefronto-limbic network impaired in FEP with particular regard to the right hemisphere.

Type
Article: 0054
Copyright
Copyright © European Psychiatric Association 2015
Submit a response

Comments

No Comments have been published for this article.