Brain texture as a marker of transdiagnostic clinical profiles in patients with recent-onset psychosis and depression

the PRONIA consortium

doi:10.1038/s44220-023-00168-z

Brain texture as a marker of transdiagnostic clinical profiles in patients with recent-onset psychosis and depression

the PRONIA consortium

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

The inter-relationships of voxels can be captured by the radiomics texture features across multiple spatial scales. Prediction models of brain texture changes captured by the contrast texture feature in recent-onset psychosis (ROP) and recent-onset depression (ROD) have recently been proposed, although the validation of these models transdiagnostically at the individual level and the investigation of the variability in clinical profiles are lacking. Established prevention and treatment approaches focus on specific diagnoses and do not address the heterogeneity and manifold potential outcomes of patients. Here we aimed to investigate the cross-sectional utility of brain texture changes for (1) identification of the psychopathological state (ROP and ROD) and (2) the association of individualized brain texture maps with clinical symptom severity and outcome profiles. We developed transdiagnostic models based on structural magnetic resonance imaging data for 116 patients with ROD, 122 patients with ROP and 197 healthy control participants from the PRONIA (Personalized pROgNostic tools for early psychosIs mAnagement) study by applying a set of tools and frameworks to explain the classification decisions of the deep-learning algorithm (named explainable artificial intelligence) and clustering analysis. We investigated the contrast texture feature as the key feature for the identification of a general psychopathological state. The discrimination power of the trained prediction model was >72% and was validated in a second independent age- and sex-matched sample of 137 ROP, 94 ROD and 159 healthy control participants. Clustering analysis was implemented to map the changes in texture brain produced from an explainable artificial intelligence algorithm, in a group fashion. The explained individualized brain contrast map grouped into eight homogeneous clusters. In the clinical group, we investigated the association between the explained brain contrast texture map and clinical symptom severity as well as outcome profiles. Different patterns in the explained brain contrast texture map showed unique associations of brain alterations with clinical symptom severity and clinical outcomes, that is, age, positive, negative and depressive symptoms, and functionality. In some clusters, the mean explained brain contrast texture map values and/or brain contrast texture voxels that contributed significantly to the classification decision predicted accurately the PANSS (positive and negative symptom scale) scores, functionality and change in functionality over time. In conclusion, we created homogeneous clusters which predict the clinical severity and outcome profile in ROP and ROD patients.

Original language	English
Article number	106
Pages (from-to)	76-87
Number of pages	12
Journal	Nature Mental Health
Volume	2
Issue number	1
DOIs	https://doi.org/10.1038/s44220-023-00168-z
Publication status	Published - Jan 2024

Access to Document

10.1038/s44220-023-00168-z

Cite this

@article{a9c48fc64cb0470db45fdae4edac7a27,

title = "Brain texture as a marker of transdiagnostic clinical profiles in patients with recent-onset psychosis and depression",

abstract = "The inter-relationships of voxels can be captured by the radiomics texture features across multiple spatial scales. Prediction models of brain texture changes captured by the contrast texture feature in recent-onset psychosis (ROP) and recent-onset depression (ROD) have recently been proposed, although the validation of these models transdiagnostically at the individual level and the investigation of the variability in clinical profiles are lacking. Established prevention and treatment approaches focus on specific diagnoses and do not address the heterogeneity and manifold potential outcomes of patients. Here we aimed to investigate the cross-sectional utility of brain texture changes for (1) identification of the psychopathological state (ROP and ROD) and (2) the association of individualized brain texture maps with clinical symptom severity and outcome profiles. We developed transdiagnostic models based on structural magnetic resonance imaging data for 116 patients with ROD, 122 patients with ROP and 197 healthy control participants from the PRONIA (Personalized pROgNostic tools for early psychosIs mAnagement) study by applying a set of tools and frameworks to explain the classification decisions of the deep-learning algorithm (named explainable artificial intelligence) and clustering analysis. We investigated the contrast texture feature as the key feature for the identification of a general psychopathological state. The discrimination power of the trained prediction model was >72% and was validated in a second independent age- and sex-matched sample of 137 ROP, 94 ROD and 159 healthy control participants. Clustering analysis was implemented to map the changes in texture brain produced from an explainable artificial intelligence algorithm, in a group fashion. The explained individualized brain contrast map grouped into eight homogeneous clusters. In the clinical group, we investigated the association between the explained brain contrast texture map and clinical symptom severity as well as outcome profiles. Different patterns in the explained brain contrast texture map showed unique associations of brain alterations with clinical symptom severity and clinical outcomes, that is, age, positive, negative and depressive symptoms, and functionality. In some clusters, the mean explained brain contrast texture map values and/or brain contrast texture voxels that contributed significantly to the classification decision predicted accurately the PANSS (positive and negative symptom scale) scores, functionality and change in functionality over time. In conclusion, we created homogeneous clusters which predict the clinical severity and outcome profile in ROP and ROD patients.",

author = "{the PRONIA consortium} and Korda, {Alexandra I.} and Christina Andreou and Anne Ruef and Lisa Hahn and Andr{\'e} Schmidt and Udo Dannlowski and Lana Kambeitz-Ilankovic and Dwyer, {Dominic B.} and Joseph Kambeitz and Julian Wenzel and Stephan Ruhrmann and Wood, {Stephen J.} and Salokangas, {Raimo K.R.} and Christos Pantelis and Frauke Schultze-Lutter and Eva Meisenzahl and Paolo Brambilla and Pierluigi Selvaggi and Alessandro Bertolino and Jarmo Hietala and Rachel Upthegrove and Lalousis, {Paris Alexandros} and Anita Riecher-R{\"o}ssler and Christos Davatzikos and Rebekka Lencer and Nikolaos Koutsouleris and Stefan Borgwardt",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2024",

month = jan,

doi = "10.1038/s44220-023-00168-z",

language = "English",

volume = "2",

pages = "76--87",

journal = "Nature Mental Health ",

issn = "2731-6076",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - Brain texture as a marker of transdiagnostic clinical profiles in patients with recent-onset psychosis and depression

AU - the PRONIA consortium

AU - Korda, Alexandra I.

AU - Andreou, Christina

AU - Ruef, Anne

AU - Hahn, Lisa

AU - Schmidt, André

AU - Dannlowski, Udo

AU - Kambeitz-Ilankovic, Lana

AU - Dwyer, Dominic B.

AU - Kambeitz, Joseph

AU - Wenzel, Julian

AU - Ruhrmann, Stephan

AU - Wood, Stephen J.

AU - Salokangas, Raimo K.R.

AU - Pantelis, Christos

AU - Schultze-Lutter, Frauke

AU - Meisenzahl, Eva

AU - Brambilla, Paolo

AU - Selvaggi, Pierluigi

AU - Bertolino, Alessandro

AU - Hietala, Jarmo

AU - Upthegrove, Rachel

AU - Lalousis, Paris Alexandros

AU - Riecher-Rössler, Anita

AU - Davatzikos, Christos

AU - Lencer, Rebekka

AU - Koutsouleris, Nikolaos

AU - Borgwardt, Stefan

PY - 2024/1

Y1 - 2024/1

N2 - The inter-relationships of voxels can be captured by the radiomics texture features across multiple spatial scales. Prediction models of brain texture changes captured by the contrast texture feature in recent-onset psychosis (ROP) and recent-onset depression (ROD) have recently been proposed, although the validation of these models transdiagnostically at the individual level and the investigation of the variability in clinical profiles are lacking. Established prevention and treatment approaches focus on specific diagnoses and do not address the heterogeneity and manifold potential outcomes of patients. Here we aimed to investigate the cross-sectional utility of brain texture changes for (1) identification of the psychopathological state (ROP and ROD) and (2) the association of individualized brain texture maps with clinical symptom severity and outcome profiles. We developed transdiagnostic models based on structural magnetic resonance imaging data for 116 patients with ROD, 122 patients with ROP and 197 healthy control participants from the PRONIA (Personalized pROgNostic tools for early psychosIs mAnagement) study by applying a set of tools and frameworks to explain the classification decisions of the deep-learning algorithm (named explainable artificial intelligence) and clustering analysis. We investigated the contrast texture feature as the key feature for the identification of a general psychopathological state. The discrimination power of the trained prediction model was >72% and was validated in a second independent age- and sex-matched sample of 137 ROP, 94 ROD and 159 healthy control participants. Clustering analysis was implemented to map the changes in texture brain produced from an explainable artificial intelligence algorithm, in a group fashion. The explained individualized brain contrast map grouped into eight homogeneous clusters. In the clinical group, we investigated the association between the explained brain contrast texture map and clinical symptom severity as well as outcome profiles. Different patterns in the explained brain contrast texture map showed unique associations of brain alterations with clinical symptom severity and clinical outcomes, that is, age, positive, negative and depressive symptoms, and functionality. In some clusters, the mean explained brain contrast texture map values and/or brain contrast texture voxels that contributed significantly to the classification decision predicted accurately the PANSS (positive and negative symptom scale) scores, functionality and change in functionality over time. In conclusion, we created homogeneous clusters which predict the clinical severity and outcome profile in ROP and ROD patients.

AB - The inter-relationships of voxels can be captured by the radiomics texture features across multiple spatial scales. Prediction models of brain texture changes captured by the contrast texture feature in recent-onset psychosis (ROP) and recent-onset depression (ROD) have recently been proposed, although the validation of these models transdiagnostically at the individual level and the investigation of the variability in clinical profiles are lacking. Established prevention and treatment approaches focus on specific diagnoses and do not address the heterogeneity and manifold potential outcomes of patients. Here we aimed to investigate the cross-sectional utility of brain texture changes for (1) identification of the psychopathological state (ROP and ROD) and (2) the association of individualized brain texture maps with clinical symptom severity and outcome profiles. We developed transdiagnostic models based on structural magnetic resonance imaging data for 116 patients with ROD, 122 patients with ROP and 197 healthy control participants from the PRONIA (Personalized pROgNostic tools for early psychosIs mAnagement) study by applying a set of tools and frameworks to explain the classification decisions of the deep-learning algorithm (named explainable artificial intelligence) and clustering analysis. We investigated the contrast texture feature as the key feature for the identification of a general psychopathological state. The discrimination power of the trained prediction model was >72% and was validated in a second independent age- and sex-matched sample of 137 ROP, 94 ROD and 159 healthy control participants. Clustering analysis was implemented to map the changes in texture brain produced from an explainable artificial intelligence algorithm, in a group fashion. The explained individualized brain contrast map grouped into eight homogeneous clusters. In the clinical group, we investigated the association between the explained brain contrast texture map and clinical symptom severity as well as outcome profiles. Different patterns in the explained brain contrast texture map showed unique associations of brain alterations with clinical symptom severity and clinical outcomes, that is, age, positive, negative and depressive symptoms, and functionality. In some clusters, the mean explained brain contrast texture map values and/or brain contrast texture voxels that contributed significantly to the classification decision predicted accurately the PANSS (positive and negative symptom scale) scores, functionality and change in functionality over time. In conclusion, we created homogeneous clusters which predict the clinical severity and outcome profile in ROP and ROD patients.

UR - http://www.scopus.com/inward/record.url?scp=85202974308&partnerID=8YFLogxK

U2 - 10.1038/s44220-023-00168-z

DO - 10.1038/s44220-023-00168-z

M3 - Article

AN - SCOPUS:85202974308

SN - 2731-6076

VL - 2

SP - 76

EP - 87

JO - Nature Mental Health

JF - Nature Mental Health

IS - 1

M1 - 106

ER -

Brain texture as a marker of transdiagnostic clinical profiles in patients with recent-onset psychosis and depression

Abstract

Access to Document

Other files and links

Fingerprint

Cite this