Universität zu Köln

Antonucci, Linda A. ORCID: 0000-0002-7919-7402, Penzel, Nora, Sanfelici, Rachele, Pigoni, Alessandro ORCID: 0000-0002-9122-5656, Kambeitz-Ilankovic, Lana ORCID: 0000-0002-8218-0425, Dwyer, Dominic ORCID: 0000-0003-3949-5867, Ruef, Anne, Sen Dong, Mark, Ozturk, Omer Faruk ORCID: 0000-0003-3665-0526, Chisholm, Katharine ORCID: 0000-0002-0575-0789, Haidl, Theresa, Rosen, Marlene, Ferro, Adele, Pergola, Giulio, Andriola, Ileana, Blasi, Giuseppe, Ruhrmann, Stephan ORCID: 0000-0002-6022-2364, Schultze-Lutter, Frauke, Falkai, Peter, Kambeitz, Joseph, Lencer, Rebekka, Dannlowski, Udo, Upthegrove, Rachel ORCID: 0000-0001-8204-5103, Salokangas, Raimo K. R., Pantelis, Christos ORCID: 0000-0002-9565-0238, Meisenzahl, Eva, Wood, Stephen J., Brambilla, Paolo, Borgwardt, Stefan ORCID: 0000-0002-5792-3987, Bertolino, Alessandro and Koutsouleris, Nikolaos (2022). Using combined environmental-clinical classification models to predict role functioning outcome in clinical high-risk states for psychosis and recent-onset depression. Br. J. Psychiatry, 220 (4). S. 229 - 246. CAMBRIDGE: CAMBRIDGE UNIV PRESS. ISSN 1472-1465

Full text not available from this repository.

Abstract

Background Clinical high-risk states for psychosis (CHR) are associated with functional impairments and depressive disorders. A previous PRONIA study predicted social functioning in CHR and recent-onset depression (ROD) based on structural magnetic resonance imaging (sMRI) and clinical data. However, the combination of these domains did not lead to accurate role functioning prediction, calling for the investigation of additional risk dimensions. Role functioning may be more strongly associated with environmental adverse events than social functioning. Aims We aimed to predict role functioning in CHR, ROD and transdiagnostically, by adding environmental adverse events-related variables to clinical and sMRI data domains within the PRONIA sample. Method Baseline clinical, environmental and sMRI data collected in 92 CHR and 95 ROD samples were trained to predict lower versus higher follow-up role functioning, using support vector classification and mixed k-fold/leave-site-out cross-validation. We built separate predictions for each domain, created multimodal predictions and validated them in independent cohorts (74 CHR, 66 ROD). Results Models combining clinical and environmental data predicted role outcome in discovery and replication samples of CHR (balanced accuracies: 65.4% and 67.7%, respectively), ROD (balanced accuracies: 58.9% and 62.5%, respectively), and transdiagnostically (balanced accuracies: 62.4% and 68.2%, respectively). The most reliable environmental features for role outcome prediction were adult environmental adjustment, childhood trauma in CHR and childhood environmental adjustment in ROD. Conclusions Findings support the hypothesis that environmental variables inform role outcome prediction, highlight the existence of both transdiagnostic and syndrome-specific predictive environmental adverse events, and emphasise the importance of implementing real-world models by measuring multiple risk dimensions.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Antonucci, Linda A. UNSPECIFIED orcid.org/0000-0002-7919-7402 UNSPECIFIED Penzel, Nora UNSPECIFIED UNSPECIFIED UNSPECIFIED Sanfelici, Rachele UNSPECIFIED UNSPECIFIED UNSPECIFIED Pigoni, Alessandro UNSPECIFIED orcid.org/0000-0002-9122-5656 UNSPECIFIED Kambeitz-Ilankovic, Lana UNSPECIFIED orcid.org/0000-0002-8218-0425 UNSPECIFIED Dwyer, Dominic UNSPECIFIED orcid.org/0000-0003-3949-5867 UNSPECIFIED Ruef, Anne UNSPECIFIED UNSPECIFIED UNSPECIFIED Sen Dong, Mark UNSPECIFIED UNSPECIFIED UNSPECIFIED Ozturk, Omer Faruk UNSPECIFIED orcid.org/0000-0003-3665-0526 UNSPECIFIED Chisholm, Katharine UNSPECIFIED orcid.org/0000-0002-0575-0789 UNSPECIFIED Haidl, Theresa UNSPECIFIED UNSPECIFIED UNSPECIFIED Rosen, Marlene UNSPECIFIED UNSPECIFIED UNSPECIFIED Ferro, Adele UNSPECIFIED UNSPECIFIED UNSPECIFIED Pergola, Giulio UNSPECIFIED UNSPECIFIED UNSPECIFIED Andriola, Ileana UNSPECIFIED UNSPECIFIED UNSPECIFIED Blasi, Giuseppe UNSPECIFIED UNSPECIFIED UNSPECIFIED Ruhrmann, Stephan UNSPECIFIED orcid.org/0000-0002-6022-2364 UNSPECIFIED Schultze-Lutter, Frauke UNSPECIFIED UNSPECIFIED UNSPECIFIED Falkai, Peter UNSPECIFIED UNSPECIFIED UNSPECIFIED Kambeitz, Joseph UNSPECIFIED UNSPECIFIED UNSPECIFIED Lencer, Rebekka UNSPECIFIED UNSPECIFIED UNSPECIFIED Dannlowski, Udo UNSPECIFIED UNSPECIFIED UNSPECIFIED Upthegrove, Rachel UNSPECIFIED orcid.org/0000-0001-8204-5103 UNSPECIFIED Salokangas, Raimo K. R. UNSPECIFIED UNSPECIFIED UNSPECIFIED Pantelis, Christos UNSPECIFIED orcid.org/0000-0002-9565-0238 UNSPECIFIED Meisenzahl, Eva UNSPECIFIED UNSPECIFIED UNSPECIFIED Wood, Stephen J. UNSPECIFIED UNSPECIFIED UNSPECIFIED Brambilla, Paolo UNSPECIFIED UNSPECIFIED UNSPECIFIED Borgwardt, Stefan UNSPECIFIED orcid.org/0000-0002-5792-3987 UNSPECIFIED Bertolino, Alessandro UNSPECIFIED UNSPECIFIED UNSPECIFIED Koutsouleris, Nikolaos UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-696035
DOI:	10.1192/bjp.2022.16
Journal or Publication Title:	Br. J. Psychiatry
Volume:	220
Number:	4
Page Range:	S. 229 - 246
Date:	2022
Publisher:	CAMBRIDGE UNIV PRESS
Place of Publication:	CAMBRIDGE
ISSN:	1472-1465
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language MACHINE-LEARNING ALGORITHM; QUALITY-OF-LIFE; PSYCHOMETRIC PROPERTIES; CHILDHOOD TRAUMA; INDIVIDUALS; ADVERSITY; SCHIZOPHRENIA; PERSISTENCE; VALIDATION; CALCULATOR Multiple languages Psychiatry Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/69603