TY - JOUR
T1 - Using combined environmental-clinical classification models to predict role functioning outcome in clinical high-risk states for psychosis and recent-onset depression
AU - Antonucci, Linda A
AU - Penzel, Nora
AU - Sanfelici, Rachele
AU - Pigoni, Alessandro
AU - Kambeitz-Ilankovic, Lana
AU - Dwyer, Dominic
AU - Ruef, Anne
AU - Sen Dong, Mark
AU - Öztürk, Ömer Faruk
AU - Chisholm, Katharine
AU - Haidl, Theresa
AU - Rosen, Marlene
AU - Ferro, Adele
AU - Pergola, Giulio
AU - Andriola, Ileana
AU - Blasi, Giuseppe
AU - Ruhrmann, Stephan
AU - Schultze-Lutter, Frauke
AU - Falkai, Peter
AU - Kambeitz, Joseph
AU - Lencer, Rebekka
AU - Dannlowski, Udo
AU - Upthegrove, Rachel
AU - Salokangas, Raimo K R
AU - Pantelis, Christos
AU - Meisenzahl, Eva
AU - Wood, Stephen J
AU - Brambilla, Paolo
AU - Borgwardt, Stefan
AU - Bertolino, Alessandro
AU - Koutsouleris, Nikolaos
PY - 2022/4/20
Y1 - 2022/4/20
N2 - 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.
AB - 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.
KW - Machine learning
KW - PRONIA
KW - personalised psychiatry
KW - psychosis
KW - role functioning
UR - https://www.cambridge.org/core/journals/the-british-journal-of-psychiatry/article/abs/using-combined-environmentalclinical-classification-models-to-predict-role-functioning-outcome-in-clinical-highrisk-states-for-psychosis-and-recentonset-depression/431FF911E37590FA71F9B94174126AE8
UR - http://www.scopus.com/inward/record.url?scp=85124964248&partnerID=8YFLogxK
U2 - 10.1192/bjp.2022.16
DO - 10.1192/bjp.2022.16
M3 - Article
C2 - 35152923
SN - 0007-1250
VL - 220
SP - 229
EP - 245
JO - The British journal of psychiatry : the journal of mental science
JF - The British journal of psychiatry : the journal of mental science
IS - 4
ER -