Heterogeneity and classification of recent onset psychosis and depression: a multimodal machine learning approach

Research output: Contribution to journalArticlepeer-review

Standard

Heterogeneity and classification of recent onset psychosis and depression : a multimodal machine learning approach. / Lalousis, Paris Alexandros; Wood, Stephen; Schmaal, Lianne; Chisholm, Katie; Griffiths, Lowri; Reniers, Renate; Bertolino, Alessandro; Borgwardt, Stefan; Brambilla, Paolo; Kambeitz, Joseph ; Lencer, Rebekka; Pantelis, Christos; Ruhrmann, Stephan; Salokangas, Raimo K.R.; Schultze-Lutter, Frauke; Bonivento, C.; Dwyer, Dominic; Ferro, Adele; Haidl, Theresa; Rosen, Marlene; Schmidt, André; Meisenzahl, Eva; Koutsouleris, Nikolaos; Upthegrove, Rachel; PRONIA Consortium.

In: Schizophrenia bulletin, 05.02.2021.

Research output: Contribution to journalArticlepeer-review

Harvard

Lalousis, PA, Wood, S, Schmaal, L, Chisholm, K, Griffiths, L, Reniers, R, Bertolino, A, Borgwardt, S, Brambilla, P, Kambeitz, J, Lencer, R, Pantelis, C, Ruhrmann, S, Salokangas, RKR, Schultze-Lutter, F, Bonivento, C, Dwyer, D, Ferro, A, Haidl, T, Rosen, M, Schmidt, A, Meisenzahl, E, Koutsouleris, N, Upthegrove, R & PRONIA Consortium 2021, 'Heterogeneity and classification of recent onset psychosis and depression: a multimodal machine learning approach', Schizophrenia bulletin. https://doi.org/10.1093/schbul/sbaa185

APA

Lalousis, P. A., Wood, S., Schmaal, L., Chisholm, K., Griffiths, L., Reniers, R., Bertolino, A., Borgwardt, S., Brambilla, P., Kambeitz, J., Lencer, R., Pantelis, C., Ruhrmann, S., Salokangas, R. K. R., Schultze-Lutter, F., Bonivento, C., Dwyer, D., Ferro, A., Haidl, T., ... PRONIA Consortium (2021). Heterogeneity and classification of recent onset psychosis and depression: a multimodal machine learning approach. Schizophrenia bulletin, [sbaa185]. https://doi.org/10.1093/schbul/sbaa185

Vancouver

Author

Lalousis, Paris Alexandros ; Wood, Stephen ; Schmaal, Lianne ; Chisholm, Katie ; Griffiths, Lowri ; Reniers, Renate ; Bertolino, Alessandro ; Borgwardt, Stefan ; Brambilla, Paolo ; Kambeitz, Joseph ; Lencer, Rebekka ; Pantelis, Christos ; Ruhrmann, Stephan ; Salokangas, Raimo K.R. ; Schultze-Lutter, Frauke ; Bonivento, C. ; Dwyer, Dominic ; Ferro, Adele ; Haidl, Theresa ; Rosen, Marlene ; Schmidt, André ; Meisenzahl, Eva ; Koutsouleris, Nikolaos ; Upthegrove, Rachel ; PRONIA Consortium. / Heterogeneity and classification of recent onset psychosis and depression : a multimodal machine learning approach. In: Schizophrenia bulletin. 2021.

Bibtex

@article{7aa1d1c4e1cd45c18b563f542c540a2b,
title = "Heterogeneity and classification of recent onset psychosis and depression: a multimodal machine learning approach",
abstract = "Diagnostic heterogeneity within and across psychotic and affective disorders challenges accurate treatment selection, particularly in early stages. Delineation of shared and distinct illness features at the phenotypic and brain levels may inform the development of more precise differential diagnostic tools. We aimed to identify prototypes of depression and psychosis to investigate their heterogeneity, with common, comorbid transdiagnostic symptoms. Analysing clinical/neurocognitive and grey matter volume (GMV) data from the PRONIA database, we generated prototypic models of recent-onset depression (ROD) vs. recent-onset psychosis (ROP) by training support-vector machines to separate patients with ROD from patients with ROP, who were selected for absent comorbid features (pure groups). Then, models were applied to patients with comorbidity, i.e., ROP with depressive symptoms (ROP+D) and ROD participants with sub-threshold psychosis-like features (ROD+P), to measure their positions within the affective-psychotic continuum. All models were independently validated in a replication sample. Comorbid patients were positioned between pure groups, with ROP+D patients being more frequently classified as ROD compared to pure ROP patients (clinical/neurocognitive model: χ2=14.874; p<0.001; GMV model: χ2=4.933; p=0.026). ROD+P patient classification did not differ from ROD (clinical/neurocognitive model: χ2=1.956; p=0.162; GMV model: χ2=0.005; p=0.943). Clinical/neurocognitive and neuroanatomical models demonstrated separability of prototypic depression from psychosis. The shift of comorbid patients towards the depression prototype, observed at the clinical and biological levels, suggests that psychosis with affective comorbidity aligns more strongly to depressive rather than psychotic disease processes. Future studies should assess how these quantitative measures of comorbidity predict outcomes and individual responses to stratified therapeutic interventions.",
author = "Lalousis, {Paris Alexandros} and Stephen Wood and Lianne Schmaal and Katie Chisholm and Lowri Griffiths and Renate Reniers and Alessandro Bertolino and Stefan Borgwardt and Paolo Brambilla and Joseph Kambeitz and Rebekka Lencer and Christos Pantelis and Stephan Ruhrmann and Salokangas, {Raimo K.R.} and Frauke Schultze-Lutter and C. Bonivento and Dominic Dwyer and Adele Ferro and Theresa Haidl and Marlene Rosen and Andr{\'e} Schmidt and Eva Meisenzahl and Nikolaos Koutsouleris and Rachel Upthegrove and {PRONIA Consortium}",
year = "2021",
month = feb,
day = "5",
doi = "10.1093/schbul/sbaa185",
language = "English",
journal = "Schizophrenia bulletin",
issn = "0586-7614",
publisher = "Oxford University Press",

}

RIS

TY - JOUR

T1 - Heterogeneity and classification of recent onset psychosis and depression

T2 - a multimodal machine learning approach

AU - Lalousis, Paris Alexandros

AU - Wood, Stephen

AU - Schmaal, Lianne

AU - Chisholm, Katie

AU - Griffiths, Lowri

AU - Reniers, Renate

AU - Bertolino, Alessandro

AU - Borgwardt, Stefan

AU - Brambilla, Paolo

AU - Kambeitz, Joseph

AU - Lencer, Rebekka

AU - Pantelis, Christos

AU - Ruhrmann, Stephan

AU - Salokangas, Raimo K.R.

AU - Schultze-Lutter, Frauke

AU - Bonivento, C.

AU - Dwyer, Dominic

AU - Ferro, Adele

AU - Haidl, Theresa

AU - Rosen, Marlene

AU - Schmidt, André

AU - Meisenzahl, Eva

AU - Koutsouleris, Nikolaos

AU - Upthegrove, Rachel

AU - PRONIA Consortium

PY - 2021/2/5

Y1 - 2021/2/5

N2 - Diagnostic heterogeneity within and across psychotic and affective disorders challenges accurate treatment selection, particularly in early stages. Delineation of shared and distinct illness features at the phenotypic and brain levels may inform the development of more precise differential diagnostic tools. We aimed to identify prototypes of depression and psychosis to investigate their heterogeneity, with common, comorbid transdiagnostic symptoms. Analysing clinical/neurocognitive and grey matter volume (GMV) data from the PRONIA database, we generated prototypic models of recent-onset depression (ROD) vs. recent-onset psychosis (ROP) by training support-vector machines to separate patients with ROD from patients with ROP, who were selected for absent comorbid features (pure groups). Then, models were applied to patients with comorbidity, i.e., ROP with depressive symptoms (ROP+D) and ROD participants with sub-threshold psychosis-like features (ROD+P), to measure their positions within the affective-psychotic continuum. All models were independently validated in a replication sample. Comorbid patients were positioned between pure groups, with ROP+D patients being more frequently classified as ROD compared to pure ROP patients (clinical/neurocognitive model: χ2=14.874; p<0.001; GMV model: χ2=4.933; p=0.026). ROD+P patient classification did not differ from ROD (clinical/neurocognitive model: χ2=1.956; p=0.162; GMV model: χ2=0.005; p=0.943). Clinical/neurocognitive and neuroanatomical models demonstrated separability of prototypic depression from psychosis. The shift of comorbid patients towards the depression prototype, observed at the clinical and biological levels, suggests that psychosis with affective comorbidity aligns more strongly to depressive rather than psychotic disease processes. Future studies should assess how these quantitative measures of comorbidity predict outcomes and individual responses to stratified therapeutic interventions.

AB - Diagnostic heterogeneity within and across psychotic and affective disorders challenges accurate treatment selection, particularly in early stages. Delineation of shared and distinct illness features at the phenotypic and brain levels may inform the development of more precise differential diagnostic tools. We aimed to identify prototypes of depression and psychosis to investigate their heterogeneity, with common, comorbid transdiagnostic symptoms. Analysing clinical/neurocognitive and grey matter volume (GMV) data from the PRONIA database, we generated prototypic models of recent-onset depression (ROD) vs. recent-onset psychosis (ROP) by training support-vector machines to separate patients with ROD from patients with ROP, who were selected for absent comorbid features (pure groups). Then, models were applied to patients with comorbidity, i.e., ROP with depressive symptoms (ROP+D) and ROD participants with sub-threshold psychosis-like features (ROD+P), to measure their positions within the affective-psychotic continuum. All models were independently validated in a replication sample. Comorbid patients were positioned between pure groups, with ROP+D patients being more frequently classified as ROD compared to pure ROP patients (clinical/neurocognitive model: χ2=14.874; p<0.001; GMV model: χ2=4.933; p=0.026). ROD+P patient classification did not differ from ROD (clinical/neurocognitive model: χ2=1.956; p=0.162; GMV model: χ2=0.005; p=0.943). Clinical/neurocognitive and neuroanatomical models demonstrated separability of prototypic depression from psychosis. The shift of comorbid patients towards the depression prototype, observed at the clinical and biological levels, suggests that psychosis with affective comorbidity aligns more strongly to depressive rather than psychotic disease processes. Future studies should assess how these quantitative measures of comorbidity predict outcomes and individual responses to stratified therapeutic interventions.

U2 - 10.1093/schbul/sbaa185

DO - 10.1093/schbul/sbaa185

M3 - Article

JO - Schizophrenia bulletin

JF - Schizophrenia bulletin

SN - 0586-7614

M1 - sbaa185

ER -