Heterogeneity and Classification of Recent Onset Psychosis and Depression: A Multimodal Machine Learning Approach

Paris Alexandros Lalousis; Stephen J Wood; Lianne Schmaal; Katharine Chisholm; Sian Lowri Griffiths; Renate L E P Reniers; Alessandro Bertolino; Stefan Borgwardt; Paolo Brambilla; Joseph Kambeitz; Rebekka Lencer; Christos Pantelis; Stephan Ruhrmann; Raimo K R Salokangas; Frauke Schultze-Lutter; Carolina Bonivento; Dominic Dwyer; Adele Ferro; Theresa Haidl; Marlene Rosen; Andre Schmidt; Eva Meisenzahl; Nikolaos Koutsouleris; Rachel Upthegrove; PRONIA Consortium

doi:10.1093/schbul/sbaa185

Heterogeneity and Classification of Recent Onset Psychosis and Depression: A Multimodal Machine Learning Approach

Schizophr Bull. 2021 Jul 8;47(4):1130-1140. doi: 10.1093/schbul/sbaa185.

Authors

Paris Alexandros Lalousis^{1

2}, Stephen J Wood^{1

3

4}, Lianne Schmaal^{3

4}, Katharine Chisholm^{1

5}, Sian Lowri Griffiths^{1

2}, Renate L E P Reniers^{1

2

6}, Alessandro Bertolino⁷, Stefan Borgwardt^{8

9}, Paolo Brambilla^{10

11}, Joseph Kambeitz¹², Rebekka Lencer¹³, Christos Pantelis¹⁴, Stephan Ruhrmann¹⁵, Raimo K R Salokangas¹⁶, Frauke Schultze-Lutter^{17

18

19}, Carolina Bonivento²⁰, Dominic Dwyer¹², Adele Ferro¹¹, Theresa Haidl¹⁵, Marlene Rosen¹⁵, Andre Schmidt⁸, Eva Meisenzahl¹⁷, Nikolaos Koutsouleris¹², Rachel Upthegrove^{1

2

21}; PRONIA Consortium

Affiliations

¹ Institute for Mental Health, University of Birmingham, Birmingham, UK.
² Centre for Human Brain Health, University of Birmingham, Birmingham, UK.
³ Orygen, The National Centre of Excellence in Youth Mental Health, Melbourne, Australia.
⁴ Centre for Youth Mental Health, The University of Melbourne, Parkville, Australia.
⁵ Department of Psychology, Aston University, Birmingham, UK.
⁶ Institute of Clinical Sciences, University of Birmingham, Birmingham, UK.
⁷ Department of Basic Medical Sciences, Neuroscience and Sense Organs, University of Bari Aldo Moro, Bari, Italy.
⁸ Department of Psychiatry, University of Basel, Basel, Switzerland.
⁹ Department of Psychiatry and Psychotherapy, Center of Brain, Behavior and Metabolism, University of Lübeck, Germany.
¹⁰ Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy.
¹¹ Department of Neurosciences and Mental Health, IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan, Italy.
¹² Department of Psychiatry and Psychotherapy, Ludwig Maxmilians University, Munich, Germany.
¹³ Department of Psychiatry, University of Münster, Münster, Germany.
¹⁴ Melbourne Neuropsychiatry Centre, University of Melbourne, Melbourne, Australia.
¹⁵ Department of Psychiatry and Psychotherapy, Faculty of Medicine and University Hospital, University of Cologne, Cologne, Germany.
¹⁶ Department of Psychiatry, University of Turku, Turku, Finland.
¹⁷ Department of Psychiatry and Psychotherapy, Heinrich-Heine University Düsseldorf, Düsseldorf, Germany.
¹⁸ Department of Psychology and Mental Health, Faculty of Psychology, Airlangga University, Surabaya, Indonesia.
¹⁹ University Hospital of Child and Adolescent Psychiatry and Psychotherapy, University of Bern, Bern, Switzerland.
²⁰ IRCCS "E. Medea" Scientific Institute, San Vito al Tagliamento (Pn), Italy.
²¹ Early Intervention Service, Birmingham Women's and Children's NHS Foundation Trust, Birmingham, UK.

Abstract

Diagnostic heterogeneity within and across psychotic and affective disorders challenges accurate treatment selection, particularly in the 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. Analyzing 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, ie, 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 < .001; GMV model: χ2 = 4.933; P = .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 = .943). Clinical/neurocognitive and neuroanatomical models demonstrated separability of prototypic depression from psychosis. The shift of comorbid patients toward 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.

Keywords: MRI; comorbidity; depression; gray matter volume; machine learning; psychosis; transdiagnostic.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adult
Comorbidity
Depression / classification
Depression / diagnosis
Depression / epidemiology*
Female
Humans
Machine Learning
Male
Psychotic Disorders / classification
Psychotic Disorders / diagnosis
Psychotic Disorders / epidemiology*
Young Adult