Heterogeneity and Classification of Recent Onset Psychosis and Depression: A Multimodal Machine Learning Approach
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 55 · Cited by 42
Research works printed but not linked: 14
- Wolpert DH. Stacked generalization. Neural Netw. 1992;5(2):241-259. doi:10.1016/S0893- 574 6080(05)80023-1 575 · DOI
- Kay SR, Fiszbein A, Opler LA. The positive and negative syndrome scale (PANSS) for 542 schizophrenia. Schizophr Bull. 1987;13(2):261-276. 543
- First, Michael B, Spitzer, Robert L, Gibbon, Miriam, Williams, Janet B.W. Structured 549 Clinical Interview for DSM-IV-TR Axis I Disorders, Research Version, Patient Edition With 550 Psychotic Screen (SCID-I/P W/ PSY SCREEN). Biometrics Research, New York State 551 Psychiatric Institute.; 2002. 552
- Veale JF. Edinburgh Handedness Inventory-Short Form: A revised version based on 566 confirmatory factor analysis. Laterality: Asymmetries of Body, Brain and Cognition. 567 2014;19(2):164-177. doi:10.1080/1357650X.2013.783045 568 · DOI
- Cole JD, Kazarian SS. The Level of Expressed Emotion Scale: A new measure of expressed 570 emotion. Journal of Clinical Psychology. 1988;44(3):392-397. doi:10.1002/1097- 571 4679(198805)44:3<392::AID-JCLP2270440313>3.0.CO;2-3 572 · DOI
- Friborg O, Hjemdal O, Rosenvinge JH, Martinussen M. A new rating scale for adult 579 resilience: what are the central protective resources behind healthy adjustment? Int J 580 Methods Psychiatr Res. 2003;12(2):65-76. 581
- Connor KM, Davidson JR, Churchill LE, Sherwood A, Foa E, Weisler RH. Psychometric 582 properties of the Social Phobia Inventory (SPIN). New self-rating scale. Br J Psychiatry. 583 2000;176:379-386. doi:10.1192/bjp.176.4.379 584 · DOI
- Cornblatt BA, Risch NJ, Faris G, Friedman D, Erlenmeyer-Kimling L. The Continuous 588 Performance Test, identical pairs version (CPT-IP): I. New findings about sustained 589 attention in normal families. Psychiatry Res. 1988;26(2):223-238. doi:10.1016/0165- 590 1781(88)90076-5 591 · DOI
- Rey A. L'examen psychologique dans les cas d'encéphalopathie traumatique. (Les 596 problems.). [The psychological examination in cases of traumatic encepholopathy. 597 Problems.]. Archives de Psychologie. 1941;28:215-285. 598
- Mushquash C, O'Connor BP. SPSS and SAS programs for generalizability theory analyses. 612 Behavior Research Methods. 2006;38(3):542-547. doi:10.3758/BF03192810 613 · DOI
- R. Polikar. Ensemble based systems in decision making -IEEE Journals & Magazine. 616 Published 2006. Accessed May 20, 2019. https://ieeexplore.ieee.org/document/1688199 617
- Fan R-E, Chang K-W, Hsieh C-J, Wang X-R, Lin C-J. LIBLINEAR: A Library for Large 620 Linear Classification. J Mach Learn Res. 2008;9:1871-1874. 621
- Marulanda S, Addington J. Resilience in Individuals at Clinical High Risk for Psychosis. 643 Early Interv Psychiatry. 2016;10(3):212-219. doi:10.1111/eip.12174 644 · DOI
- Koutsouleris N, Kambeitz-Ilankovic L, Ruhrmann S, et al. Prediction Models of Functional 655 Outcomes for Individuals in the Clinical High-Risk State for Psychosis or With Recent- 656 Onset Depression: A Multimodal, Multisite Machine Learning Analysis. JAMA Psychiatry. 657 2018;75(11):1156-1172. doi:10.1001/jamapsychiatry.2018.2165 658 · DOI
- Authors
- Lalousis, P. A., Wood, S. J., Schmaal, L., Chisholm, K., Griffiths, S. L., Reniers, R. L. E. P., 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., Rosen, M., Schmidt, A., Meisenzahl, E., Koutsouleris, N., Upthegrove, R., & PRONIA Consortium
- Affiliations
- University of Birmingham (GB)
- The University of Melbourne (AU)
- Aston University (GB)
- Institute for Mental Health, University of Birmingham, Birmingham, UK
- University of Bari Aldo Moro (IT)
- University of Basel (CH)
- University of Milan (IT)
- Ludwig-Maximilians-Universität München (DE)
- University of Münster (DE)
- University of Cologne (DE)
- University of Turku (FI)
- Department of Psychiatry and Psychotherapy, Heinrich-Heine University Düsseldorf, Düsseldorf, Germany
- IRCCS Eugenio Medea (IT)
- Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT)
- Department of Psychiatry, University of Basel, Basel, Switzerland
- Heinrich Heine University Düsseldorf (DE)
- Birmingham Women’s and Children’s NHS Foundation Trust (GB)
- Corresponding author
- Lalousis, Paris Alexandros
- ORCID
- Lalousis, Paris Alexandros
- Wood, Stephen J
- Schmaal, Lianne
- Chisholm, Katharine
- Griffiths, Sian Lowri
- Reniers, Renate L E P
- Bertolino, Alessandro
- Borgwardt, Stefan
- Brambilla, Paolo
- Kambeitz, Joseph
- Lencer, Rebekka
- Pantelis, Christos
- Ruhrmann, Stephan
- Salokangas, Raimo K R
- Bonivento, Carolina
- Dwyer, Dominic
- Ferro, Adele
- Rosen, Marlene
- Schmidt, Andre
- Meisenzahl, Eva
- Koutsouleris, Nikolaos
- Upthegrove, Rachel
- Venue
- Schizophrenia Bulletin
- Publisher
- Oxford University Press (OUP)
- Published
- 2021-02-05
- Volume
- 47
- Issue
- 4
- Pages
- 1130-1140
- ISSN
- 0586-7614 (ISSN-L)
- 1745-1701
- PMC
- PMC8266654
- OpenAlex
- W3127346740
- Cited by
- 42
- References
- 55
- Citations by year
- 2026: 4 · 2025: 4 · 2024: 13 · 2023: 10 · 2022: 10 · 2021: 1
- FWCI
- 3.82
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- Schizophrenia Bulletin (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Kölner Universitäts PublikationsServer (Universität zu Köln) (publishedVersion)
- University of Birmingham Research Portal (University of Birmingham) (publishedVersion, other-oa)
- Minerva Access (University of Melbourne) (submittedVersion)
- CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro) (submittedVersion)
- Funders
- European Union (602152)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Schizophrenia research and treatment
- Health Sciences › Medicine › Psychiatry and Mental health › Bipolar Disorder and Treatment
- Social Sciences › Arts and Humanities › Philosophy › Mental Health and Psychiatry
- Keywords
- recent-onset psychosis, recent-onset depression
- MeSH terms
- Machine Learning, Adult, Depression, Female, Humans, Male, Psychotic Disorders, Comorbidity, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
