English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Multimodal Machine Learning Workflows for Prediction of Psychosis in Patients With Clinical High-Risk Syndromes and Recent-Onset Depression

Koutsouleris, N., Dwyer, D. B., Degenhardt, F., Maj, C., Urquijo-Castro, M. F., Sanfelici, R., et al. (2021). Multimodal Machine Learning Workflows for Prediction of Psychosis in Patients With Clinical High-Risk Syndromes and Recent-Onset Depression. JAMA PSYCHIATRY, 78(2), 195-209. doi:10.1001/jamapsychiatry.2020.3604.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Koutsouleris, Nikolaos1, Author           
Dwyer, Dominic B., Author
Degenhardt, Franziska, Author
Maj, Carlo, Author
Urquijo-Castro, Maria Fernanda, Author
Sanfelici, Rachele, Author
Popovic, David2, Author           
Oeztuerk, Oemer2, Author           
Haas, Shalaila S., Author
Weiske, Johanna, Author
Ruef, Anne, Author
Kambeitz-Ilankovic, Lana, Author
Antonucci, Linda A., Author
Neufang, Susanne, Author
Schmidt-Kraepelin, Christian, Author
Ruhrmann, Stephan, Author
Penzel, Nora, Author
Kambeitz, Joseph, Author
Haidl, Theresa K., Author
Rosen, Marlene, Author
Chisholm, Katharine, AuthorRiecher-Rossler, Anita, AuthorEgloff, Laura, AuthorSchmidt, Andre, AuthorAndreou, Christina, AuthorHietala, Jarmo, AuthorSchirmer, Timo, AuthorRomer, Georg, AuthorWalger, Petra, AuthorFranscini, Maurizia, AuthorTraber-Walker, Nina, AuthorSchimmelmann, Benno G., AuthorFluckiger, Rahel, AuthorMichel, Chantal, AuthorRossler, Wulf, AuthorBorisov, Oleg, AuthorKrawitz, Peter M., AuthorHeekeren, Karsten, AuthorBuechler, Roman, AuthorPantelis, Christos, AuthorFalkai, Peter2, Author           Salokangas, Raimo K. R., AuthorLencer, Rebekka, AuthorBertolino, Alessandro, AuthorBorgwardt, Stefan, AuthorNoethen, Markus, AuthorBrambilla, Paolo, AuthorWood, Stephen J., AuthorUpthegrove, Rachel, AuthorSchultze-Lutter, Frauke, AuthorTheodoridou, Anastasia, AuthorMeisenzahl, Eva, Author more..
Affiliations:
1Max Planck Fellow Group Precision Psychiatry, Max Planck Institute of Psychiatry, Max Planck Society, ou_3318615              
2IMPRS Translational Psychiatry, Max Planck Institute of Psychiatry, Max Planck Society, ou_3318616              

Content

show
hide
Free keywords: -
 Abstract: Importance Diverse models have been developed to predict psychosis in patients with clinical high-risk (CHR) states. Whether prediction can be improved by efficiently combining clinical and biological models and by broadening the risk spectrum to young patients with depressive syndromes remains unclear. Objectives To evaluate whether psychosis transition can be predicted in patients with CHR or recent-onset depression (ROD) using multimodal machine learning that optimally integrates clinical and neurocognitive data, structural magnetic resonance imaging (sMRI), and polygenic risk scores (PRS) for schizophrenia; to assess models' geographic generalizability; to test and integrate clinicians' predictions; and to maximize clinical utility by building a sequential prognostic system. Design, Setting, and Participants This multisite, longitudinal prognostic study performed in 7 academic early recognition services in 5 European countries followed up patients with CHR syndromes or ROD and healthy volunteers. The referred sample of 167 patients with CHR syndromes and 167 with ROD was recruited from February 1, 2014, to May 31, 2017, of whom 26 (23 with CHR syndromes and 3 with ROD) developed psychosis. Patients with 18-month follow-up (n = 246) were used for model training and leave-one-site-out cross-validation. The remaining 88 patients with nontransition served as the validation of model specificity. Three hundred thirty-four healthy volunteers provided a normative sample for prognostic signature evaluation. Three independent Swiss projects contributed a further 45 cases with psychosis transition and 600 with nontransition for the external validation of clinical-neurocognitive, sMRI-based, and combined models. Data were analyzed from January 1, 2019, to March 31, 2020. Main Outcomes and Measures Accuracy and generalizability of prognostic systems. Results A total of 668 individuals (334 patients and 334 controls) were included in the analysis (mean [SD] age, 25.1 [5.8] years; 354 [53.0%] female and 314 [47.0%] male). Clinicians attained a balanced accuracy of 73.2% by effectively ruling out (specificity, 84.9%) but ineffectively ruling in (sensitivity, 61.5%) psychosis transition. In contrast, algorithms showed high sensitivity (76.0%-88.0%) but low specificity (53.5%-66.8%). A cybernetic risk calculator combining all algorithmic and human components predicted psychosis with a balanced accuracy of 85.5% (sensitivity, 84.6%; specificity, 86.4%). In comparison, an optimal prognostic workflow produced a balanced accuracy of 85.9% (sensitivity, 84.6%; specificity, 87.3%) at a much lower diagnostic burden by sequentially integrating clinical-neurocognitive, expert-based, PRS-based, and sMRI-based risk estimates as needed for the given patient. Findings were supported by good external validation results. Conclusions and Relevance These findings suggest that psychosis transition can be predicted in a broader risk spectrum by sequentially integrating algorithms' and clinicians' risk estimates. For clinical translation, the proposed workflow should undergo large-scale international validation. Question Can a transition to psychosis be predicted in patients with clinical high-risk states or recent-onset depression by optimally integrating clinical, neurocognitive, neuroimaging, and genetic information with clinicians' prognostic estimates? Findings In this prognostic study of 334 patients and 334 control individuals, machine learning models sequentially combining clinical and biological data with clinicians' estimates correctly predicted disease transitions in 85.9% of cases across geographically distinct patient populations. The clinicians' lack of prognostic sensitivity, as measured by a false-negative rate of 38.5%, was reduced to 15.4% by the sequential prognostic model. Meaning These findings suggest that an individualized prognostic workflow integrating artificial and human intelligence may facilitate the personalized prevention of psychosis in young patients with clinical high-risk syndromes or recent-onset depression. This prognostic study evaluates whether psychosis transition can be predicted in patients with clinical high-risk syndromes or recent-onset depression by multimodal machine learning that optimally integrates clinical and neurocognitive data, structural magnetic resonance imaging, and polygenic risk scores for schizophrenia.

Details

show
hide
Language(s):
 Dates: 2021
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: JAMA PSYCHIATRY
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 78 (2) Sequence Number: - Start / End Page: 195 - 209 Identifier: ISSN: 2168-622X