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

作者：Nikolaos Koutsouleris, Dominic Dwyer, Franziska Degenhardt, Carlo Maj, Maria Fernanda Urquijo-Castro, Rachele Sanfelici, David Popovic, Oemer Faruk Oeztuerk, Shalaila S. Haas, Johanna Weiske, Anne Ruef, Lana Kambeitz‐Ilankovic, Linda A. Antonucci, Susanne Neufang, Christian Schmidt-Kraepelin, Stephan Ruhrmann, Nora Penzel, Joseph Kambeitz, Theresa Haidl, Marlene Rosen, Katharine Chisholm, Anita Riecher‐Rössler, Laura Egloff, André Schmidt, Christina Andreou, Jarmo Hietala, Timo Schirmer, Georg Romer, Petra Walger, Maurizia Franscini, Nina Traber‐Walker, Benno G. Schimmelmann, Rahel Flückiger, Chantal Michel, Wulf Rössler, Oleg Borisov, Peter Krawitz, Karsten Heekeren, Roman Buechler, Christos Pantelis, Peter Falkai, Raimo K. R. Salokangas, Rebekka Lencer, Alessandro Bertolino, Stefan Borgwardt, Markus M. Nöethen, Paolo Brambilla, Stephen J. Wood, Rachel Upthegrove, Frauke Schultze‐Lutter, Anastasia Theodoridou, Eva Meisenzahl · 发表于：JAMA Psychiatry · 年份：2020 · DOI：10.1001/jamapsychiatry.2020.3604 · 被引用次数：272 · 研究领域：Schizophrenia research and treatment、Functional Brain Connectivity Studies、Treatment of Major Depression

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 pr...