PMID- 34215752 OWN - NLM STAT- PubMed-not-MEDLINE LR - 20230204 IS - 2334-265X (Print) IS - 2334-265X (Electronic) IS - 2334-265X (Linking) VI - 7 IP - 1 DP - 2021 Jul 2 TI - Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach. PG - 34 LID - 10.1038/s41537-021-00162-3 [doi] LID - 34 AB - Schizophrenia and related disorders have heterogeneous outcomes. Individualized prediction of long-term outcomes may be helpful in improving treatment decisions. Utilizing extensive baseline data of 523 patients with a psychotic disorder and variable illness duration, we predicted symptomatic and global outcomes at 3-year and 6-year follow-ups. We classified outcomes as (1) symptomatic: in remission or not in remission, and (2) global outcome, using the Global Assessment of Functioning (GAF) scale, divided into good (GAF >/= 65) and poor (GAF < 65). Aiming for a robust and interpretable prediction model, we employed a linear support vector machine and recursive feature elimination within a nested cross-validation design to obtain a lean set of predictors. Generalization to out-of-study samples was estimated using leave-one-site-out cross-validation. Prediction accuracies were above chance and ranged from 62.2% to 64.7% (symptomatic outcome), and 63.5-67.6% (global outcome). Leave-one-site-out cross-validation demonstrated the robustness of our models, with a minor drop in predictive accuracies of 2.3% on average. Important predictors included GAF scores, psychotic symptoms, quality of life, antipsychotics use, psychosocial needs, and depressive symptoms. These robust, albeit modestly accurate, long-term prognostic predictions based on lean predictor sets indicate the potential of machine learning models complementing clinical judgment and decision-making. Future model development may benefit from studies scoping patient's and clinicians' needs in prognostication. FAU - de Nijs, Jessica AU - de Nijs J AD - Department of Psychiatry, University Medical Center Utrecht, UMC Utrecht Brain Center, Utrecht University, Utrecht, The Netherlands. FAU - Burger, Thijs J AU - Burger TJ AD - Arkin, Institute for Mental Health, Amsterdam, The Netherlands. AD - Department of Psychiatry, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. FAU - Janssen, Ronald J AU - Janssen RJ AUID- ORCID: 0000-0001-9622-5420 AD - Department of Psychiatry, University Medical Center Utrecht, UMC Utrecht Brain Center, Utrecht University, Utrecht, The Netherlands. FAU - Kia, Seyed Mostafa AU - Kia SM AUID- ORCID: 0000-0002-7128-814X AD - Department of Psychiatry, University Medical Center Utrecht, UMC Utrecht Brain Center, Utrecht University, Utrecht, The Netherlands. FAU - van Opstal, Daniel P J AU - van Opstal DPJ AUID- ORCID: 0000-0002-6038-7177 AD - Department of Psychiatry, University Medical Center Utrecht, UMC Utrecht Brain Center, Utrecht University, Utrecht, The Netherlands. FAU - de Koning, Mariken B AU - de Koning MB AD - Arkin, Institute for Mental Health, Amsterdam, The Netherlands. AD - Department of Psychiatry, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. FAU - de Haan, Lieuwe AU - de Haan L AD - Arkin, Institute for Mental Health, Amsterdam, The Netherlands. AD - Department of Psychiatry, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. CN - GROUP investigators FAU - Cahn, Wiepke AU - Cahn W AUID- ORCID: 0000-0002-0482-8759 AD - Department of Psychiatry, University Medical Center Utrecht, UMC Utrecht Brain Center, Utrecht University, Utrecht, The Netherlands. AD - Altrecht, General Mental Health Care, Utrecht, The Netherlands. FAU - Schnack, Hugo G AU - Schnack HG AUID- ORCID: 0000-0002-4620-3853 AD - Department of Psychiatry, University Medical Center Utrecht, UMC Utrecht Brain Center, Utrecht University, Utrecht, The Netherlands. h.schnack@umcutrecht.nl. LA - eng PT - Journal Article DEP - 20210702 PL - United States TA - NPJ Schizophr JT - NPJ schizophrenia JID - 101657919 PMC - PMC8253813 COIS- L.H. has received research funding form Eli Lilly and honoraria for educational programs from Eli Lilly, Jansen Cilag, BMS, Astra Zeneca. R.K. is or has been a member of DSMB for Janssen, Otsuka, Sunovion. and Roche. W.C. is or has been an unrestricted research grant holder with, or has received financial compensation as an independent symposium speaker or as an consultant from, Eli Lilly, BMS, Lundbeck, Sanofi-Aventis, Janssen-Cilag, AstraZeneca and Schering-Plough. I.M.-G. is an unrestricted research grant holder with Janssen-Cilag and has received financial compensation as an independent symposium speaker from Eli Lilly, BMS, Lundbeck, and Janssen-Cilag. All other authors report no potential competing interests. FIR - Alizadeh, Behrooz Z IR - Alizadeh BZ FIR - Bartels-Velthuis, Agna A IR - Bartels-Velthuis AA FIR - van Beveren, Nico J IR - van Beveren NJ FIR - Bruggeman, Richard IR - Bruggeman R FIR - de Haan, Lieuwe IR - de Haan L FIR - Delespaul, Philippe IR - Delespaul P FIR - Luykx, Jurjen J IR - Luykx JJ FIR - Myin-Germeys, Inez IR - Myin-Germeys I FIR - Kahn, Rene S IR - Kahn RS FIR - Schirmbeck, Frederike IR - Schirmbeck F FIR - Simons, Claudia J P IR - Simons CJP FIR - van Amelsvoort, Therese IR - van Amelsvoort T FIR - van Os, Jim IR - van Os J FIR - van Winkel, Ruud IR - van Winkel R EDAT- 2021/07/04 06:00 MHDA- 2021/07/04 06:01 PMCR- 2021/07/02 CRDT- 2021/07/03 05:45 PHST- 2020/06/29 00:00 [received] PHST- 2021/02/17 00:00 [accepted] PHST- 2021/07/03 05:45 [entrez] PHST- 2021/07/04 06:00 [pubmed] PHST- 2021/07/04 06:01 [medline] PHST- 2021/07/02 00:00 [pmc-release] AID - 10.1038/s41537-021-00162-3 [pii] AID - 162 [pii] AID - 10.1038/s41537-021-00162-3 [doi] PST - epublish SO - NPJ Schizophr. 2021 Jul 2;7(1):34. doi: 10.1038/s41537-021-00162-3.