Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach
Abstract 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 symptomat...
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/c0a120a59e46409f9c9e2a8a2725decb |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:c0a120a59e46409f9c9e2a8a2725decb |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:c0a120a59e46409f9c9e2a8a2725decb2021-12-02T18:18:58ZIndividualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach10.1038/s41537-021-00162-32334-265Xhttps://doaj.org/article/c0a120a59e46409f9c9e2a8a2725decb2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41537-021-00162-3https://doaj.org/toc/2334-265XAbstract 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.Jessica de NijsThijs J. BurgerRonald J. JanssenSeyed Mostafa KiaDaniël P. J. van OpstalMariken B. de KoningLieuwe de HaanGROUP investigatorsWiepke CahnHugo G. SchnackNature PortfolioarticlePsychiatryRC435-571ENnpj Schizophrenia, Vol 7, Iss 1, Pp 1-11 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Psychiatry RC435-571 |
| spellingShingle |
Psychiatry RC435-571 Jessica de Nijs Thijs J. Burger Ronald J. Janssen Seyed Mostafa Kia Daniël P. J. van Opstal Mariken B. de Koning Lieuwe de Haan GROUP investigators Wiepke Cahn Hugo G. Schnack Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach |
| description |
Abstract 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. |
| format |
article |
| author |
Jessica de Nijs Thijs J. Burger Ronald J. Janssen Seyed Mostafa Kia Daniël P. J. van Opstal Mariken B. de Koning Lieuwe de Haan GROUP investigators Wiepke Cahn Hugo G. Schnack |
| author_facet |
Jessica de Nijs Thijs J. Burger Ronald J. Janssen Seyed Mostafa Kia Daniël P. J. van Opstal Mariken B. de Koning Lieuwe de Haan GROUP investigators Wiepke Cahn Hugo G. Schnack |
| author_sort |
Jessica de Nijs |
| title |
Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach |
| title_short |
Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach |
| title_full |
Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach |
| title_fullStr |
Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach |
| title_full_unstemmed |
Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach |
| title_sort |
individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/c0a120a59e46409f9c9e2a8a2725decb |
| work_keys_str_mv |
AT jessicadenijs individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT thijsjburger individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT ronaldjjanssen individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT seyedmostafakia individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT danielpjvanopstal individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT marikenbdekoning individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT lieuwedehaan individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT groupinvestigators individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT wiepkecahn individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach AT hugogschnack individualizedpredictionofthreeandsixyearoutcomesofpsychosisinalongitudinalmulticenterstudyamachinelearningapproach |
| _version_ |
1718378180799102976 |