Towards clinical application of prediction models for transition to psychosis: A systematic review and external validation study in the PRONIA sample

• Published in: Neuroscience and biobehavioral reviews Vol. 125; pp. 478 - 492
• Main Authors: Rosen, Marlene, Betz, Linda T., Schultze-Lutter, Frauke, Chisholm, Katharine, Haidl, Theresa K., Kambeitz-Ilankovic, Lana, Bertolino, Alessandro, Borgwardt, Stefan, Brambilla, Paolo, Lencer, Rebekka, Meisenzahl, Eva, Ruhrmann, Stephan, Salokangas, Raimo K.R., Upthegrove, Rachel, Wood, Stephen J., Koutsouleris, Nikolaos, Kambeitz, Joseph
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2021
• Subjects: Clinical high-risk; Early intervention; Model validation; Precision medicine; Prediction; Psychosis; Translational psychiatry; Psychosis; Early intervention; Precision medicine; Model validation; Prediction; Translational psychiatry; Clinical high-risk
• ISSN: 0149-7634; 1873-7528
• DOI: 10.1016/j.neubiorev.2021.02.032

•First comprehensive validation of prediction models for transition to psychosis.•In external PRONIA validation sample, two models show good discrimination performance.•Combining predictions from raters and transition models improves performance.•Prediction of transition to psychosis is feasible on global scale.•Yet transition models need additional research efforts before clinical implementation. A multitude of prediction models for a first psychotic episode in individuals at clinical high-risk (CHR) for psychosis have been proposed, but only rarely validated. We identified transition models based on clinical and neuropsychological data through a registered systematic literature search and evaluated their external validity in 173 CHRs from the Personalised Prognostic Tools for Early Psychosis Management (PRONIA) study. Discrimination performance was assessed with the area under the receiver operating characteristic curve (AUC), and compared to the prediction of clinical raters. External discrimination performance varied considerably across the 22 identified models (AUC 0.40−0.76), with two models showing good discrimination performance. None of the tested models significantly outperformed clinical raters (AUC = 0.75). Combining predictions of clinical raters and the best model descriptively improved discrimination performance (AUC = 0.84). Results show that personalized prediction of transition in CHR is potentially feasible on a global scale. For implementation in clinical practice, further rounds of external validation, impact studies, and development of an ethical framework is necessary.