Predicting early clinical recovery in first-episode psychosis: development and external validation of a clinically interpretable multivariable model

Year: 2026

Type: article

Abstract: BACKGROUND: Identifying patients with first-episode psychosis (FEP) who are unlikely to achieve early clinical recovery (ECR) is critical for personalised intervention and resource allocation. ECR - defined as the concurrent achievement of symptomatic and functional remission - represents a clinically meaningful outcome that captures both illness control and functional reintegration. AIMS: To develop and externally validate prediction models for ECR using clinical, cognitive and genetic data. METHOD: = 668), for external validation. Forty-seven baseline clinical and cognitive variables and 87 polygenic risk scores (PRSs) were examined. Predictors were selected using penalised logistic regression. Logistic regression and three machine learning algorithms were compared for discrimination, calibration and clinical utility. RESULTS: The best-performing model was a logistic regression using six routinely collected clinical and cognitive predictors (duration of untreated psychosis, days of treated psychosis, baseline functioning, insight, executive function and cognitive reserve), with an optimism-corrected area under the receiver operating characteristic curve of 0.73 in development and 0.63 in external validation. PRS models showed limited external generalisability and did not improve prediction. Machine learning algorithms offered no advantage over regression models. CONCLUSIONS: A simple, interpretable logistic regression model based on routine clinical and cognitive variables can predict early recovery in FEP with acceptable generalisability. These findings support the use of transparent, clinically grounded models in early psychosis care and highlight the current limitations of genetic predictors for individualised treatment.

Source: The British Journal of Psychiatry

DOI: 10.1192/bjp.2026.10581

Institutions: Consorci Institut D'Investigacions Biomediques August Pi I Sunyer, Universitat de Barcelona, Instituto de Investigación Marqués de Valdecilla, Hospital Clínic de Barcelona, Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental, Instituto de Biomedicina de Sevilla, Universidad Complutense de Madrid, Hospital General Universitario Gregorio Marañón, University of the Basque Country, Hospital de Sant Pau, Institut de Recerca Sant Pau, Universidad de Cantabria, Marqués de Valdecilla University Hospital, Hospital Sierrallana, Universidad de Alcalá, Instituto Ramón y Cajal de Investigación Sanitaria, Universidad de Cádiz, Servicio Gallego de Salud, Hospital Universitario Virgen del Rocío, Hospital de Basurto, Osakidetza, Navarre Institute of Health Research, Vall d'Hebron Institut de Recerca, Vall d'Hebron Hospital Universitari

Language: English

Topic: Schizophrenia research and treatment

Subfield: Psychiatry and Mental health

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: hybrid

Estimated APC paid: $4,920

Funders: Centres de Recerca de Catalunya, European Commission, Ministerio de Economía y Competitividad, Euskal Herriko Unibertsitatea, Universitat de Barcelona, Universidad de Alcalá, Universidad de Cantabria, Centro de Investigación Biomédica en Red de Salud Mental, Fundació Institut de Recerca Hospital Universitari Vall d’Hebron, H. Lundbeck A/S, Gobierno de Navarra, Instituto de Investigación Marqués de Valdecilla, Instituto de Salud Carlos III, European Regional Development Fund, Servicio Gallego de Salud, Institut d’Investigacions Biomèdiques August Pi i Sunyer, Universitat de Barcelona, Cilag

OpenAlex ID: W7140117981