Third external replication of an individualised transdiagnostic prediction model for the automatic detection of individuals at risk of psychosis using electronic health records

Background: Primary indicated prevention is a key target for reducing the incidence and burden of schizophrenia and related psychotic disorders. An individualised, clinically-based transdiagnostic model for the detection of individuals at risk of psychosis has been developed and validated in two large, urban healthcare providers. We tested its external validity in a geographically and demographically different non-urban population. Method: Retrospective EHR cohort study. All individuals accessing secondary healthcare provided by Oxford Health NHS Foundation Trust between 1st January 2011 and 30th November 2019 and receiving a primary index diagnosis of a non-psychotic or non-organicmental disorder were considered eligible. The previously developed model was applied to this database and its external prognostic accuracy was measured with Harrell's C. Findings: The study included n = 33,710 eligible individuals, with an average age of 27.7 years (SD = 19.8), mostly white (92.0%) and female (57.3%). The mean follow-up was 1863.9 days (SD = 948.9), with 868 transitions to psychosis and a cumulative incidence of psychosis at 6 years of 2.9% (95%CI: 2.7-3.1). Compared to the urban development database, OxfordHealthwas characterised by a relevant case mix, lower incidence of psychosis, different distribution of baseline predictors, higher proportion of white females, and a lack of specialised clinical services for at risk individuals. Despite these differences the model retained an adequate prognostic performance (Harrell's C = 0.79, 95%CI: 0.78-0.81), with no major miscalibration. Interpretation: The transdiagnostic, individualised, clinically-based risk calculator is transportable outside urban healthcare providers. Further research should test transportability of this risk prediction model in an international setting. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

The study demonstrates that a personalized and clinically-based risk calculator shows external validity in a non-urban population. Despite differences between Oxford Health and urban development databases, the model retains accurate prognostic performance in diverse population groups.