Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Digital screening tools for individuals at risk of mental disorders: a systematic review
ABSTRACT
Background:
Detecting individuals at risk of mental disorders is central to primary indicated preventive approaches and is the first rate-limiting step to their success. Digital screening tools present a notable opportunity to systematically screen wide-scale populations for people at risk of developing mental disorders.
Objective:
This systematic review aimed to summarise the operationalisation of available digital screening tools for detecting individuals at risk of mental disorders.
Methods:
MEDLINE, Embase, and PsycINFO were searched until 15th July 2026 for any-language original articles that involved using a digital tool to identify individuals currently meeting at-risk criteria for psychosis, bipolar disorder, depression, personality disorders, anxiety disorders and/or eating disorders, or predicting future incident full-threshold disorder onset. Risk of bias was assessed using an adapted QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies, Version 2). Screening tools were summarised regarding: i) disorders screened; ii) populations screened; iii) data types and predictors; iv) modelling techniques; v) study designs; and vi) validation structures.
Results:
A total of 173 studies were included; 142 (82.1%) screened individuals for meeting current at-risk criteria, 25 (14.5%) screened individuals for future incident full-threshold disorder, and 6 (3.5%) screened individuals for both. Studies were concentrated in eating disorders, depression and psychosis, with comparatively little evidence for bipolar disorder, anxiety disorders, PTSD or personality disorders. Website-based questionnaires were the most common digital approach, followed by electronic health records, with other digital biomarkers evaluated less frequently. Most studies relied predominantly on clinical questionnaire data. Only a small number used independent clinical reference standards for current at-risk states. 98.9% of the included screening tools were judged to be at risk of bias, and 83.8% had concerns regarding applicability.
Conclusions:
Digital screening tools show promise in detecting at-risk individuals. However, this is limited by the paucity of reporting of relevant performance metrics. Future studies should use independent reference standards, explore the use of transdiagnostic models to detect early signs more comprehensively, and to harness other digital data beyond clinically-focussed data to refine the performance of these screening tools. Emerging technologies may enable richer phenotyping but the promise of digital screening tools will only translate to patient benefit when integrated with clinically meaningful staging frameworks and effective preventive care pathways. Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.