Learning latent profiles via cognitive growth charting in psychosis: design and rationale for the PRECOGNITION project

Abstract

Cognitive impairments are a core feature of psychosis that are often evident before illness onset and have substantial impact on both clinical and real-world functional outcomes. Therefore, these are an excellent target for stratification and early detection in order to facilitate early intervention. While many studies have aimed to characterise the effects of cognition at the group level and others have aimed to detect individual differences by referencing subjects against existing norms, these studies have limited generalisability across clinical populations, demographic backgrounds and instruments and also do not fully account for the inter-individual heterogeneity inherent in psychosis. Here, we outline the rationale, design and analysis plan for the PRECOGNITION project which aims to address these challenges. This project is a collaboration between partners in five European countries, that aims to (i) translate normative modelling approaches that have been pioneered in brain imaging to psychosis data, to yield cognitive growth charts for longitudinal tracking and prediction at the individual level (ii) develop machine learning models for harmonising and stratifying cohorts on the basis of these models; (iii) provide comprehensive reference models that provide broad sociodemographic coverage including different languages and distinct norms for individuals with psychosis and unaffected individuals and (iv) stratification models and predictions for functional outcome measures in psychosis cohorts. Crucially, this project will be guided throughout by experts with lived experience.