Learning Latent Profiles via Cognitive Growth Charting in Psychosis: Design and Rationale for the PRECOGNITION Project

Abstract

Background and hypothesis: 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 characterize 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 generalizability across clinical populations, demographic backgrounds, and instruments and do not fully account for the interindividual heterogeneity inherent in psychosis.

Study design: Here, we outline the rationale, design, and analysis plan for the PRECOGNITION project, which aims to address these challenges.

Study results: This project is a collaboration between partners in 5 European countries. The project will not generate any primary data, but by leveraging existing datasets and combining these with novel analytic methods, it will produce multiple contributions including: (i) translating normative modeling approaches pioneered in brain imaging to psychosis data, to yield "cognitive growth charts" for longitudinal tracking and individual prediction; (ii) developing machine learning models for harmonizing and stratifying cohorts on the basis of these models; and (iii) providing integrated next-generation norms, having broad sociodemographic coverage including different languages and distinct norms for individuals with psychosis and unaffected individuals.

Conclusions: This study will enable precision stratification of psychosis cohorts and furnish predictions for a broad range of functional outcome measures. It will be guided throughout by lived experience experts.

Keywords: cognition; data; functional outcomes; harmonization; normative models; psychosis.

Figure 1.

The PRECOGNITION project is structured into 3 mutually interacting workpackages (WPs), with lived experience engagement throughout the project. Key themes for each WP are identified.

Figure 2.

A high-level overview of our analytical workflow including prestatistical harmonization (A), imputation (B), followed by fitting normative models (C). In panel A, 2 measures are shown that are equivalent, but derived from different tests and having slight variations. These can be accommodated by simple mathematical operations such as rescalings. In panel B, we show a graphical representation of data derived from the Thematically Organized Psychosis (TOP) cohort, which contains 2 distinct cognitive batteries applied to different subjects, inducing a strong pattern of structured missingness in the data, requiring custom-built imputation techniques to complete (right). In panel C, we show an example of an identical measure derived from the NIH toolbox for multiple studies from the Human Connectome Project lifespan datasets. In this case cohort, effects and nonlinearity across the lifespan can be accommodated in the normative modeling step.

Figure 3.

Illustrative data assembled from some of the cohorts used in the PRECOGNITION project. Left panel: Delayed recall scores from the California Verbal Learning Test and Hopkins Verbal Learning Test, derived from the different Thematically Organized Psychosis (TOP) batteries. Although the tests are nearly identical, they have different psychometric properties across the lifespan. Middle panel: MATRICS “Mazes” score (assessing planning and foresight) used in the second TOP battery shows clear heteroskedasticity across the lifespan and does not have an equivalent in the first TOP battery. This means it must be reconstructed using imputation. Right panel: Reading age score from the Human Connectome Project (HCP) lifespan data. This shows a nonlinear relationship with age and strong cohort effects, which must be accommodated during the modeling.