The Normative Modeling Framework for Computational Psychiatry

TLDR

Normative modeling maps individual differences relative to a reference model by charting centiles across a population that link biology and behavior, offering a framework that addresses the slow shift in computational psychiatry from case–control approaches due to a lack of tools for modeling biological heterogeneity. This article defines a standardized protocol for conducting normative modeling analysis with the Predictive Clinical Neuroscience toolkit (PCNtoolkit). The protocol outlines data selection, modeling choices, and demonstrates downstream applications such as high‑risk stratification, subtyping, and behavioral prediction, and can be completed in approximately 1–3 hours. Normative modeling resolves the limitations of case–control comparisons by enabling analysis that does not depend on potentially noisy clinical labels.

Abstract

Abstract Normative modeling is an emerging and innovative framework for mapping individual differences at the level of a single subject or observation in relation to a reference model. It involves charting centiles of variation across a population in terms of mappings between biology and behavior which can then be used to make statistical inferences at the level of the individual. The fields of computational psychiatry and clinical neuroscience have been slow to transition away from patient versus “healthy” control analytic approaches, likely due to a lack of tools designed to properly model biological heterogeneity of mental disorders. Normative modeling provides a solution to address this issue and moves analysis away from case-control comparisons that rely on potentially noisy clinical labels. In this article, we define a standardized protocol to guide users through, from start to finish, normative modeling analysis using the Predictive Clinical Neuroscience toolkit (PCNtoolkit). We describe the input data selection process, provide intuition behind the various modeling choices, and conclude by demonstrating several examples of down-stream analyses the normative model results may facilitate, such as stratification of high-risk individuals, subtyping, and behavioral predictive modeling. The protocol takes approximately 1-3 hours to complete.