The Coupled Stochastic Dynamical System: A Generative Model for Simulating and Forecasting Youth Mental Health Trajectories
Year: 2026
Type: preprint
Abstract: Predicting individual mental-health trajectories requires models that capture cross-domain dynamics rather than only statistical associations. We introduce the Coupled Stochastic Dynamical System (CSDS), a forward generative model of interacting digital behaviour, wearable-derived physiology and psychiatric burden. In the multi-year GLOBEM student cohort (N=496), Bayesian inversion recovered four behavioural phenotypes, reproducing 80–83% of cluster targets through distinct trait-vulnerability, physical-activity and affective-response parameter combinations. These phenotypes were primarily differentiated by digital-media overuse, physical activity, sleep and affective burden. Participant-specific inversion then generated virtual twins whose synthetic trajectories preserved observed behavioural traces: hidden Markov models trained on virtual-twin data reproduced state occupancy and transition patterns ( r =0.84–0.87 and 0.93–0.94). Forecasts outperformed causal mean and persistence baselines for short-horizon magnitude prediction and predicted affective-state changes with 66–78% balanced accuracy over 21 days. These findings establish CSDS as an interpretable framework for simulating individual behavioural dynamics and advancing personalised mental-health modelling.
Source: medRxiv
Institutions: King's College London, Max Planck Institute of Psychiatry, Deutsches Zentrum für Psychische Gesundheit, Ludwig-Maximilians-Universität München, MRC Cognition and Brain Sciences Unit, University of Cambridge, Max Planck Institute for Human Development, Stanford University, Harvard University, Mass General Brigham, University of Bari Aldo Moro, Ruhr University Bochum, Inserm, Aix-Marseille Université, Institut de Neurosciences des Systèmes
Language: English
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7171637467