Modeling trajectories of mental health: challenges and opportunities

TL;DR

This paper explores modeling childhood mental health trajectories using longitudinal data, comparing latent class mixture models and Gaussian process models, highlighting their strengths and limitations for early risk prediction.

Contribution

It introduces a platform for defining subtypes of childhood social-emotional development using advanced models, aiming to improve early detection of mental health issues.

Findings

GP models nearly match LCMM accuracy in predicting trajectories

LCMMs are faster than GP models in computation

Current models lack sufficient accuracy for clinical use

Abstract

More than two thirds of mental health problems have their onset during childhood or adolescence. Identifying children at risk for mental illness later in life and predicting the type of illness is not easy. We set out to develop a platform to define subtypes of childhood social-emotional development using longitudinal, multifactorial trait-based measures. Subtypes discovered through this study could ultimately advance psychiatric knowledge of the early behavioural signs of mental illness. To this extent we have examined two types of models: latent class mixture models and GP-based models. Our findings indicate that while GP models come close in accuracy of predicting future trajectories, LCMMs predict the trajectories as well in a fraction of the time. Unfortunately, neither of the models are currently accurate enough to lead to immediate clinical impact. The available data related to the development of childhood mental health is often sparse with only a few time points measured and require novel methods with improved efficiency and accuracy.