Automatic structure estimation of predictive models for symptom development

TL;DR

This paper introduces a multi-objective optimization method to automatically infer predictive model structures from ecological momentary assessment data, aiming to improve early detection of symptom development and reduce drop-out in online mental health treatments.

Contribution

It presents a novel two-staged multi-objective optimization process for automatic structure estimation of temporal-causal network models in mental health prediction.

Findings

Achieves models with optimal prediction performance for different mental health concepts.

Enables selection of disorder-specific models tailored to specific applications.

Improves early identification of clients at risk of drop-out.

Abstract

Online mental health treatment has the premise to meet the increasing demand for mental health treatment at a lower cost than traditional treatment. However, online treatment suffers from high drop-out rates, which might negate their cost effectiveness. Predictive models might aid in early identification of deviating clients which allows to target them directly to prevent drop-out and improve treatment outcomes. We propose a two-staged multi-objective optimization process to automatically infer model structures based on ecological momentary assessment for prediction of future symptom development. The proposed multi-objective optimization approach results in a temporal-causal network model with the best prediction performance for each concept. This allows for a selection of a disorder-specific model structure based on the envisioned field of application.