A probabilistic framework for predicting disease dynamics: A case study of psychotic depression

[Display omitted] •A methodology that facilitates hypothesis generation in medical domains is proposed.•Structured hidden Markov models are proposed as effective models.•Predictive models for psychotic depression treatment are built.•Association between psychosis and depression and patient recovery is demonstrated.•Patient sensitivity to intervention is uncovered. Unsupervised learning is often used to obtain insight into the underlying structure of medical data, but it is not always clear how to use such structure in an effective way. In this paper, we propose a probabilistic framework for predicting disease dynamics guided by latent states. The framework is based on hidden Markov models and aims to facilitate the selection of hypotheses that might yield insight into the dynamics. We demonstrate this by using clinical trial data for psychotic depression treatment as a case study. The discovered latent structure and proposed outcome are then validated using standard depression criteria, and are shown to provide new insight into the heterogeneity of psychotic depression in terms of predictive symptoms for different interventions.