The 'at risk mental state' (ARMS) paradigm has been introduced in psychiatry to study prodromal phases of schizophrenia. With time it was seen that the ARMS state can also precede mental disorders other than schizophrenia, such as depression and anxiety. However, several problems hamper the paradigm's use in preventative medicine, such as varying transition rates across studies, the use of non-naturalistic samples, and the multifactorial nature of psychiatric disorders. To strengthen ARMS predictive power, there is a need for a holistic model incorporating-in an unbiased fashion-the small-effect factors that cause mental disorders. Bayesian networks, a probabilistic graphical model, was used in a populational cohort of 83 ARMS individuals to predict conversion to psychiatric illness. Nine predictors-including state, trait, biological and environmental factors-were inputted. Dopamine receptor 2 polymorphism, high private religiosity, and childhood trauma remained in the final model, which reached an 85.51% (SD = 0.1190) accuracy level in predicting conversion. This is the first time a robust model was produced with Bayesian networks to predict psychiatric illness among at risk individuals from the general population. This could be an important tool to strengthen predictive measures in psychiatry which should be replicated in larger samples to provide the model further learning.
Keywords: Clinical high risk; Dopamine; Machine learning; Religiosity; Schizophrenia.
Copyright © 2021 Elsevier B.V. All rights reserved.