Predicting hospitalization following psychiatric crisis care using machine learning.

Journal: BMC medical informatics and decision making
Published Date:

Abstract

BACKGROUND: Accurate prediction models for whether patients on the verge of a psychiatric criseis need hospitalization are lacking and machine learning methods may help improve the accuracy of psychiatric hospitalization prediction models. In this paper we evaluate the accuracy of ten machine learning algorithms, including the generalized linear model (GLM/logistic regression) to predict psychiatric hospitalization in the first 12 months after a psychiatric crisis care contact. We also evaluate an ensemble model to optimize the accuracy and we explore individual predictors of hospitalization.

Authors

  • Matthijs Blankers
    Department of Research, Arkin Mental Health Care, Klaprozenweg 111, 1033NN, Amsterdam, The Netherlands. matthijs.blankers@arkin.nl.
  • Louk F M van der Post
    Department of Research, Arkin Mental Health Care, Klaprozenweg 111, 1033NN, Amsterdam, The Netherlands.
  • Jack J M Dekker
    Department of Research, Arkin Mental Health Care, Klaprozenweg 111, 1033NN, Amsterdam, The Netherlands.