Comparing Deep Learning and Classical Machine Learning Approaches for Predicting Inpatient Violence Incidents from Clinical Text

Machine learning techniques are increasingly being applied to clinical text that is already captured in the Electronic Health Record for the sake of delivering quality care. Applications for example include predicting patient outcomes, assessing risks, or performing diagnosis. In the past, good results have been obtained using classical techniques, such as bag-of-words features, in combination with statistical models. Recently however Deep Learning techniques, such as Word Embeddings and Recurrent Neural Networks, have shown to possibly have even greater potential. In this work, we apply several Deep Learning and classical machine learning techniques to the task of predicting violence incidents during psychiatric admission using clinical text that is already registered at the start of admission. For this purpose, we use a novel and previously unexplored dataset from the Psychiatry Department of the University Medical Center Utrecht in The Netherlands. Results show that predicting violence incidents with state-of-the-art performance is possible, and that using Deep Learning techniques provides a relatively small but consistent improvement in performance. We finally discuss the potential implication of our findings for the psychiatric practice.