Federated learning for violence incident prediction in a simulated cross-institutional psychiatric setting

Thomas Borger, Pablo Mosteiro Romero, Heysem Kaya, Emil Rijcken, Albert Salah, Floortje Scheepers, Marco Spruit

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Inpatient violence is a common and severe problem within psychiatry. Knowing who might become violent can influence staffing levels and mitigate severity. Predictive machine learning models can assess each patient’s likelihood of becoming violent based on clinical notes. Yet, while machine learning models benefit from having more data, data availability is limited as hospitals typically do not share their data for privacy preservation. Federated Learning (FL) can overcome the problem of data limitation by training models in a decentralised manner, without disclosing data between collaborators. However, although several FL approaches exist, none of these train Natural Language Processing models on clinical notes. In this work, we investigate the application of Federated Learning to clinical Natural Language Processing, applied to the task of Violence Risk Assessment by simulating a cross-institutional psychiatric setting. We train and compare four models: two local models, a federated model and a data-centralised model. Our results indicate that the federated model outperforms the local models and has similar performance as the data-centralised model. These findings suggest that Federated Learning can be used successfully in a cross-institutional setting and is a step towards new applications of Federated Learning based on clinical notes.
Original languageEnglish
Article number116720
Pages (from-to)1-9
Number of pages9
JournalExpert Systems with Applications
Volume199
DOIs
Publication statusPublished - 1 Aug 2022

Bibliographical note

Funding Information:
This work was supported by Utrecht University, The Netherlands , the PsyData team from UMC Utrecht, The Netherlands , and KPMG, The Netherlands n.v. Useful discussions were held with Sebastian Mildiner and Laurens Breij.

Publisher Copyright:
© 2022 The Authors

Keywords

  • Clinical notes
  • Federated learning
  • Neural networks
  • Psychiatry
  • Violence prediction

Fingerprint

Dive into the research topics of 'Federated learning for violence incident prediction in a simulated cross-institutional psychiatric setting'. Together they form a unique fingerprint.

Cite this