eWound-PRIOR: An Ensemble Framework for Cases Prioritization After Orthopedic Surgeries

Authors

Felipe Neves, Universidade Federal de Juiz de Fora
Morgan Jennings, The University of Western Ontario
Miriam Capretz, The University of Western Ontario
Dianne Bryant, The University of Western Ontario
Fernanda Campos, Universidade Federal de Juiz de Fora
Victor Ströele, Universidade Federal de Juiz de Fora

Document Type

Conference Proceeding

Publication Date

1-1-2021

Journal

Lecture Notes in Networks and Systems

Volume

158 LNNS

First Page

113

Last Page

125

URL with Digital Object Identifier

10.1007/978-3-030-61105-7_12

Abstract

© 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG. Patient follow-up appointments are an imperative part of the healthcare model to ensure safe patient recovery and proper course of treatment. The use of mobile devices can help patient monitoring and predictive approaches can provide computational support to identify deteriorating cases. Aiming to aggregate the data produced by those devices with the power of predictive approaches, this paper proposes the eWound-PRIOR framework to provide a remote assessment of postoperative orthopedic wounds. Our approach uses Artificial Intelligence (AI) techniques to process patients’ data related to postoperative wound healing and makes predictions as to whether the patient requires an in-person assessment or not. The experiment results showed that the predictions are promising and adherent to the application context, even if the on-line questionnaire had impaired the training model and the performance.