Open AccessMobile Convolutional Neural Network for Neonatal Pain Assessment
Author(s) -
Lucas Pereira Carlini,
Leonardo Ferreira,
Gabriel de Almeida Sá Coutrin,
Victor V. Varoto,
Tatiany Marcondes,
Rita de Cássia Xavier Balda,
Marina Barros,
Ruth Guinsburg,
Carlos Eduardo Thomaz
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.52591/lxai202106258
Subject(s) - facial expression , convolutional neural network , neonatal intensive care unit , pain assessment , generalization , psychological intervention , computer science , perception , expression (computer science) , recurrent neural network , nonverbal communication , pain management , medicine , physical medicine and rehabilitation , artificial intelligence , artificial neural network , physical therapy , psychology , pediatrics , developmental psychology , neuroscience , nursing , mathematical analysis , mathematics , programming language
More than 500 painful interventions are carried out during the hospitalization of a newborn baby in an Intensive Care Unit. Since a direct and objective verbal communication by neonates is unlikely, this work proposes and implements a computational framework to automatically classify the neonatal pain based on its facial expression. Our findings showed promising results to correctly identify the facial expression of pain in neonates with high accuracy and generalization capability, highlighting as well sound facial regions that agree with pain scales used by neonatologists and with the visual perception of adults when assessing pain in neonates, whether they are health professionals or not.