No abstract

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.