Automated facial recognition system using deep learning for pain assessment in adults with cerebral palsy

Abstract

[eng] <p><strong><em>Objective: </em></strong><em>Assessing pain in individuals with neurological conditions like cerebral palsy is challenging due to limitedself-reporting and expression abilities. Current methods lack sensitivity and specificity, underlining the need for a reliableevaluation protocol. An automated facial recognition system could revolutionize pain assessment for such patients.The research focuses on two primary goals: developing a dataset of facial pain expressions for individuals with cerebralpalsy and creating a deep learning-based automated system for pain assessment tailored to this group.</em><strong><em>Methods: </em></strong><em>The study trained ten neural networks using three pain image databases and a newly curated CP-PAIN Dataset of109 images from cerebral palsy patients, classified by experts using the Facial Action Coding System.</em><strong><em>Results:</em></strong><em> The InceptionV3 model demonstrated promising results, achieving 62.67% accuracy and a 61.12% F1 score on theCP-PAIN dataset. Explainable AI techniques confirmed the consistency of crucial features for pain identification across models.</em><strong><em>Conclusion: </em></strong><em>The study underscores the potential of deep learning in developing reliable pain detection systems using facialrecognition for individuals with communication impairments due to neurological conditions. A more extensive and diversedataset could further enhance the models’ sensitivity to subtle pain expressions in cerebral palsy patients and possiblyextend to other complex neurological disorders. This research marks a significant step toward more empathetic and accuratepain management for vulnerable populations.</em></p>