Improving Access Trust in Healthcare Through Multimodal Deep Learning for Affective Computing

Abstract In healthcare domain, access trust is of prime importance paramount to ensure effective delivery of medical services. It also fosters positive patient-provider relationships. With the advancement of technology, affective computing has emerged as a promising approach to enhance access trust. It enables systems to understand and respond to human emotions. The research work investigates the application of multimodal deep learning techniques in affective computing to improve access trust in healthcare environment. A novel algorithm, "Belief-Emo-Fusion," is proposed, aiming to enhance the understanding and interpretation of emotions in healthcare. The research conducts a comprehensive simulation analysis, comparing the performance of Belief-Emo-Fusion with existing algorithms using simulation metrics: modal accuracy, ınference time, and F1-score. The study emphasizes the importance of emotion recognition and understanding in healthcare settings. The work highlights the role of deep learning models in facilitating empathetic and emotionally intelligent technologies. By addressing the challenges associated with affective computing, the proposed approach contributes to the development of more effective and reliable healthcare systems. The findings offer valuable insights for researchers and practitioners seeking to leverage deep learning techniques for enhancing trust and communication in healthcare environments.