Artificial Intelligence (AI) and emerging technologies are revolutionising digital human models (DHMs), offering significant opportunities to enhance accessibility and inclusion in healthcare systems. This evolution is further amplified by the concept of the “digital twin”—a virtual representation of a human patient that is dynamically updated with real-world data. This paper explores the potential of explainable AI (XAI) in conjunction with digital twins to create transparent, interpretable, and responsible healthcare solutions, particularly through privacy-preserving techniques like federated learning. By integrating advanced technologies such as computer vision, natural language processing, and machine learning, DHMs can be designed to understand, predict, and simulate the behaviours and requirements of individuals with varying abilities and backgrounds, ultimately creating personalised digital twins for enhanced healthcare.
Preventive Healthcare Through Privacy-Preserving, Explainable and Inclusive Artificial Intelligence / Mahmud, M.; Brown, D. J.; Shen, Y.; Rahman, M. A.; He, J.; Kaiser, M. S.; Luqman, H.; Mistry, S.; Shaffi, N.; Viswan, V.; Rahman, M. M.; Mamun, S. A.; Sharmeen, T.; Alahmad, R.; Aradhya, V. N. M.; Hashmi, M. F.; Wang, S.; Ieracitano, C.; Mammone, N.; Doborjeh, M.; Ray, K.. - 16340:(2026), pp. 359-374. ( Late breaking papers from the 27th International Conference on Human-Computer Interaction, HCI International 2025 swe 2025) [10.1007/978-3-032-13022-8_25].
Preventive Healthcare Through Privacy-Preserving, Explainable and Inclusive Artificial Intelligence
Rahman M. A.;Ieracitano C.;
2026
Abstract
Artificial Intelligence (AI) and emerging technologies are revolutionising digital human models (DHMs), offering significant opportunities to enhance accessibility and inclusion in healthcare systems. This evolution is further amplified by the concept of the “digital twin”—a virtual representation of a human patient that is dynamically updated with real-world data. This paper explores the potential of explainable AI (XAI) in conjunction with digital twins to create transparent, interpretable, and responsible healthcare solutions, particularly through privacy-preserving techniques like federated learning. By integrating advanced technologies such as computer vision, natural language processing, and machine learning, DHMs can be designed to understand, predict, and simulate the behaviours and requirements of individuals with varying abilities and backgrounds, ultimately creating personalised digital twins for enhanced healthcare.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
