Scholarlink

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.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Preventive Healthcare Through Privacy-Preserving, Explainable and Inclusive Artificial Intelligence

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mufti Mahmud,
  • David J. Brown,
  • Yuan Shen,
  • Muhammad Arifur Rahman,
  • Jun He,
  • M Shamim Kaiser,
  • Hamzah Luqman,
  • Sajib Mistry,
  • Noushath Shaffi,
  • Vimbi Viswan,
  • M Mostafizur Rahman,
  • Shamim Al Mamun,
  • Tamanna Sharmeen,
  • Rasha Alahmad,
  • V. N. Manjunath Aradhya,
  • Mohammad Farukh Hashmi,
  • Shuqiang Wang,
  • Cosimo Ieracitano,
  • Nadia Mammone,
  • Maryam Doborjeh,
  • Kanad Ray

摘要

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.