Scholarlink

<p>Generative artificial intelligence (AI), enabled digital twins are emerging as a transformative paradigm for precision medicine, enabling dynamic, patient-specific modeling across clinical care, drug development, and population health. Digital twins provide computational representations of biological systems, while generative AI enhances their capacity for data synthesis, prediction, and simulation under uncertainty. Despite rapid technological progress, the clinical translation of these systems remains limited by challenges in validation, safety, interpretability, and regulatory oversight. In this work, we present a structured analysis of generative AI–powered digital twins in healthcare, spanning patient-level modeling, clinical trials, and preclinical drug discovery. Beyond reviewing existing applications, we introduce a clinical-grade evaluation framework encompassing validation strategies, uncertainty calibration, safety monitoring, and synthetic data governance. By articulating both opportunities and unresolved barriers, this study provides a roadmap for the responsible deployment of generative AI–enabled digital twins in precision medicine.</p>

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

Generative AI empowered digital twins for advancing precision medicine

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月27日

查看全文
  • Hossein Akbarialiabad,
  • Ehsan Safaee,
  • Mehdi Letafati,
  • Jian Gong,
  • Sancy A. Leachman,
  • Ayman Grada,
  • Amirmohammad Pasdar,
  • Maryam Janatifar,
  • Farhan Shakil,
  • Christopher G. Bunick,
  • Dedee F. Murrell,
  • Michelle Tarbox,
  • Cameron West,
  • Alireza Haghighi

摘要

Generative artificial intelligence (AI), enabled digital twins are emerging as a transformative paradigm for precision medicine, enabling dynamic, patient-specific modeling across clinical care, drug development, and population health. Digital twins provide computational representations of biological systems, while generative AI enhances their capacity for data synthesis, prediction, and simulation under uncertainty. Despite rapid technological progress, the clinical translation of these systems remains limited by challenges in validation, safety, interpretability, and regulatory oversight. In this work, we present a structured analysis of generative AI–powered digital twins in healthcare, spanning patient-level modeling, clinical trials, and preclinical drug discovery. Beyond reviewing existing applications, we introduce a clinical-grade evaluation framework encompassing validation strategies, uncertainty calibration, safety monitoring, and synthetic data governance. By articulating both opportunities and unresolved barriers, this study provides a roadmap for the responsible deployment of generative AI–enabled digital twins in precision medicine.