发表机构
College of Health Solutions, Arizona State University; School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学健康解决方案学院; 亚利桑那州立大学计算与增强智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述针对数字健康领域可信AI研究缺口，构建框架梳理鲁棒性与可解释性的技术进展、应用考量与评估指标，为相关开发提供支持。
AI 中文摘要
确保AI系统的可信性对于将机器学习系统安全、符合伦理地集成到数字健康等高风险领域至关重要。在AI生命周期的各个阶段，从问题定义、数据收集到模型部署和人机交互，都需要解决鲁棒性、可解释性、公平性、可问责性和隐私等关键维度。尽管已有多项研究针对可信AI的不同方面展开工作，但针对医疗场景量身定制的鲁棒性与可解释性的聚焦性综合研究仍然有限。本综述通过将最新进展组织为一个易于理解的框架，突出技术与实践层面的考量，以满足这一需求。我们对方法、挑战与解决方案进行结构化概述，旨在支持研究人员与从业者开发面向数字健康的可靠、可解释的AI解决方案。本综述文章分为三个主要部分：第一，介绍可信AI的支柱，并讨论尤其在数字健康背景下的技术与伦理挑战；第二，探讨重症监护、新生儿健康、代谢健康等领域中特定于应用的可信性考量，强调鲁棒性与可解释性如何支撑可信性；最后，介绍旨在提升数据稀缺与分布偏移场景下鲁棒性的最新技术进展，以及从特征归因到基于梯度的解释、反事实解释等可解释AI方法。本文还进一步丰富了关于数字健康领域鲁棒性与可解释性贡献、大语言模型（LLMs）时代可信AI系统的开发，以及用于测量可信性及相关参数（如有效性、保真度、多样性）的各类评估指标的详细讨论。
英文摘要
Ensuring trust in AI systems is essential for the safe and ethical integration of machine learning systems into high-stakes domains such as digital health. Key dimensions, including robustness, explainability, fairness, accountability, and privacy, need to be addressed throughout the AI lifecycle, from problem formulation and data collection to model deployment and human interaction. While various contributions address different aspects of trustworthy AI, a focused synthesis on robustness and explainability, especially tailored to the healthcare context, remains limited. This review addresses that need by organizing recent advancements into an accessible framework, highlighting both technical and practical considerations. We present a structured overview of methods, challenges, and solutions, aiming to support researchers and practitioners in developing reliable and explainable AI solutions for digital health. This review article is organized into three main parts. First, we introduce the pillars of trustworthy AI and discuss the technical and ethical challenges, particularly in the context of digital health. Second, we explore application-specific trust considerations across domains such as intensive care, neonatal health, and metabolic health, highlighting how robustness and explainability support trust. Lastly, we present recent advancements in techniques aimed at improving robustness under data scarcity and distributional shifts, as well as explainable AI methods ranging from feature attribution to gradient-based interpretations and counterfactual explanations. This paper is further enriched with detailed discussions of the contributions toward robustness and explainability in digital health, the development of trustworthy AI systems in the era of LLMs, and various evaluation metrics for measuring trust and related parameters such as validity, fidelity, and diversity.
CommentsPreprint of the paper published in Progress in Biomedical Engineering. 26 pages, 5 figures
Journal refProgress in Biomedical Engineering, Volume 8, Number 2, Article 022007, 2026
