Dutta Roy Taposh P
Responsible AI, Kaiser Permanente, Oakland, USA.
Bioethics, Harvard Medical School, Boston, USA.
Cureus. 2025 Mar 12;17(3):e80494. doi: 10.7759/cureus.80494. eCollection 2025 Mar.
Healthcare professionals face complex ethical dilemmas in clinical settings in cases involving end-of-life care, informed consent, and surrogate decision-making. These nuanced situations often lead to moral distress among care providers. This paper introduces the Bioethics Artificial Intelligence Advisory (BAIA) framework, a novel and innovative approach that leverages artificial intelligence (AI) to support clinical ethical decision-making. The BAIA framework integrates multiple bioethical approaches, including principlism, casuistry, and narrative ethics, with advanced AI capabilities to provide comprehensive decision support. The framework employs a structured methodology that includes data collection, paradigmatic case review, analysis through "mattering maps," and scenario-based decision reasoning. A detailed analysis of two challenging cases, an end-of-life care decision and a complex conjoined twins case, demonstrates BAIA's potential to harmonize diverse ethical perspectives while reducing the moral burden on healthcare providers. The framework's agentic architecture additionally allows integration with any new and existing ethical AI systems like METHAD, Delphi, and EAIFT, enabling multiframework collaboration. This work also acknowledges limitations related to data quality, bias, and complexity of ethical decisions and proposes mitigation strategies, including standardized databases, fairness algorithms, and maintaining human oversight. Thus, this work represents a significant step toward combining technological advancement in agentic AI with established bioethical principles to improve the quality and consistency of clinical ethical decision-making, thus reducing moral distress for clinicians.
在涉及临终关怀、知情同意和替代决策的临床案例中，医疗保健专业人员面临着复杂的伦理困境。这些细微差别往往会给护理人员带来道德困扰。本文介绍了生物伦理学人工智能咨询（BAIA）框架，这是一种新颖且创新的方法，利用人工智能（AI）来支持临床伦理决策。BAIA框架将多种生物伦理学方法，包括原则主义、决疑法和叙事伦理学，与先进的人工智能能力相结合，以提供全面的决策支持。该框架采用一种结构化方法，包括数据收集、典型案例审查、通过“重要性地图”进行分析以及基于场景的决策推理。对两个具有挑战性的案例进行详细分析，一个是临终关怀决策案例，另一个是复杂的连体双胞胎案例，展示了BAIA在协调不同伦理观点的同时减轻医疗保健提供者道德负担的潜力。该框架的智能架构还允许与任何新的和现有的伦理人工智能系统（如METHAD、Delphi和EAIFT）集成，实现多框架协作。这项工作也认识到与数据质量、偏差和伦理决策复杂性相关的局限性，并提出了缓解策略，包括标准化数据库、公平算法以及保持人工监督。因此，这项工作代表了朝着将智能人工智能的技术进步与既定的生物伦理学原则相结合迈出的重要一步，以提高临床伦理决策的质量和一致性，从而减轻临床医生的道德困扰。
