Leveraging artificial intelligence in advance care planning: A scoping review

Area of Science:

• Healthcare Informatics
• Artificial Intelligence in Medicine
• Clinical Decision Support

Background:

• Advance care planning (ACP) facilitates crucial future health decisions for individuals.
• Artificial intelligence (AI) shows potential to enhance healthcare processes, including ACP.
• The precise role and effectiveness of AI in facilitating ACP require comprehensive investigation.

Purpose of the Study:

• To systematically review and synthesize the current applications of AI in facilitating ACP.
• To identify the primary objectives, AI algorithms, data sources, and performance metrics used in AI-driven ACP research.
• To understand the scope and limitations of existing AI interventions in ACP.

Main Methods:

• A scoping review methodology was employed, adhering to established frameworks.
• A comprehensive literature search was conducted across major databases (PubMed, EMBASE, Web of Science, CINAHL, Cochrane Library, IEEE Xplore) up to July 2025.
• Descriptive analysis and narrative synthesis were utilized to summarize findings from 42 eligible studies.

Main Results:

• AI in ACP primarily focuses on detecting conversations/documents, identifying patients needing ACP, and promoting education.
• Rule-based natural language processing (NLP) and textual data are the most prevalent AI approaches.
• The application of advanced AI, such as generative AI, is limited, and performance evaluation often relies on discrimination metrics, showing significant variation.

Conclusions:

• Current AI applications in ACP are predominantly centered on data extraction from electronic health records and patient identification.
• There is a notable gap in the utilization of advanced AI technologies and standardized performance evaluation methods in ACP research.
• Further research is needed to explore the potential of advanced AI and establish robust evaluation frameworks to fully leverage AI in enhancing ACP.