โก Quick Summary
This scoping review explores the use of artificial intelligence (AI) in Advance Care Planning (ACP), highlighting its potential to enhance decision-making and identify patients who may benefit from ACP. Despite promising results, challenges regarding data transparency and code availability persist.
๐ Key Details
- ๐ Studies Reviewed: 41 research articles and conference papers
- ๐งฉ Focus Areas: Identifying patients for ACP, initiating discussions, and documenting ACP information
- โ๏ธ Analytical Methods: Predominantly logistic regression (15 studies)
- ๐ Performance Metrics: 28 models showed good to very good performance
๐ Key Takeaways
- ๐ค AI applications in ACP can optimize patient care and decision-making.
- ๐ Most studies focused on identifying individuals who might benefit from ACP.
- ๐ Transparency issues were noted, with many studies lacking data and code availability.
- ๐ฅ Logistic regression was the most common analytical method used.
- ๐ Future research should prioritize open-source code to enhance reproducibility.
- ๐ก Novel AI approaches could support the review and updating of ACP information.
๐ Background
Advance Care Planning (ACP) is a crucial process that empowers individuals to make informed decisions about their future healthcare. However, barriers such as time constraints and unclear professional responsibilities often hinder its implementation. The integration of artificial intelligence (AI) into ACP processes presents an opportunity to overcome these challenges and improve patient outcomes.
๐๏ธ Study
This scoping review utilized the Arksey and O’Malley framework and PRISMA-ScR guidelines to analyze the current landscape of AI applications in ACP. The researchers conducted a comprehensive search across electronic databases and preprint servers, focusing on studies published in the last decade that addressed the intersection of AI and ACP.
๐ Results
The review included 41 studies, primarily utilizing retrospective cohort designs and real-world electronic health record data. A significant majority (39 studies) concentrated on identifying patients who could benefit from ACP, while fewer addressed initiating discussions (10 studies) or documenting ACP information (8 studies). Notably, 28 models demonstrated good to very good performance, yet concerns regarding data transparency and reproducibility were prevalent, with 17 studies lacking data availability and 36 lacking code availability.
๐ Impact and Implications
The findings of this review underscore the potential of AI to revolutionize Advance Care Planning by enhancing decision-making processes and identifying patients in need of ACP. However, the challenges related to data and code transparency must be addressed to ensure the reliability and reproducibility of AI models. By prioritizing these aspects, future research can pave the way for more effective and trustworthy AI applications in palliative care.
๐ฎ Conclusion
This scoping review highlights the promising role of artificial intelligence in Advance Care Planning, with many studies reporting models that predict patient outcomes effectively. However, significant challenges remain, particularly regarding data transparency and code availability. Moving forward, it is essential for researchers to focus on these issues to facilitate rigorous evaluation and foster innovation in AI-based ACP approaches.
๐ฌ Your comments
What are your thoughts on the integration of AI in Advance Care Planning? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
Artificial intelligence-based approaches for advance care planning: a scoping review.
Abstract
BACKGROUND: Advance Care Planning (ACP) empowers individuals to make informed decisions about their future healthcare. However, barriers including time constraints and a lack of clarity on professional responsibilities for ACP hinder its implementation. The application of artificial intelligence (AI) could potentially optimise elements of ACP in practice by, for example, identifying patients for whom ACP may be relevant and aiding ACP-related decision-making. However, it is unclear how applications of AI for ACP are currently being used in the delivery of palliative care.
OBJECTIVES: To explore the use of AI models for ACP, identifying key features that influence model performance, transparency of data used, source code availability, and generalizability.
METHODS: A scoping review was conducted using the Arksey and O’Malley framework and the PRISMA-ScR guidelines. Electronic databases (Scopus and Web of Science (WoS)) and seven preprint servers were searched to identify published research articles and conference papers in English, German and French for the last 10รย years’ records. Our search strategy was based on terms for ACP and artificial intelligence models (including machine learning). The GRADE approach was used to assess the quality of included studies.
RESULTS: Included studies (Nโ=โ41) predominantly used retrospective cohort designs and real-world electronic health record data. Most studies (nโ=โ39) focused on identifying individuals who might benefit from ACP, while fewer studies addressed initiating ACP discussions (nโ=โ10) or documenting and sharing ACP information (nโ=โ8). Among AI and machine learning models, logistic regression was the most frequent analytical method (nโ=โ15). Most models (nโ=โ28) demonstrated good to very good performance. However, concerns remain regarding data and code availability, as many studies lacked transparency and reproducibility (nโ=โ17 and nโ=โ36, respectively).
CONCLUSION: Most studies report models with promising results for predicting patient outcomes and supporting decision-making, but significant challenges remain, particularly regarding data and code availability. Future research should prioritize transparency and open-source code to facilitate rigorous evaluation. There is scope to explore novel AI-based approaches to ACP, including to support processes surrounding the review and updating of ACP information.
Author: [‘Arioz U’, ‘Allsop MJ’, ‘Goodman WD’, ‘Timmons S’, ‘Simbirtseva K’, ‘Mlakar I’, ‘Mocnik G’]
Journal: BMC Palliat Care
Citation: Arioz U, et al. Artificial intelligence-based approaches for advance care planning: a scoping review. Artificial intelligence-based approaches for advance care planning: a scoping review. 2025; 24:268. doi: 10.1186/s12904-025-01827-x