โก Quick Summary
This scoping review highlights the potential of AI in palliative care, particularly in areas like prognostication and symptom management. However, it reveals significant gaps in validation, transparency, and ethical frameworks that must be addressed for safe integration into clinical practice.
๐ Key Details
- ๐ Dataset: 4,747 unique records, 125 studies included
- ๐งฉ Focus areas: Prognostication, symptom management, decision support
- โ๏ธ Methodologies: AI applications including machine learning and natural language processing
- ๐ Key findings: 86% of studies were retrospective proof-of-concept designs
๐ Key Takeaways
- ๐ AI applications in palliative care are primarily focused on mortality prediction.
- ๐ก Most studies (63) concentrated on cancer populations.
- ๐ฉโ๐ฌ Data sources predominantly utilized structured electronic health records.
- ๐ Limited transparency with only 15% of studies sharing code.
- ๐ค Ethical frameworks for evaluation were notably absent in the reviewed studies.
- ๐ Majority of studies were published in the last three years, indicating a growing interest.
- ๐ Future research should focus on external validation and broader patient data inclusion.
๐ Background
The integration of artificial intelligence (AI) into healthcare has shown promise in various fields, and palliative care is no exception. AI technologies can potentially enhance patient outcomes by improving prognostication, symptom management, and decision support in sensitive end-of-life settings. However, the current landscape reveals foundational gaps that must be addressed to ensure these tools are both effective and ethically sound.
๐๏ธ Study
This scoping review systematically mapped the landscape of AI applications in palliative and hospice care. The researchers conducted a comprehensive search across multiple databases, including PubMed and Embase, to identify studies that applied AI methodologies in adult palliative care contexts. The review focused on three key domains: the purposes and data sources of AI models, the methods and extent of model validation, and the degree of transparency and reproducibility.
๐ Results
Out of 4,747 unique records, 125 studies met the inclusion criteria. A significant finding was that over half of these studies were published in the last three years, predominantly from the United States. Most studies (86%) were retrospective proof-of-concept designs, with only a handful being randomized controlled trials or prospective evaluations. The primary focus was on mortality prediction, particularly in cancer populations, with structured electronic health record data being the most common input. Alarmingly, transparency was limited, with only 15% of studies sharing code and 11% providing data access.
๐ Impact and Implications
The findings of this review underscore the early development stage of AI in palliative care. While there is significant promise in areas such as prognosis and documentation support, the current limitations in validation, cross-site testing, and transparency hinder clinical applicability. Addressing these gaps is crucial for the responsible integration of AI technologies in palliative care, ensuring that they are reliable, safe, and trustworthy for patients and healthcare providers alike.
๐ฎ Conclusion
This scoping review highlights the incredible potential of AI in enhancing palliative care, particularly in improving prognostication and symptom management. However, the identified gaps in validation, transparency, and ethical considerations must be addressed to facilitate the safe and effective use of these technologies. Future research should prioritize external validation and the adoption of open science practices to ensure that AI tools can be trusted in sensitive end-of-life settings.
๐ฌ Your comments
What are your thoughts on the integration of AI in palliative care? Do you see it as a beneficial tool or are there concerns that need to be addressed? ๐ฌ Join the conversation in the comments below or connect with us on social media:
AI in Palliative Care: A Scoping Review of Foundational Gaps and Future Directions for Responsible Innovation.
Abstract
BACKGROUND: AI holds increasing promise for enhancing palliative care through applications in prognostication, symptom management, and decision support. However, the utilization of real-world data, the rigor of validation, and the transparency and reproducibility of these AI tools remain largely unexamined, posing critical considerations for their safe and ethical integration in sensitive end-of-life settings.
OBJECTIVES: This scoping review systematically mapped the landscape of AI applications in palliative and hospice care, focusing on three key domains: (1) the purposes and data sources of AI models; (2) the methods and extent of model validation and generalizability; and (3) the degree of transparency and reproducibility.
METHODS: A comprehensive search was conducted across multiple databases (e.g., PubMed/MEDLINE, Embase, IEEE Xplore, Web of Science, ClinicalTrials.gov) from inception to December 31, 2023. Studies of any design applying AI (including machine learning or natural language processing) in palliative or hospice contexts for adults were included. Two independent reviewers screened studies and charted data on study context, patient population, data type, AI methodology, outcome, evaluation approach, and indicators of model generalizability, transparency and reproducibility.
RESULTS: From 4,747 unique records, 125 studies met inclusion criteria, with over half published in the last three years, predominantly from the United States. Most studies (86%) were retrospective proof-of-concept designs, with few randomized controlled trials (nโฏ=โฏ7) or prospective evaluations (nโฏ=โฏ6). AI applications primarily focused on mortality prediction (nโฏ=โฏ63) in cancer populations (nโฏ=โฏ62), followed by advance care planning (nโฏ=โฏ18) and symptom assessment (nโฏ=โฏ17). Structured electronic health record data were the most common input (nโฏ=โฏ67, 54%). Transparency was limited, with only 19 studies (15%) sharing code and 14 (11%) providing data access; none adhered to AI-specific reporting guidelines. Ethical frameworks for evaluation were notably absent.
CONCLUSION: AI in palliative care remains in early development, showing promise in areas such as prognosis and documentation support. However, limited validation, insufficient cross-site testing, and lack of transparency currently limit clinical applicability. Future research should emphasize external validation, inclusion of broader patient data, and adoption of open science practices to ensure these tools are reliable, safe, and trustworthy.
Author: [‘Bozkurt S’, ‘Fereydooni S’, ‘Kar I’, ‘Chalmers CD’, ‘Leslie SL’, ‘Pathak R’, ‘Walling AM’, ‘Lindvall C’, ‘Lorenz K’, ‘Parikh R’, ‘Quest T’, ‘Giannitrapani K’, ‘Kavalieratos D’]
Journal: J Pain Symptom Manage
Citation: Bozkurt S, et al. AI in Palliative Care: A Scoping Review of Foundational Gaps and Future Directions for Responsible Innovation. AI in Palliative Care: A Scoping Review of Foundational Gaps and Future Directions for Responsible Innovation. 2025; (unknown volume):(unknown pages). doi: 10.1016/j.jpainsymman.2025.08.009