The Role of Artificial Intelligence in Palliative Care: A Scoping Review
TL;DR
It is indicated that AI holds significant potential to improve symptom management, support clinical decisions, and enable data-driven interventions in palliative care, however, several challenges must be addressed for sustainable and effective implementation.
Abstract
Palliative care is a holistic, multidisciplinary approach aimed at improving the quality of life for patients with life-limiting illnesses and their families. Despite the global need for these services, many patients—especially in low-income countries—lack adequate access. Artificial Intelligence (AI) has emerged as a promising tool to enhance palliative care delivery by supporting early identification of patient needs, optimizing clinical decision-making, and improving patient outcomes. This scoping review examined the applications of AI in palliative care. A systematic search was conducted in PubMed, Scopus, and Web of Science up to June 2025, ultimately identifying 8 empirical studies that met the inclusion criteria. These studies were carried out across 5 countries and involved diverse patient populations, including advanced cancer, organ failure, dementia, and traumatic brain injury. AI applications were categorized into five main areas: (1) evaluating chatbot responses (e.g., ChatGPT, Gemini, Copilot), which revealed inadequate readability and quality; (2) identifying communication silences in patient-provider conversations using machine learning; (3) supporting clinical documentation and decision-making to reduce clinician workload; (4) analyzing inequalities in access to palliative care through predictive algorithms; and (5) predicting disease progression and patient status using longitudinal symptom data. The findings indicate that AI holds significant potential to improve symptom management, support clinical decisions, and enable data-driven interventions in palliative care. However, several challenges must be addressed for sustainable and effective implementation, including poor readability of AI-generated content, ethical concerns, patient privacy issues, and disparities in access to technology. Future research should focus on broader and more diverse populations, integrate survival prediction models, and carefully consider the ethical, regulatory, and organizational dimensions of AI integration into palliative care practice.