Application of artificial intelligence in palliative care: a bibliometric analysis of research hotspots and trends

Abstract

Background: Palliative care, essential for improving quality of life in patients with serious illnesses, faces challenges such as resource limitations, workforce shortages, and the complexity of personalized care. AI's capabilities in data analysis and decision-making offer opportunities to optimize symptom management, predict end-of-life risks, and tailor care plans. However, existing research emphasizes isolated AI technologies rather than systematic evaluations of its developmental trajectory in palliative care, particularly through bibliometric and visualization studies. This gap obscures trends in technological applications, interdisciplinary collaboration pathways, and research hotspots, potentially hindering AI's practical innovation in the field.

Objective: This study employs bibliometric methods to analyze research trends in AI-driven palliative care, mapping knowledge structures and identifying hotspots to inform future advancements.

Methods: Data from the Web of Science Core Collection (inception to February 28, 2024) were analyzed using HistCite for bibliometric aggregation, VOSviewer for co-occurrence analysis, and CiteSpace for keyword trends.

Results: Among 246 publications from 45 countries, 615 institutions, and 1,456 authors, output surged notably between 2020 and 2024. The U.S. and the Journal of Pain and Symptom Management led contributions. Keyword analysis highlighted research foci on deep learning, neural networks, quality-of-life enhancement, survival prediction, AI model development, and clinical optimization. Emerging trends emphasize machine learning and holistic AI integration.

Conclusion: Despite the increasing number of related studies in recent years, the field remains in its early developmental stage, indicating vast potential for further research. Studies have shown that international collaboration, particularly between the United States and China, is crucial for enhancing global academic influence. Prominent institutions in the United States, such as Harvard Medical School and the University of Pennsylvania, have led research in this area, while the involvement of other countries, especially developing nations, still requires strengthening. Technological analyses reveal that machine learning, deep learning, and natural language processing are becoming increasingly significant in palliative care. Future research will focus on improving patient quality of life, personalized treatment, and disease prognosis prediction, with an emphasis on interdisciplinary collaboration and the integration of technology with clinical practice to foster the innovative development of artificial intelligence in palliative care.

Systematic review registration: https://osf.io/, identifier https://doi.org/10.17605/OSF.IO/YCHNQ.

Keywords: artificial intelligence; bibliometric analysis; nursing care; palliative care; visual analytics.

FIGURE 1

Flowchart of the literature-screening process.

FIGURE 2

Publication output and the TLCS over time. TLCS, total local citation score.

FIGURE 3

Visualization of research networks of countries/regions.

FIGURE 4

Visualization of research networks of institutions.

FIGURE 5

Visualization of research networks of authors.

FIGURE 6

Keyword co-occurrence network.

FIGURE 7

Top 15 keywords with the strongest citation bursts.