Artificial intelligence in symptom management and clinical decision support for palliative care.

BACKGROUND

Artificial intelligence (AI) is increasingly applied to palliative care to enhance symptom management and decision support. However, the breadth and implementation strategies of such technologies remain underexplored.

AIM/

OBJECTIVES

This scoping review aimed to map empirical studies from 2015 to 2025 that used AI for symptom assessment, mortality prediction and care planning in palliative settings.

METHODS

The review followed Arksey and O'Malley's five-stage framework for scoping reviews and was reported according to PRISMA-ScR guidelines. Included studies were appraised using the Mixed Methods Appraisal Tool.

RESULTS

A total of 12 peer-reviewed studies were included, revealing five major themes: (1) Predictive modeling for mortality and referral, enabling early identification of high-risk patients; (2) Automated symptom detection, improving distress surveillance via NLP and decision trees; (3) Wearable and time-series forecasting, allowing real-time physiologic tracking; (4) Workflow integration, demonstrating seamless adoption of AI tools in clinical systems; and (5) Explainability and trust, where interpretable outputs enhanced clinician confidence. These studies showed improved symptom control, timely referrals and interdisciplinary coordination.

CONCLUSION

AI offers promising solutions to enhance palliative nursing through proactive, data-driven care. Ethical implementation, training, and validation are key to sustainable adoption.