Brett M. Prestia, DO, HMDC: No financial relationships to disclose
Alex Choi, MD: No financial relationships to disclose
Key Message: The AI Guys are at it again, with even more updates! This session reviews emerging research on how AI-driven innovations can strengthen team efficiency, patient outcomes, and equity. AI may not hold a hand or offer a hug, but it might help us do both more often and more effectively.
Abstract: Back by popular demand! The AI Guys are returning to AAHPM to provide the latest and greatest updates in the fast-paced intersection of artificial intelligence (AI) and hospice/palliative medicine. This presentation will cover a few of the most impactful studies that enhance care delivery, improve workflow efficiency, and personalize patient support with particular attention to studies involving workflow integration, digital health tools, and predictive analytics.
We will survey a small but growing body of evidence supporting AI use in hospice-specific domains, such as automated triaging of referrals, prognostication models for timelier hospice enrollment, and natural language processing tools to streamline documentation and symptom tracking. Also reviewing studies that demonstrate AI’s ability to improve interdisciplinary team efficiency, reduce documentation burden, and support decision-making in complex care scenarios.
In palliative care, AI applications are more developed, with successful implementation in hospital-based symptom prediction tools, early identification of serious illness trajectories, and risk stratification for resource allocation. Across settings, machine learning models have been used to forecast health decline and enhance equity by detecting disparities in access and utilization.
While our review is not exhaustive, the studies curated suggest that AI can serve as a scalable, quality-enhancing solution aligned with hospice values when developed and applied ethically. The presentation will synthesize key findings, assess readiness for clinical adoption, and identify opportunities for quality improvement, workforce support, and equity-promoting interventions. While the heart of hospice remains human, AI offers a data-driven compass to guide us more effectively.
References: 1) Wilson PM et al. – Effect of an Artificial Intelligence Decision Support Tool on Palliative Care Referral in Hospitalized Patients: A Randomized Clinical Trial J Pain Symptom Manage. 2023 Jul;66(1):24-32. doi: 10.1016/j.jpainsymman.2023.02.317. Epub 2023 Feb 24.
2) Owusuaa C, et al. Development of a Clinical Prediction Model for 1-Year Mortality in Patients With Advanced Cancer. JAMA Netw Open. 2022;5(11):e2244350. doi:10.1001/jamanetworkopen.2022.44350
3) Gaber, F et al. Evaluating large language model workflows in clinical decision support for triage and referral and diagnosis. npj Digit. Med. 8, 263 (2025). https://doi.org/10.1038/s41746-025-01684-1
4) Jacob J. Strand et al. Performance of an artificial intelligence/machine learning model designed to identify hospitalized patients with cancer who could benefit from timely specialized palliative care delivery.. JCO 42, 1559-1559(2024). DOI:10.1200/JCO.2024.42.16_suppl.1559
Learning Objectives:
Upon successful completion, participants will be able to apply evidence-based AI tools and workflow strategies to optimize hospice and palliative care delivery within their clinical practice settings.
Upon successful completion, participants will be able to evaluate emerging artificial intelligence innovations to develop quality improvement initiatives that enhance patient outcomes and interdisciplinary team efficiency in serious illness care.
