Leveraging Artificial Intelligence to Uncover Symptom Burden in Palliative Care: Analysis of Nonscheduled Visits Using a Phi-3 Small Language Model
This study highlights the substantial burden of symptom-driven NSVs in palliative care and demonstrates the effectiveness of using a SLM to identify and manage symptoms. Implementing such models in clinical practice can improve patient care by optimizing the allocation of health care resources and tailoring interventions to the needs of patients with advanced illnesses.
Authors
- Marcela González (ORCID: https://orcid.org/0000-0001-7176-7194)
- Antonia Demarchi
- Castellanos López
- Javier Retamales (ORCID: https://orcid.org/0000-0001-7051-0362)
- Nicolás Ramírez (ORCID: https://orcid.org/0000-0002-0444-8094)
- Virginia Chih-Yi Sun (ORCID: https://orcid.org/0000-0003-3129-4235)
- Juan Pablo Retamales
- Tamara Retamal
Institutions
- Chinese Academy of Science South America Center for Astronomy (CL)
- City of Hope (US)
- Complejo Asistencial Sótero del Río (CL)
Publication Details
- Journal
- JCO Global Oncology
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1200/go-24-00432
- Citations
- 2
- Primary Topic
- Palliative Care and End-of-Life Issues
- Type
- article
- Field-Weighted Citation Impact
- 3.76