Leveraging Artificial Intelligence to Uncover Symptom Burden in Palliative Care: Analysis of Nonscheduled Visits Using a Phi-3 Small Language Model.

Journal: JCO global oncology
PMID:

Abstract

PURPOSE: This study aimed to differentiate nonscheduled visits (NSVs) in an outpatient palliative care setting that are driven by or accompanied by uncontrolled symptoms from those that are administrative or routine, such as prescription refills and examination readings. A small language model (SLM) was used to enhance the detection and management of symptoms, thus improving health care resource allocation.

Authors

  • Javier Retamales
    Hospital Sotero del Río, Santiago, Chile.
  • Juan Pablo Retamales
    QJV, Santiago, Chile.
  • Ana Maria Demarchi
    Hospital Sotero del Río, Santiago, Chile.
  • Marcela Gonzalez
    Hospital Sotero del Río, Santiago, Chile.
  • Caroll Lopez
    Hospital Sotero del Río, Santiago, Chile.
  • Nina Ramirez
    Hospital Sotero del Río, Santiago, Chile.
  • Tamara Retamal
    Hospital Sotero del Río, Santiago, Chile.
  • Virginia Sun
    Department of Surgery, City of Hope National Medical Center, Duarte, California, USA.