Deep Learning for Cancer Symptoms Monitoring on the Basis of Electronic Health Record Unstructured Clinical Notes.

Journal: JCO clinical cancer informatics
PMID: 35714301

Abstract

PURPOSE: Symptoms are vital outcomes for cancer clinical trials, observational research, and population-level surveillance. Patient-reported outcomes (PROs) are valuable for monitoring symptoms, yet there are many challenges to collecting PROs at scale. We sought to develop, test, and externally validate a deep learning model to extract symptoms from unstructured clinical notes in the electronic health record.

Authors

  • Charlotta Lindvall
    Harvard Medical School, Boston, MA.
  • Chih-Ying Deng
    Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute (C.L., CY.D.,E.M., N.A., JR.L., JA.T.), Boston, Massachusetts.
  • Nicole D Agaronnik
    Harvard Medical School, Boston, MA.
  • Anne Kwok
    Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, 450 Brookline Ave, Boston, MA, 02115, United States.
  • Soujanya Samineni
    Dana-Farber Cancer Institute, Boston, MA, USA.
  • Renato Umeton
    Dana-Farber Cancer Institute, Boston, MA, USA.
  • Warren Mackie-Jenkins
    Dana-Farber Cancer Institute, Boston, MA.
  • Kenneth L Kehl
    Department of Medicine, Dana-Farber Cancer Institute, Boston, MA, 02215, United States.
  • James A Tulsky
    Harvard Medical School, Boston, MA.
  • Andrea C Enzinger
    Dana-Farber Cancer Institute, Boston, MA.

Keywords

External Resources

Popular Topics
Recent Journals