Using Generative AI to Translate Administrative Claims Data into Narrative Summaries for Palliative Care Needs Assessment: A Case Study.

Journal: Studies in health technology and informatics
PMID:

Abstract

Community-based palliative care is a useful, but underutilized service to support seriously ill older adults to remain safely at home and improve quality of life. Clinical decision support tools can assist palliative care need assessments if presented in a way that is useful to clinicians. This case study explores the potential for generative artificial intelligence (AI) to translate diagnostic and billing codes from administrative data into a narrative format to facilitate clinical decision-making regarding palliative care need. Informatics structures for protecting patient confidentiality are described. Generative AI has the potential to support clinical decision-making but requires additional testing, validation, and refinement.

Authors

  • Kathryn H Bowles
    Visiting Nurse Service of New York, NY, USA; School of Nursing, University of Pennsylvania, PA, USA.
  • Carlin Brickner
    Science and Technology, Center for Home Care Policy and Research, VNS Health, New York, NY, USA.
  • Elizabeth A Luth
    Rutgers University and Robert Wood Johnson School of Medicine, New Brunswick, NJ., USA.