Exploring the Role of ChatGPT in Enhancing Palliative Care for Sleep-Wake Disturbances
Open Access
Author:
Liu, Siqi
Graduate Program:
Informatics
Degree:
Master of Science
Document Type:
Master Thesis
Date of Defense:
March 05, 2025
Committee Members:
Saeed M Abdullah, Thesis Advisor/Co-Advisor Kenneth Huang, Committee Member Dongwon Lee, Professor in Charge/Director of Graduate Studies Luke Zhang, Committee Member
Keywords:
artificial intelligence sleep-wake disturbances medical care decision support large language model palliative care human computer interaction
Abstract:
Palliative care focuses on improving the quality of life for individuals with serious illnesses. This study explores the use of large language models (LLMs), specifically ChatGPT-4o, to generate interventions for patients in palliative care experiencing sleep-wake disturbances. Using a dataset of expert guidelines and benchmark interventions, we evaluated the model’s capability for generating personalized, empathetic, and guideline-adherent responses. The ChatGPT-4o model demonstrated 100% adherence to non-pharmacological intervention guidelines. Linguistic analysis of model outcomes indicated a positive tone, high levels of authenticity, and an empathetic style. These findings highlight the potential of LLMs to augment palliative care by providing tailored, empathetic, and actionable support for patients and care partners. We also discuss the implications of these findings for integrating LLMs into palliative care practices.
