Placement: University of Pennsylvania
Co-Mentors: Kenrick Cato, PhD, RN, CPHIMS, FAAN, Nurse Scientist – Pediatric Data and Analytics, Children’s Hospital of Philadelphia; Professor of Nursing, Clinician Educator, University of Pennsylvania School of Nursing
Jiyoun Song, PhD, AGACNP-BC, APRN, NRSA Postdoctoral Research Fellow, NewCourtland Center for Transitions and Health, University of Pennsylvania School of Nursing
Project: Redefining Health Care Documentation: Unveiling AI's Potential in Streamlining Nursing Records
Brigitte Woo, PhD is a 2024–25 Singaporean Harkness Fellow in Health Care Policy and Practice. She currently works as a Research Fellow at the Alice Lee Centre for Nursing Studies, Yong Loo Lin School of Medicine, National University of Singapore (NUS). Before her appointment as a Research Fellow, Woo practiced as a registered nurse for six years at Singapore’s National University Hospital. During that time, she was trained and worked as a critical care nurse. She has retained her professional nursing license with the Singapore Nursing Board since leaving clinical practice.
Woo’s research focuses on the role, implementation, and professional development of advanced practice nurses. So far, she has conducted nationwide cross-sectional studies and has collaborated with the Chief Nursing Officer (CNO) Office, Ministry of Health (MOH), Singapore. She continues to work with the MOH CNO Office to effect change in policy through research and evaluation. Apart from workforce-related research on nursing, Woo has conducted research and published work on integrating and optimizing care for patients living with atrial fibrillation and ischemic heart disease.
Beyond her academic pursuits, Woo shares her knowledge as a faculty member in the undergraduate programs at NUS Nursing. She also engages in leadership roles as a board member of the Sigma Theta Tau – Upsilon Eta Chapter and as a member of the International Council of Nurses (ICN) Nurse Practitioner / Advanced Practice Nurse Research Subgroup.
Project Overview: Despite the undeniable importance of nursing documentation in communication, care continuity, and legal compliance, it is a frequently time-consuming task for nurses that limits their patient interaction time and adds to their workload. This study proposes exploring the potential of artificial intelligence, specifically large language models (LLMs) like ChatGPT, to streamline nursing documentation processes and alleviate the burden on nurses.
I propose a three-phase, multi-method research design to achieve the study objectives. The first phase involves a comprehensive review of literature and a cross-sectional survey to understand health care professionals' perceptions of using AI in medical recordkeeping. The second phase encompasses fieldwork studies, including time–motion studies, retrospective chart reviews, and qualitative interviews with nurses, aiming to understand their challenges and perspectives regarding documentation. The third phase focuses on developing an LLM prototype for nursing documentation through integrating study findings and co-designing training data and parameters with key stakeholders.
The expected contributions of this research are substantial. If successful, the study could revolutionize health care documentation by demonstrating the feasibility and benefits of integrating LLMs, like ChatGPT, in nursing documentation. This could lead to improved efficiency, reduced workload for nurses, and, ultimately, enhanced patient care and health care delivery. The findings may also have implications for other aspects of medical recordkeeping, potentially transforming health care practices beyond nursing documentation.