- Scott Barton
- Summer 2026
Faculty instructor: Annette Jenkins, MSN
Abstract
Nurses today have an increased workload of complex patients, that need quality and timely care. However, due to the care demand of these patients and needs of the unit, nurses are having higher rates of burnout and many are leaving the profession. Sustainable, safe staffing ratios have helped mitigate this problem, but in order to have good staffing ratios there must be a rationale for increased staffing. This can be measured by patient acuity tools. However, previous acuity tools have required nurses to have “another task to do” which has made their implementation challenging. With the new development of artificial intelligence and machine learning tools, nurses can get the subjective data that is not always counted for when making staffing assignments and prove that they need higher rates of staffing. The goal of this project was to find current research on learning language models and programs that can help mitigate the problems of patient acuity and also use this technologies to help reduce nurse burnout. The project included speaking with current nurses on a busy medical-surgical unit, reading new articles on developments of technologies, and creating a proposal deliverable that may help convince hospital management to consider using Machine Learning to help staffing assignments.
Keywords
Machine learning, proposal, ratios, burnout