Google & HCA Healthcare announced the launch of a pilot program for Nurse Handoff, a new application leveraging Google’s MedLM models to generate concise, AI-driven summaries of patient data and streamline nursing shift transitions.
Developed in close collaboration with frontline nursing staff, Nurse Handoff displays the electronic health record (EHR) on one side of a hospital-provided mobile device and an AI-generated shift report on the other. Throughout their shift, nurses can review, verify, and enrich the automatically compiled information—drawing from notes, orders, tests, and other critical data—ensuring each handoff is accurate and comprehensive without compromising patient confidentiality.
“Traditionally, nurses rely upon their recollection of events, conversations, and data points, leaving room for error and inconsistency in the information given during handoff,” said a spokesperson for HCA Healthcare. “Using Nurse Handoff during their shift, nurses can easily find the information they and their peers have collected through the automated shift report and add their own notes, so the system keeps building. This can include relevant patient data from notes, orders, tests, and more. All this happens within a highly secure cloud environment, to keep patient information confidential.”
Also Read: Welldoc & Databricks Expand AI-Powered Health Partnership
Design Driven by Nurses’ Needs
Central to the success of Nurse Handoff was the involvement of clinical staff in every development phase. Registered nurse and HCA Healthcare DT&I product owner K.C. DeShetler led efforts to fine-tune the model, stating:
“We fed our model the information nurses want to know, prompted the model in a multitude of ways, used retrieval augmented generation to identify citations for the generated content, provided templates for organizing information the way we want and so forth.”
Early testers, including a Tennessee nurse named Hall, worked alongside developers to evaluate and refine the AI summaries:
“We went through that process three or four different times,” Hall recalls. “And each time, it became a little bit more accurate, a little less filled with fluff that we don’t need. The more we worked with it and provided our feedback, the more useful it became for the handoff setting.”
Promising Early Results and Next Steps
In its initial deployment across five HCA Healthcare hospitals, Nurse Handoff has achieved an 86% factual accuracy rating and 90% helpfulness score from testing nurses. Based on this success, HCA Healthcare intends to roll out the solution system-wide to support all 99,000 nurses.
“When I talk to direct care nurses and nurse leaders about technology and the emergence of AI in nursing,” said Dr. Staub-Juergens, “I often challenge them to be bold, be brave, take the keys to the car, get in the driver’s seat and use their voices to drive the design of the solutions moving forward.”
Source: Google
