HCA Healthcare collaborates with Google Cloud to bring generative AI to hospitals

Today, HCA Healthcare and Google Cloud are proud to announce a new collaboration designed to use generative AI technology to improve workflows on time-consuming tasks, such as clinical documentation, so physicians and nurses can focus more on patient care.

This expanded work with Google Cloud is part of a strategic partnership announced in 2021 that includes safeguards to protect patient privacy and the security of data. HCA Healthcare’s partnership with Google Cloud, as well as our multi-year implementation of MEDITECH Expanse which began in 2022, are key elements of HCA Healthcare’s work to advance our digital transformation.

As part of a pilot program that began early this year, approximately 75 emergency room physicians at four HCA Healthcare hospitals started using Google’s AI technology to quickly and more easily document key medical information from conversations during patient visits. It is part of a collaboration among HCA Healthcare, Google Cloud, and Augmedix, a healthcare technology company that specializes in ambient medical documentation. According to a 2022 study in JAMA Internal Medicine, 58% of physicians said time spent on documentation limits the amount of time they can spend with patients.

Physicians use an Augmedix app on a hands-free device to create accurate and timely medical notes from clinician-patient conversations. Augmedix’s proprietary platform then leverages natural language processing, along with Google Cloud’s generative AI technology and multi-party medical speech-to-text processing, to instantly convert the data into medical notes, which physicians review and finalize before they are transferred in real time to the hospital’s electronic health record (EHR).

Experts from HCA Healthcare’s Care Transformation and Innovation team (CT&I), along with the Google Cloud and Augmedix teams, continue to work closely with physicians to refine the solution, and HCA Healthcare plans to expand its use to more hospitals later this year. While we are in the process of collecting measurement data, physicians in the pilot program have reported strong overall satisfaction.

Another opportunity HCA Healthcare has targeted for improvement through generative AI is patient handoffs between nurses. Typically, this important process is manual and time-consuming, and often provides varying levels of detail.  HCA Healthcare’s CT&I team built a system using one of Google Cloud’s large language models (LLMs) that helps automatically generate handoff reports and is designed to promote continuity, consistency, patient safety, and clinical quality – while saving nurses significant time and maintaining human oversight.

Prompts were carefully designed to guide the LLM toward prioritized details, such as medication changes, laboratory results, vital sign fluctuations, patient concerns, and overall response to treatment. HCA Healthcare’s team also shaped the model’s outputs to make them intuitive and easy for nurses to read, comprehend, and act upon. During initial beta testing, HCA Healthcare collected nurse feedback to further refine the tool. Currently, the nurse handoff tool is undergoing continued testing at UCF Lake Nona Hospital. After seeing the prototype, nurses were pleased with the speed, accuracy, and relevance of the draft reports the tool is generating and expressed high interest in putting the tool into practice.

Longer term, HCA Healthcare is exploring the use of Google’s medically-tuned Med-PaLM 2 LLM to support caregivers.

“Having an LLM tailored for medical questions and content could be beneficial for certain critical use cases,” said Dr. Schlosser. “We expect Med-PaLM 2 will be especially useful when we’re asking complex medical questions that are grounded on scientific and medical knowledge, while looking for insights in complicated and unstructured medical texts.”

Google Cloud’s approach to data governance and privacy policies are designed for its customers to retain control over their data. In healthcare settings, access and use of patient data is protected through the implementation of Google Cloud’s reliable infrastructure and secure data storage that support HIPAA compliance, along with each customer’s security, privacy controls, and processes. Google Cloud’s responsible approach to generative AI also means customers have access to tools to directly tune large language models and to review model responses for biased or unvalidated content, teaching the model to avoid inappropriate outputs.

Related article: HCA Healthcare’s Michael Schlosser Takes on Innovation and Transformation | HealthLeaders Media