HCA, Google Cloud bring AI into the ER

Earlier this year, HCA Healthcare initiated a pilot program that provided about 75 emergency room physicians at four hospitals with Google’s AI technology in hopes of making clinical documentation more streamlined.

On Tuesday, HCA Healthcare and Google Cloud announced they will be expanding their work together, as the hospital system looks to implement the tech in more hospitals across the country.

“We’re on a mission to redesign the way care is delivered, letting clinicians focus on patient care and using technology where it can best support doctors and nurses,” said Michael J. Schlosser, MD, MBA, FAANS, SVP, Care Transformation and Innovation, HCA Healthcare, said in a press release. “Generative AI and other new technologies are helping us transform the ways teams interact, create better workflows, and have the right team, at the right time, empowered with the information they need for our patients.”

The technology is powered by Google Cloud and Augmedix, a healthcare technology company specializing in ambient clinical documentation.

In the pilot program, physicians used an Augmedix app on a hands-free device to create clinical notes from conversations they have with their patients. Leveraging a combination of natural language processing, Google Cloud’s generative AI technology, and text-to-speech technology, the platform creates clinical notes for review before being added to the hospital’s electronic health record (EHR).

Documentation burdens are a well-recorded issue for clinicians, and some studies show it can take up to 35% of clinicians’ time. This heavy administrative load not only contributes to heightened burnout rates among healthcare professionals but also significantly curtails the amount of time they can dedicate to direct patient care. This technology has the potential to support a transformative shift in this landscape, alleviating the painstaking documentation process and allowing physicians to redirect their energy towards what truly matters: delivering personalized, high-quality care that enhances patient outcomes and experiences.

HCA Healthcare leadership, along with Google Cloud and Augmedix are in the process of collecting more data to “refine the solution.” In the meantime, physicians in the pilot program reported “strong overall satisfaction.”

“HCA Healthcare is a leader in care delivery, and our expanded partnership has the potential to benefit the entire healthcare industry,” said Thomas Kurian, CEO, Google Cloud. “Bringing generative AI into solutions that support doctors and nurses can significantly improve their day-to-day experiences and help them focus on what matters most – caring for patients.”

Google Cloud AI for nurse-patient handoffs

HCA Healthcare has set its sights on improving another critical aspect of healthcare operations: patient handoffs between nurses. Typically, this process is tedious and time-consuming. Using one of Google Cloud’s large language models (LLMs), HCA Healthcare’s Care Transformation & Innovation Team (CTI) created a system that automatically generates handoff reports.

The reports are designed to be easy-to-read and to highlight a patient’s changes in medications and vital signs, lab results, and response to treatment. Nurses using the model at UCF Lake Nona Hospital have expressed high interest in adopting the tool.

LLMs for caregivers

Looking ahead, HCA Healthcare is considering using Google’s specialized Med-PaLM 2 LLM to provide support to caregivers. Med-PaLM 2, a large language model tailored for healthcare,  is designed to provide answers to medical questions. The model has been tailored to the medical realm through alignment with medical exams, medical research, and consumer health-related questions.

HCA hopes it could provide useful answers to caregivers. Google is currently working to add functionality so the model can synthesize information from X-rays and mammograms.

“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.”