Researchers at UC San Diego Health used artificial intelligence to automate clinical reviews and provide real-time feedback to emergency department teams.
RT’s Three Key Takeaways:
- Rapid Quality Abstraction: Large language models can accurately scan medical charts to assess complex quality measures for severe sepsis and septic shock in seconds.
- Real-Time Clinical Feedback: Automated reviews allow for immediate notifications to clinical leadership, providing physicians with actionable guidance while the patient is still receiving treatment.
- Improved Regulatory Compliance: The implementation of Ai-driven assessments resulted in higher compliance with national sepsis quality measures and reduced administrative costs.
Utilizing artificial intelligence (Ai) can lead to more timely and efficient assessments of care for patients with severe sepsis in the emergency department, according to a study published in JAMA Network Open.
The study utilized large language models (LLMs) to automatically assess complex measurements of care and deliver targeted feedback for hospital providers. In partnership with the Joan & Irwin Jacobs Center for Health Innovation at UC San Diego Health, researchers found that LLMs can perform accurate abstractions for the Centers for Medicare & Medicaid Services (CMS) SEP-1 measure for severe sepsis and septic shock.
The clinical review process for SEP-1 traditionally involves a 63-step evaluation of medical charts that requires months of effort from multiple reviewers. The study found that LLMs can reduce the time and resources needed by scanning hundreds of charts and generating contextual insights in seconds, often while the patient is still hospitalized.
“Medicine can learn a lot from professional athletics, where every player knows their performance statistics almost immediately, and that feedback changes how they train and perform,” said Gabriel Wardi, MD, co-corresponding author and emergency and critical care medicine physician at UC San Diego Health and chief of the division of critical care in the department of emergency medicine at UC San Diego School of Medicine, in a news release. “Rarely do physicians get that same type of quick, individualized feedback, even for conditions as time-sensitive as sepsis. By measuring performance in near-real time, we can turn quality reporting from a retrospective administrative exercise into something that actually helps physicians improve care.”
Once charts are automatically reviewed by the LLM, a notification is sent to clinical leadership in the emergency department for evaluation and dissemination to medical teams. This process provides physicians with recommendations for meeting SEP-1 guidelines during the care delivery process.
“By using Ai to quickly assess sepsis quality care measures, we are able to provide guidance to our care teams in the most teachable moment,” said Karandeep Singh, MD, study co-author and chief health artificial intelligence officer at UC San Diego Health, in a news release. “In turn, this has resulted in improved compliance with national sepsis quality measures and helps our teams consistently improve upon the care they provide to the communities we are proud to serve each day.”
According to the CDC, at least 1.7 million adults in the US develop sepsis each year, and approximately 350,000 die from the infection. The study also found that LLMs can improve efficiency by correcting errors, and lowering administrative costs by automating tasks across various healthcare settings.
“Using small, privacy-preserving language models allows for rapid and actionable insights distilled from large amounts of documentation in medical charts,” said Aaron Boussina, PhD, first author of the paper and affiliate faculty at the Joan & Irwin Jacobs Center for Health Innovation at UC San Diego School of Medicine, in a news release. “This seamlessly embeds best practices in the care delivery process.”
