A pilot study led by researchers at the University of California, San Diego School of Medicine shows that advanced artificial intelligence (AI) could lead to easier, faster, and more efficient hospital quality reporting while maintaining high accuracy. It turns out that this could lead to enhanced healthcare delivery.
Research published online in the New England Journal of Medicine (NEJM) AI on October 21, 2024 shows that an AI system using large-scale language models (LLM) accurately assesses hospital quality. It was found that 90% agreement with manual reporting could be achieved. This could lead to a more efficient and reliable approach to medical reporting.
Researchers on this study collaborated with the Joan and Irwin Jacobs Center for Health Innovation at the University of California, San Diego Health (JCHI) to help LLM accurately measure complex quality measures, especially in the challenging context of the Centers for Medicare and Medicaid. I discovered that it can be abstracted into Service (CMS) SEP-1 measures severe sepsis and septic shock.
Integrating LLM into hospital workflows has the potential to transform healthcare delivery by making processes more real-time, enhancing personalized care, and improving patient access to quality data. As we advance this research, we envision a future where high-quality reporting is not only efficient, but also improves the overall patient experience. ”
Aaron Bussina, Postdoctoral Researcher, University of California, San Diego School of Medicine, Senior Study Author
Traditionally, the SEP-1 abstraction process involved a thorough 63-step evaluation of extensive patient charts, requiring weeks of effort by multiple reviewers. The study found that LLM can significantly reduce the time and resources required for this process by accurately scanning patient medical records and generating critical contextual insights in seconds.
The researchers believe that by addressing the complex demands of quality measurement, this discovery paves the way for more efficient and responsive health systems.
“We are leveraging technology to reduce the administrative burden of care, so quality improvement professionals can spend more time helping care teams,” said study co-author Chad Vandenberg. We continue to work diligently on our path to support the excellent care we provide.” Author and Chief Quality and Patient Safety Officer at the University of California, San Diego Health.
Other key findings from the study found that LLM can improve efficiency by correcting errors and speeding up processing time. Reduce administrative costs by automating tasks. Enables near real-time quality assessment. It can be expanded to various medical settings.
Future steps include the research team validating these findings and implementing them to strengthen reliable data and reporting methods.
Co-authors of the study include Shamim Nemati, Rishvardhan Krishnamoorthy, Kimberly Quintero, Shreyansh Joshi, Gabriel Wardi, Hayden Pour, Nicholas Hilbert, Atul Malhotra, Michael Hogarth, Amy Sitapati, Karandeep Singh, and Christopher Longhurst, all from California. I am affiliated with the University of San Diego.
This study was funded in part by the National Institute of Allergy and Infectious Diseases (1R42AI177108-1), the National Library of Medicine (2T15LM011271-11 and R01LM013998), the National Institute of General Medical Sciences (R35GM143121 and K23GM146092), and JCHI . .
sauce:
University of California San Diego
Reference magazines:
Boussina, A., et al. (2024) A large-scale language model for more efficient reporting of hospital quality measures. NEJM AI. doi.org/10.1056/AIcs2400420.
