A recent pilot study from researchers at the University of California San Diego School of Medicine suggests that advanced artificial intelligence (AI), particularly large language models (LLMs), could significantly enhance hospital quality reporting.

The study, published in NEJM AI, demonstrated that an AI system utilizing LLMs achieved 90% agreement with traditional manual reporting methods for hospital quality measures.

Specifically, the research focused on the Centers for Medicare & Medicaid Services (CMS) SEP-1 measure concerning severe sepsis and septic shock, showcasing the effectiveness of LLMs in accurately processing complex quality measures.

Co-author Chad VanDenBerg emphasized that leveraging these technologies could reduce the administrative burden, allowing quality improvement specialists to concentrate more on patient care.

Future research will focus on validating these findings and integrating LLMs into ongoing healthcare reporting improvement efforts to enhance data reliability.

Key findings indicate that LLMs can correct errors, speed up processing time, lower administrative costs, enable near-real-time assessments, and are scalable across various healthcare settings.

The study was conducted in collaboration with the Joan and Irwin Jacobs Center for Health Innovation at UC San Diego Health, with contributions from a diverse group of experts.

Lead author Aaron Boussina stated that integrating LLMs into hospital workflows could make the reporting process more real-time, thereby enhancing personalized care and patient access to quality data.

The findings represent a significant step towards improving healthcare reporting, highlighting the potential of AI in transforming healthcare delivery.

Overall, the integration of LLMs could lead to a more efficient healthcare system, allowing professionals to focus on delivering better patient care.

It is worth noting that Boussina holds equity in Healcisio Inc., a digital health start-up, and the study received funding related to this company, adhering to UC San Diego's conflict of interest policies.

The collaborative effort among researchers at UC San Diego underscores the importance of teamwork in advancing healthcare technology.