Lead author Aaron Boussina highlighted that integrating LLMs into hospital workflows could transform health care delivery by enabling real-time processing and improving patient access to quality data.

It was disclosed that Boussina holds equity in Healcisio Inc, a digital health start-up, and the study received funding related to this company, reviewed in accordance with UC San Diego's conflict of interest policies.

The research was conducted in collaboration with the Joan and Irwin Jacobs Center for Health Innovation at UC San Diego Health.

The findings suggest that LLMs can significantly reduce administrative burdens, allowing quality improvement specialists to concentrate more on patient care.

A recent pilot study from researchers at the University of California San Diego School of Medicine suggests that advanced artificial intelligence (AI) could significantly enhance hospital quality reporting while maintaining high accuracy.

Co-author Chad VanDenBerg emphasized the goal of leveraging technologies to reduce the administrative burden in health care, allowing quality improvement specialists to focus more on patient care.

Future research will focus on validating these findings and implementing improved data reliability and reporting methods.

The study's co-authors include various researchers from UC San Diego, showcasing a collaborative effort in advancing health care technology.

Traditionally, the SEP-1 abstraction process involves a meticulous 63-step evaluation of patient charts, which can take weeks; however, LLMs can significantly reduce this time by quickly scanning charts and providing contextual insights.

The study also found that LLMs can correct errors, speed up processing times, lower administrative costs through task automation, and provide scalable near-real-time quality assessments across various health care settings.

Published on October 21, 2024, in the New England Journal of Medicine (NEJM) AI, the study reveals that AI systems utilizing large language models (LLMs) achieved 90% agreement with traditional manual reporting methods for hospital quality measures.

The study demonstrates that LLMs can accurately process complex quality measures, particularly the Centers for Medicare & Medicaid Services (CMS) SEP-1 measure for severe sepsis and septic shock.