Researchers discover that advanced AI can simplify, accelerate, and enhance hospital quality reporting.
A pilot study conducted by scientists at the University of California San Diego School of Medicine has shown that advanced artificial intelligence (AI) may facilitate simpler, quicker, and more efficient hospital quality reporting without compromising accuracy, potentially improving healthcare delivery.
The findings, published in the online edition of the New England Journal of Medicine (NEJM) AI on October 21, 2024, reveal that an AI system utilizing large language models (LLMs) can effectively handle hospital quality metrics, achieving a 90% match with manual reporting. This advancement could foster more effective and dependable health care reporting methods.
The research team, in collaboration with the Joan and Irwin Jacobs Center for Health Innovation at UC San Diego Health (JCHI), discovered that LLMs can perform precise abstractions for intricate quality measurements, especially within the challenging framework of the Centers for Medicare & Medicaid Services (CMS) SEP-1 standard for severe sepsis and septic shock.
“Incorporating LLMs into hospital operations has the potential to revolutionize healthcare delivery by making the process more immediate, which can enhance personalized treatment and improve patient access to quality information,” remarked Aaron Boussina, postdoctoral scholar and lead author of the study at UC San Diego School of Medicine. “As we progress in this research, we foresee a future where quality reporting is not only effective but also enriches the overall patient experience.”
Typically, the abstraction process for SEP-1 necessitates a meticulous 63-step review of extensive patient records, taking weeks and requiring the efforts of several reviewers. This study demonstrated that LLMs could significantly shorten both the time and resources required for this task by swiftly reviewing patient records and providing essential contextual insights in mere moments.
By addressing the intricate demands of quality assessment, the researchers believe their findings can lead to a more effective and responsive healthcare system.
“We are committed to utilizing technology to lessen the administrative load in healthcare, allowing our quality improvement specialists to devote more time to supporting the exceptional care provided by our medical teams,” stated Chad VanDenBerg, study co-author and chief quality and patient safety officer at UC San Diego Health.
Key additional discoveries from the research indicated that LLMs can boost efficiency by rectifying errors and expediting processing times; lowering administrative expenses through task automation; facilitating nearly real-time quality evaluations; and being applicable across various healthcare environments.
Next steps include the research team validating these findings and applying them to improve reliable data and reporting techniques.
Co-authors of this study include Shamim Nemati, Rishivardhan Krishnamoorthy, Kimberly Quintero, Shreyansh Joshi, Gabriel Wardi, Hayden Pour, Nicholas Hilbert, Atul Malhotra, Michael Hogarth, Amy Sitapati, Karandeep Singh, and Christopher Longhurst, all affiliated with UC San Diego.
This research received partial funding from 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.
