, /PRNewswire/ — Clairyon Inc., a leader in clinical artificial intelligence and healthcare automation, today announced the publication of a groundbreaking cluster randomized quality improvement study in JAMA Network Open. The research, titled “Medical Record Abstraction for Quality Improvement in Sepsis Care Using Artificial Intelligence: A Cluster Randomized Trial,” demonstrates the ability of Clairyon’s AI-driven Clinical Abstraction Agent to significantly improve hospital quality metrics and patient care outcomes.
Conducted at two academic emergency departments, the study evaluated the impact of using large language models (LLMs) to automatically assess the complex measure for severe sepsis and septic shock (SEP-1) and deliver near-real-time feedback to physicians.
Currently, U.S. physician practices spend over $15 billion annually on quality reporting, with the average physician dedicating nearly 785 hours per year to manual administrative tasks. At the facility level, quality reporting for a single acute care hospital can require over 100,000 person-hours, costing upwards of $5 million annually. By replacing slow, manual chart abstraction with Clairyon’s AI-driven agent, health systems are empowered to move from retrospective reporting to proactive care enhancement. Concretely, the use of AI for chart review empowered teams to abstract SEP-1 at scales not previously possible with fewer resources. This has opened up frontier capabilities for health systems to improve system-wide decision making in near-real-time.
The newly published trial revealed that:
- Assignment to the AI intervention arm resulted in a 13% absolute improvement in overall SEP-1 compliance, jumping from 70.1% in the control group to 82.9% in the intervention group.
- The AI system achieved a 92% agreement rate with expert human reviewers.
- Rapid assessment of SEP-1 performance and targeted feedback improved overall compliance, demonstrating that AI-driven clinical integration can successfully address the limitations of existing hospital reporting systems.
“Having this research published in JAMA Network Open validates the immense potential of agentic AI in acute clinical settings,” said Dr. Mike McCurdy, Chief Medical Officer at Clairyon. “For too long, quality reporting has been a retrospective, labor-intensive burden that drains resources without directly benefiting patients. By automating the extraction of these complex SEP-1 metrics in near real-time, our platform benefits hospitals by alleviating administrative effort to save money and, most importantly, actively drives proactive clinical interventions that improve evidence-based bundle adherence. Moreover, by automating abstraction of all cases of sepsis instead of just the CMS standard of 20 cases per month for high-volume centers, Clairyon’s quality platform provides deeper understanding of a hospital’s ‘ground truth,’ facilitating high-quality decisions to improve sepsis care.”
This foundational study was supported through a Small Business Innovation Research (SBIR) grant from the National Library of Medicine (1R44LM014847-01), highlighting the critical national need for advanced analytical decision support tools to bridge the gap between reporting and care delivery.
About Clairyon Inc.
Clairyon Inc. is a pioneering clinical artificial intelligence company dedicated to transforming acute care and patient monitoring through predictive analytics and agentic AI. Clairyon develops the CLAIRE Continuum of Care Platform, an overarching ecosystem of advanced clinical decision support tools. This platform includes the flagship COMPOSER predictive model, proven to significantly reduce sepsis mortality, alongside comprehensive post-discharge and quality monitoring solutions.
www.clairyon.com
SOURCE Clairyon, Inc.
