Wil McKoy Senior Vice President and Chief Financial Officer Interim Chief Operating Officer | Columbia U. Irving Medical Center
Wil McKoy Senior Vice President and Chief Financial Officer Interim Chief Operating Officer | Columbia U. Irving Medical Center
Columbia University has led a significant clinical trial, demonstrating the potential of artificial intelligence in improving patient outcomes in hospitals. In the study published in Nature Medicine, researchers introduced the CONCERN Early Warning System, an AI tool that utilizes machine learning to analyze nursing documentation. The system predicts a patient's deterioration almost two days earlier than conventional methods and has been shown to lower the risk of death by over 35%.
The trial involved more than 60,000 patients over a year and highlighted additional benefits such as shortening hospital stays by over half a day and reducing sepsis risk by 7.5%. Additionally, patients monitored via the CONCERN system were 25% more likely to be transferred to an intensive care unit as compared to those receiving usual care.
Sarah Rossetti, the study's lead author and associate professor at Columbia University, emphasized the collaboration between AI and nursing expertise: “Nurses are particularly skilled and experienced in detecting when something is wrong with patients under their care. When we can combine that expertise with AI, we can produce real-time, actionable insights that save lives.”
Nurses play a critical role, often identifying subtle deterioration signs in patients that might not result in immediate action based on electronic health records. The CONCERN system enhances these skills by tracking the frequency and timing of nurses' assessments to provide hourly risk scores, aiding clinical decision-making effectively. Rossetti pointed out, “The CONCERN Early Warning System would not work without the decisions and expert opinions of nurses’ data inputs.”
The research took into collaboration experts from various institutions including Brigham and Women’s Hospital, Newton-Wellesley Hospital, University of Pennsylvania, and Siena College. It was funded by grants from the National Institutes of Health.
This advancement marks a significant step in merging clinical expertise with AI to enhance patient care and outcomes in healthcare settings. The study's authors and affiliations were detailed in the publication, with comprehensive disclosures available in the document.
The work underscores the ongoing innovation at Columbia's Vagelos College of Physicians and Surgeons in fostering leading developments in medical science and practice.
Alerts Sign-up