Photo credit: www.sciencedaily.com
AI Tool Enhances Patient Monitoring and Reduces Mortality Risk in Hospitals
A groundbreaking AI system designed to evaluate nursing data and patient notes has shown the capability to identify deteriorating patients nearly two days earlier than conventional methods. This system, known as the CONCERN Early Warning System, significantly reduces mortality risk by over 35%, as indicated by a year-long clinical trial involving more than 60,000 patients conducted by researchers at Columbia University.
The CONCERN system employs machine learning algorithms to analyze nursing documentation patterns, allowing it to anticipate when a patient’s condition is declining before such changes are evident in vital signs. This early detection empowers healthcare providers to implement timely and potentially life-saving interventions.
According to the study, the use of CONCERN also led to a notable reduction in the average duration of hospital stays, decreasing them by more than half a day. Furthermore, there was a 7.5% reduction in risk for sepsis in patients monitored by the tool. Those receiving care through CONCERN were approximately 25% more likely to be admitted to an intensive care unit compared to patients under traditional monitoring practices.
Sarah Rossetti, the lead researcher and an associate professor of biomedical informatics and nursing at Columbia University, emphasized the unique skill set of nurses in patient care. “Nurses are particularly skilled and experienced in detecting when something is wrong with patients under their care,” she noted. “By integrating their expertise with AI technology, we can obtain real-time, actionable insights that are crucial for saving lives.”
The results of this innovative study have been published in the journal Nature Medicine.
How CONCERN Aligns with Nurses’ Insights
Nurses frequently notice subtle shifts indicating a patient’s deteriorating condition, such as changes in skin color or slight variations in mental clarity. However, these observations might not always prompt immediate actions, like transferring a patient to an intensive care unit.
CONCERN successfully analyzes the moments when nurses recognize and act upon these small yet significant changes. It reviews factors like the frequency and timing of assessments, creating hourly, easy-to-interpret risk scores that facilitate clinical decision-making.
“The CONCERN Early Warning System would not function effectively without incorporating the decisions and expertise of nurses’ data inputs,” stated Rossetti. “By bringing nurses’ expert instincts to the forefront of healthcare teams, this innovation ensures swifter interventions, improved patient outcomes, and ultimately, a greater number of lives saved.”
This influential study received support through grants from the National Institutes of Health (NINR 1R01NR016941 and T32NR007969).
Source
www.sciencedaily.com