New Initiative Combines Nursing Expertise, AI to Create Prediction Model
Columbia University Irving Medical Center has launched an initiative to improve patient outcomes by leveraging nursing expertise and artificial intelligence to create the CONCERN model.
Source: Getty Images
By - Columbia University Irving Medical Center (CUIMC) is leading a multi-hospital effort known as the CONCERN (COmmunicating Narrative Concerns Entered by RNs) Initiative, which aims to utilize nurses’ expertise in risk identification to create an artificial intelligence (AI)-based prediction model to support early detection of critical conditions in hospitalized patients.
A key part of any nurse’s skill set is detecting cues about a patient's health and wellbeing through subtle changes in appearance and behavior. However, these observations are often missed or under-analyzed within the EHR. Nursing documentation in EHRs has been found to contain information that could contribute to the early detection and treatment of conditions such as cardiac arrest or sepsis, but these data are often not analyzed or presented to clinicians in time to save a patient.
The CONCERN Initiative seeks to change this by creating a prediction tool that extracts nurses’ knowledge from within EHRs and transforms it into observable data that can be used to improve patient outcomes.
“CONCERN shows what nurses already know: Our risk identification is not simply a subjective clinical hunch,” said Sarah Rossetti, assistant professor of biomedical informatics and nursing at Columbia University, in the press release. “We’re demonstrating that nurses have objective, expert-based knowledge that drives their practice, and we’re positioning nurses as knowledge workers with tremendous value to the entire care team.”
The research team designed the CONCERN tool by analyzing the frequency and types of nursing documentation that indicated nurses’ increased surveillance and level of concern for a patient. They found that this information, documented in the 48 hours preceding a cardiac arrest and hospital mortality, was predictive of the events.
Despite the predictive value of nurses’ observations, systemic communication issues within hospital settings between nurses and doctors can often cause delays in care for at-risk patients. Well-designed EHRs can theoretically support communication and show trends in patient data, but they are often unsuccessful in achieving these ends. In some cases, EHRs can increase clinicians’ cognitive burden through information overload, “note bloat,” and fragmented information displays.
The CONCERN Initiative aims to combat this by designing and evaluating a Substitutable Medical Applications & Reusable Technology (SMARTapp) using Fast Health Interoperability Resource (FHIR) standards, which allows for the open sharing and use of innovations across EHR systems. With this capability, the CONCERN tool can easily extract nursing documentation data from EHRs and present it to clinicians efficiently, increasing situational awareness of at-risk patients and decreasing preventable adverse outcomes.
The CONCERN Initiative is a partnership between CUIMC, Mass General Brigham, Vanderbilt University Medical Center, and the Washington University School of Medicine/Barnes-Jewish Hospital. The Initiative is being funded through a grant from the American Nurses Foundation Reimagining Nursing Initiative.
