Nursing notes can predict survival rates of ICU patients
Sentiments in the notes of ICU nurses are good indicators of whether patients will survive, according to researchers from the University of Waterloo in Ontario, Canada.
Hospitals can already predict the 30-day survival of ICU patient through severity of illness scores, which include lab results, vital signs and physiological and demographic characteristics gathered within 24 hours of admission.
Using a large publicly available ICU database, researchers looked at patient data from 2001 to 2012, considering 27,000 patients and the nursing notes. The study was recently published in the journal PLoS One.
“The physiological information collected in those first 24 hours of a patient’s ICU stay is really good at predicting 30-day mortality,” Joel Dubin, an associate professor at Waterloo, said in a statement. “But maybe we shouldn’t just focus on the objective components of a patient’s health status. It turns out that there is some added predictive value to including nursing notes as opposed to excluding them.”
Using a sentiment analysis algorithm that extracted adjectives, researchers established whether nursing note statements were positive, negative or neutral.
The analysis offered a “noticeable improvement” in predicting 30-day mortality rates. Patients with the most positive messages experienced the highest survival rates, while patients with the most negative messages experienced the lowest survival rates, the analysis revealed.
“Mortality is not the only outcome that nursing notes could potentially predict,” Dubin said. “They might also be used to predict readmission, or recovery from infection while in the ICU."