Nurses have their finger on the pulse - new study shows nursing notes may indicate survival rates of ICU patients

You are here

The sentiments left in nursing notes are good indicators of whether ICU patients will survive, a UK study has found. Researchers at the University of Waterloo looked at the notes from over 27,000 ICU patients and examined how sentiments related to 30-day mortality and survival.

The study, Sentiment in nursing notes as an indicator of out-of-hospital mortality in intensive care patients, was published recently in the journal PLoS ONE.

The study authors said nursing notes have not been widely used in prediction models for clinical outcomes, despite containing rich information. Hospitals typically use severity of illness scores to predict the 30-day survival of ICU patients. These scores include lab results, vital signs, and physiological and demographic characteristics gathered within 24 hours of admission.

“The physiological information collected in those first 24 hours of a patient’s ICU stay is really good at predicting 30-day mortality,” said lead author, Joel Dubin, an associate professor in the Department of Statistics and Actuarial Science and the School of Public Health and Health Systems. 

“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.”

For the study, the researchers used a publicly available ICU database containing patient data between 2001 and 2012. After some inclusion and exclusion criteria were considered, such as the need for at least one nursing note for a given patient, the dataset used in the analysis included details about more than 27,000 patients, as well as the nursing notes. The researchers applied an open-source sentiment analysis algorithm to extract adjectives in the text to establish whether it is a positive, neutral or negative statement. Some examples of words that stuck out when the team used an open-source sentiment analysis algorithm were "pleasant" and "grim".

A multiple logistic regression model was then fit to the data to show a relationship between the measured sentiment and 30-day mortality while controlling for gender, type of ICU, and simplified acute physiology score.

Dubin and colleagues then explored the relationship between the sentiment and 30-day mortality while controlling for gender, type of ICU and simplified acute physiology score.

The researchers said there was a clear difference between the patients with the most positive messages who experienced the highest survival rates and those with the most negative messages who experienced the lowest survival rates. They added that sentiments of clinicians can serve as a predictor of patient outcomes in the ICU.

“Mortality is not the only outcome that nursing notes could potentially predict,” said Dubin. “They might also be used to predict readmission or recovery from infection while in the ICU.”