Nursing Notes Can Help Predict ICU Survival, Study Finds | Healthcare Informatics Magazine | Health IT | Information Technology Skip to content Skip to navigation

Nursing Notes Can Help Predict ICU Survival, Study Finds

July 16, 2018
by Rajiv Leventhal
| Reprints

Researchers at the University of Waterloo in Ontario have found that sentiments in healthcare providers’ nursing notes can be good indicators of whether intensive care unit (ICU) patients will survive.

For this study, which was published recently in the journal PLoS ONE, the researchers used the large publicly available intensive care unit (ICU) database, which contained 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. 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.

According to the researchers, 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 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.”

As such, the note-sentiment analysis provided a noticeable improvement for predicting 30-day mortality in the multiple logistic regression model for this group of patients. There was also a clear difference between the patients with the most positive messages who experienced the highest survival rates and the patients with the most negative messages who experienced the lowest survival rates, the study revealed.

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

Get the latest information on Health IT and attend other valuable sessions at this two-day Summit providing healthcare leaders with educational content, insightful debate and dialogue on the future of healthcare and technology.

Learn More

Topics

News

Amazon, Google, IBM and Other Tech Giants Pledge to Remove Barriers to Interoperability

Six of the world's biggest technology companies, including Microsoft, Google, IBM and Amazon, made a joint pledge at the White House Monday to remove interoperability barriers and to make progress on adoption of health data standards.

Mayo Clinic Elects New President and CEO

Gianrico Farrugia, M.D., current vice president, Mayo Clinic, and CEO of Mayo Clinic in Florida has been elected as the president and CEO of the Mayo Clinic, headquartered in Minnesota.

Fitbit, Blue Cross Blue Shield Launch Mobile Health Partnership

San Francisco-based fitness wearable maker Fitbit continues its push into the health plan market with a new digital health deal to incorporate its fitness tracker into health and wellness programs.

ASCO Picks IBM Watson Exec to Lead CancerLinQ

The American Society of Clinical Oncology (ASCO) has named a former IBM Watson executive as the new CEO of its CancerLinQ big data platform.

CVS Health’s MinuteClinic Launches New Telehealth Offering

CVS’ MinuteClinic, the company’s retail medical clinic, is rolling out a new telehealth healthcare offering for patients with minor illnesses and injuries, skin conditions and other wellness needs.

Report: More than 3M Patient Records Breached in Second Quarter of 2018

More than 3.14 million patient records were breached in 142 disclosed health data breach incidents during a three-month span from April to June 2018, according to new data released in the Protenus Breach Barometer.