• Jenny Alderden, Ginette Alyce Pepper, Andrew Wilson, Joanne D Whitney, Stephanie Richardson, Ryan Butcher, Yeonjung Jo, and Mollie Rebecca Cummins.
• Jenny Alderden is an assistant professor, School of Nursing, Boise State University, Boise, Idaho, and an adjunct assistant professor, College of Nursing, University of Utah, Salt Lake City, Utah. Ginette Alyce Pepper is a professor, and Andrew Wilson is a clinical assistant professor, College of Nursing, University of Utah. Joanne D. Whitney is a professor, College of Nursing, University of Washington, Seattle, Washington. Stephanie Richardson is a professor, Rocky Mountain University of the Health Professions, Provo, Utah. Ryan Butcher is a senior data architect, Biomedical Informatics Team, Center for Clinical and Translational Science, University of Utah. Yeonjung Jo is a doctoral (PhD) student in population health science, College of Nursing, University of Utah. Mollie Rebecca Cummins is a professor, College of Nursing, University of Utah. jennyalderden@boisestate.edu.
• Am. J. Crit. Care. 2018 Nov 1; 27 (6): 461-468.

BackgroundHospital-acquired pressure injuries are a serious problem among critical care patients. Some can be prevented by using measures such as specialty beds, which are not feasible for every patient because of costs. However, decisions about which patient would benefit most from a specialty bed are difficult because results of existing tools to determine risk for pressure injury indicate that most critical care patients are at high risk.ObjectiveTo develop a model for predicting development of pressure injuries among surgical critical care patients.MethodsData from electronic health records were divided into training (67%) and testing (33%) data sets, and a model was developed by using a random forest algorithm via the R package "randomforest."ResultsAmong a sample of 6376 patients, hospital-acquired pressure injuries of stage 1 or greater (outcome variable 1) developed in 516 patients (8.1%) and injuries of stage 2 or greater (outcome variable 2) developed in 257 (4.0%). Random forest models were developed to predict stage 1 and greater and stage 2 and greater injuries by using the testing set to evaluate classifier performance. The area under the receiver operating characteristic curve for both models was 0.79.ConclusionThis machine-learning approach differs from other available models because it does not require clinicians to input information into a tool (eg, the Braden Scale). Rather, it uses information readily available in electronic health records. Next steps include testing in an independent sample and then calibration to optimize specificity.©2018 American Association of Critical-Care Nurses.

29 keywords...

hide…