Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model

Abstract

Background Hospital-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. Objective To develop a model for predicting development of pressure injuries among surgical critical care patients. Methods Data 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.” Results Among 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. Conclusion This 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. (American Journal of Critical Care. 2018; 27:461–468)

Risk Factor Analysis and Risk Prediction Model Construction of Pressure Injury in Critically Ill Patients with Cancer: A Retrospective Cohort Study in China

“…Researchers in previous studies have developed prediction tools for hospital-acquired PI in different patient populations and found them helpful [ 34 , 35 ]. In the present study, we analyzed the risk factors related to PI occurrence and constructed a risk prediction model for critically ill patients with cancer.…”

Comparative Analysis of Three Machine-Learning Techniques and Conventional Techniques for Predicting Sepsis-Induced Coagulopathy Progression

“…This method was adopted as a baseline classical method for comparison with other machine-learning methods. RF is an ensemble learning algorithm that improves generalizability by integrating multiple weak learners on the basis of decision trees [ 15 ]. When used as a classifier, the importance of variables can be examined by using Gini coefficients.…”

Artificial Intelligence Applications in Dermatology: Where Do We Stand?

“…Risk prediction tools also exist. Alderden et al described a tool that leverages data in the electronic health records of admitted patients, to predict their tendency to develop pressure ulcers (50). Altogether, these applications have preliminarily been shown to be technologically feasible, they have not yet been validated extensively in clinically trials.…”