Predicting pressure injury using nursing assessment phenotypes and machine learning methods

Abstract

Objective Pressure injuries are common and serious complications for hospitalized patients. The pressure injury rate is an important patient safety metric and an indicator of the quality of nursing care. Timely and accurate prediction of pressure injury risk can significantly facilitate early prevention and treatment and avoid adverse outcomes. While many pressure injury risk assessment tools exist, most were developed before there was access to large clinical datasets and advanced statistical methods, limiting their accuracy. In this paper, we describe the development of machine learning-based predictive models, using phenotypes derived from nurse-entered direct patient assessment data. Methods We utilized rich electronic health record data, including full assessment records entered by nurses, from 5 different hospitals affiliated with a large integrated healthcare organization to develop machine learning-based prediction models for pressure injury. Five-fold cross-validation was conducted to evaluate model performance. Results Two pressure injury phenotypes were defined for model development: nonhospital acquired pressure injury (N = 4398) and hospital acquired pressure injury (N = 1767), representing 2 distinct clinical scenarios. A total of 28 clinical features were extracted and multiple machine learning predictive models were developed for both pressure injury phenotypes. The random forest model performed best and achieved an AUC of 0.92 and 0.94 in 2 test sets, respectively. The Glasgow coma scale, a nurse-entered level of consciousness measurement, was the most important feature for both groups. Conclusions This model accurately predicts pressure injury development and, if validated externally, may be helpful in widespread pressure injury prevention.

Explainable Artificial Intelligence for Predicting Hospital-Acquired Pressure Injuries in COVID-19–Positive Critical Care Patients

“…The best-performing ML model, an ensemble SuperLearner, showed good discrimination (area under the receiver operating characteristic curve = 0.807), and the global and local SHAP plots allow nurses to understand how the model is using the variables. This study adds to the body of literature showing ML approaches are useful for assessing HAPrI risk in critical-care patients, [26][27][28][29] and it is the first study to apply explainable AI for HAPrI risk prediction. The next step is model validation and development of associated clinical decision support.…”

Development and validation of interpretable machine learning models for inpatient fall events and electronic medical record integration

“…Interpretable ML is critical for nursing practice application 24,25 . Accuracy and actionable intervention is important for falls case because falls are very sensitive event that might result in hospital lawsuits.…”

“…AI for patient safety is a very impactful and effective area. It can be extended as a valuable tool that can be used to improve patient safety in multiple clinical settings: healthcare includes healthcare-associated infections, adverse drug events, venous thromboembolism, surgical complications, pressure ulcers, falls, decompensation, and diagnostic errors 25 .…”

Development and validation of a machine learning algorithm–based risk prediction model of pressure injury in the intensive care unit

“…Regarding machine learning, we performed logistic regression (LR), DT 16 and random forest (RF) 17,18 . R package for implementation comprised glmnet for LR, the recursive partitioning and regression trees (rpart) for DT and randomForest for RF.…”

“…Regarding machine learning, we performed logistic regression (LR), DT 16 and random forest (RF). 17 , 18 R package for implementation comprised glmnet for LR, the recursive partitioning and regression trees (rpart) for DT and randomForest for RF. Multivariate logistic regression was based on the abovementioned univariate analysis to further eliminate variables with collinearity.…”