Background Patients in intensive care units are at higher risk for development of pressure ulcers than other patients. In order to prevent pressure ulcers from developing in intensive care patients, risk for development of pressure ulcers must be assessed accurately. Objectives To evaluate the predictive validity of the Braden scale for assessing risk for development of pressure ulcers in intensive care patients by using 4 years of data from electronic health records. Methods Data from the electronic health records of patients admitted to intensive care units between January 1, 2007, and December 31, 2010, were extracted from the data warehouse of an academic medical center. Predictive validity was measured by using sensitivity, specificity, positive predictive value, and negative predictive value. The receiver operating characteristic curve was generated, and the area under the curve was reported. Results A total of 7790 intensive care patients were included in the analysis. A cutoff score of 16 on the Braden scale had a sensitivity of 0.954, specificity of 0.207, positive predictive value of 0.114, and negative predictive value of 0.977. The area under the curve was 0.672 (95% CI, 0.663–0.683). The optimal cutoff for intensive care patients, determined from the receiver operating characteristic curve, was 13. Conclusions The Braden scale shows insufficient predictive validity and poor accuracy in discriminating intensive care patients at risk of pressure ulcers developing. The Braden scale may not sufficiently reflect characteristics of intensive care patients. Further research is needed to determine which possibly predictive factors are specific to intensive care units in order to increase the usefulness of the Braden scale for predicting pressure ulcers in intensive care patients.

Background Obesity contributes to immobility and subsequent pressure on skin surfaces. Knowledge of the relationship between obesity and development of pressure ulcers in intensive care patients will provide better understanding of which patients are at high risk for pressure ulcers and allow more efficient prevention. Objectives To examine the incidence of pressure ulcers in patients who differ in body mass index and to determine whether inclusion of body mass index enhanced use of the Braden scale in the prediction of pressure ulcers. Methods In this retrospective cohort study, data were collected from the medical records of 4 groups of patients with different body mass index values: underweight, normal weight, obese, and extremely obese. Data included patients’ demographics, body weight, score on the Braden scale, and occurrence of pressure ulcers. Results The incidence of pressure ulcers in the underweight, normal weight, obese, and extremely obese groups was 8.6%, 5.5%, 2.8%, and 9.9%, respectively. When both the score on the Braden scale and the body mass index were predictive of pressure ulcers, extremely obese patients were about 2 times more likely to experience an ulcer than were normal weight patients. In the final model, the area under the curve was 0.71. The baseline area under the curve for the Braden scale was 0.68. Conclusions Body mass index and incidence of pressure ulcers were related in intensive care patients. Addition of body mass index did not appreciably improve the accuracy of the Braden scale for predicting pressure ulcers.

BackgroundWe develop predictive models enabling clinicians to better understand and explore patient clinical data along with risk factors for pressure ulcers in intensive care unit patients from electronic health record data. Identifying accurate risk factors of pressure ulcers is essential to determining appropriate prevention strategies; in this work we examine medication, diagnosis, and traditional Braden pressure ulcer assessment scale measurements as patient features. In order to predict pressure ulcer incidence and better understand the structure of related risk factors, we construct Bayesian networks from patient features. Bayesian network nodes (features) and edges (conditional dependencies) are simplified with statistical network techniques. Upon reviewing a network visualization of our model, our clinician collaborators were able to identify strong relationships between risk factors widely recognized as associated with pressure ulcers.MethodsWe present a three-stage framework for predictive analysis of patient clinical data: 1) Developing electronic health record feature extraction functions with assistance of clinicians, 2) simplifying features, and 3) building Bayesian network predictive models. We evaluate all combinations of Bayesian network models from different search algorithms, scoring functions, prior structure initializations, and sets of features.ResultsFrom the EHRs of 7,717 ICU patients, we construct Bayesian network predictive models from 86 medication, diagnosis, and Braden scale features. Our model not only identifies known and suspected high PU risk factors, but also substantially increases sensitivity of the prediction - nearly three times higher comparing to logistical regression models - without sacrificing the overall accuracy. We visualize a representative model with which our clinician collaborators identify strong relationships between risk factors widely recognized as associated with pressure ulcers.ConclusionsGiven the strong adverse effect of pressure ulcers on patients and the high cost for treating pressure ulcers, our Bayesian network based model provides a novel framework for significantly improving the sensitivity of the prediction model. Thus, when the model is deployed in a clinical setting, the caregivers can suitably respond to conditions likely associated with pressure ulcer incidence.

Background A pressure ulcer is injury to the skin or underlying tissue, caused by pressure, friction, and moisture. Hospital-acquired pressure ulcers (HAPUs) may not only result in additional length of hospital stay and associated care costs but also lead to undesirable patient outcomes. Intensive care unit (ICU) patients show higher risk for HAPU development than general patients. We hypothesize that the care team’s decisions relative to HAPU risk assessment and prevention may be better supported by a data-driven, ICU-specific prediction model. Objective The aim of this study was to determine whether multiple logistic regression with ICU-specific predictor variables was suitable for ICU HAPU prediction and to compare the performance of the model with the Braden scale on this specific population. Methods We conducted a retrospective cohort study by using the data retrieved from the enterprise data warehouse of an academic medical center. Bivariate analyses were performed to compare the HAPU and non-HAPU groups. Multiple logistic regression was used to develop a prediction model with significant predictor variables from the bivariate analyses. Sensitivity, specificity, positive predictive values, negative predictive values, area under the receiver operating characteristic curve (AUC), and Youden index were used to compare with the Braden scale. Results The total number of patient encounters studied was 12,654. The number of patients who developed an HAPU during their ICU stay was 735 (5.81% of the incidence rate). Age, gender, weight, diabetes, vasopressor, isolation, endotracheal tube, ventilator episode, Braden score, and ventilator days were significantly associated with HAPU. The overall accuracy of the model was 91.7%, and the AUC was .737. The sensitivity, specificity, positive predictive value, negative predictive value, and Youden index were .650, .693, .211, 956, and .342, respectively. Male patients were 1.5 times more, patients with diabetes were 1.5 times more, and patients under isolation were 3.1 times more likely to have an HAPU than female patients, patients without diabetes, and patients not under isolation, respectively. Conclusions Using an extremely large, electronic health record–derived dataset enabled us to compare characteristics of patients who develop an HAPU during their ICU stay with those who did not, and it also enabled us to develop a prediction model from the empirical data. The model showed acceptable performance compared with the Braden scale. The model may assist with clinicians’ decision on risk assessment, in addition to the Braden scale, as it is not difficult to interpret and apply to clinical practice. This approach may support avoidable reductions in HAPU incidence in intensive care.

No abstract