Pressure Ulcers In Nursing Homes Research Articles

Identifying the Risk Factors Associated with Nursing Home Residents' Pressure Ulcers Using Machine Learning Methods.

Background: Machine learning (ML) can keep improving predictions and generating automated knowledge via data-driven predictors or decisions. Objective: The purpose of this study was to compare different ML methods including random forest, logistics regression, linear support vector machine (SVM), polynomial SVM, radial SVM, and sigmoid SVM in terms of their accuracy, sensitivity, specificity, negative predictor values, and positive predictive values by validating real datasets to predict factors for pressure ulcers (PUs). Methods: We applied representative ML algorithms (random forest, logistic regression, linear SVM, polynomial SVM, radial SVM, and sigmoid SVM) to develop a prediction model (N = 60). Results: The random forest model showed the greatest accuracy (0.814), followed by logistic regression (0.782), polynomial SVM (0.779), radial SVM (0.770), linear SVM (0.767), and sigmoid SVM (0.674). Conclusions: The random forest model showed the greatest accuracy for predicting PUs in nursing homes (NHs). Diverse factors that predict PUs in NHs including NH characteristics and residents’ characteristics were identified according to diverse ML methods. These factors should be considered to decrease PUs in NH residents.

Racial and Gender Differences in Pressure Ulcer Development Among Nursing Home Residents in the Southeastern United States

Objective: To determine whether there is a difference in the incidence of pressure ulcers (PU) between African American (AA) and White nursing home (NH) residents in the Southeastern United States. Methods: Data from the Centers for Medicare and Medicaid Services Minimum Data Set were examined for 113,869 residents who were free of PU at NH admission during 1999–2002. Facility and neighborhood characteristics were abstracted from the Online Survey Certification and Reporting database and the 2000 U.S. Census respectively. Results: The incidence of PU in NH among AAs and Whites was 4.7% (95% CI: 4.4–5.0) and 3.4 % (95% CI: 3.3–3.5) respectively. The association between race and PU development varied between males and females. Differences were noted between AA and White males who were dependent in mobility and between AA and White females who were bedfast and resided in facilities with less than 200 beds. Unlike for females, facility and neighborhood characteristics were not significant confounders in risk for PU incidence among males. Conclusion: PU occurred more frequently in AAs than in Whites. Results suggest that racial differences are marked among males and females with specific characteristics. Interventions for reducing this disparity should target these at-risk groups.