| Learning Objective #1: Identify clinically important structure and process variables associated with the outcome of postoperative pneumonia in surgical patients | |||
| Learning Objective #2: Discuss the implications of these findings for patient care delivery and patient outcomes |
Over the past decade, the overall rate of nosocomial infections has remained constant, with infections at three major sites; urinary tract infections (UTI), pneumonia, and primary blood stream infections representing the majority of nosocomial infections. Although pneumonia ranks second to UTIs, it has the highest mortality rate (20% to 46%), and it is significantly more costly to treat. Guidelines for the prevention of nosocomial pneumonia in surgical patients remain unresolved because research to date has not fully identified the factors associated with its development.
Using Donabedian's Model of Health Care Quality as a framework, the outcome of postoperative pneumonia as it is related to structures and processes of care was examined. Data mining classification methods (Attribute Importance, Support Vector Machine, Naive Bayes and Decision Trees) were used to analyze 122 structure and process variables from the hospital courses of surgical patients who developed postoperative pneumonia and those who did not. This single-site exploratory study revealed factors that contributed significantly to the outcome of postoperative pneumonia in these surgical patients. The development of a predictive model with 72% accuracy in predicting positive pneumonia cases was possible. This knowledge will contribute to the development of evidence based nursing interventions and health promotion strategies aimed at the reduction of risk of postoperative pneumonia in surgical patients.