Jung In Park1, Donna Z Bliss, Chih-Lin Chi, Connie W Delaney, Bonnie L Westra. 1. Jung In Park, PhD, RN, School of Medicine, Center for Biomedical Informatics Research, Stanford University, Stanford, California. Donna Z. Bliss, PhD, RN, FAAN, FGSA, School of Nursing, University of Minnesota, Minneapolis. Chih-Lin Chi, PhD, MBA, School of Nursing, University of Minnesota, Minneapolis. Connie W. Delaney, PhD, RN, FAAN, FACMI, School of Nursing, University of Minnesota, Minneapolis. Bonnie L. Westra, PhD, RN, FAAN, FACMI, School of Nursing, University of Minnesota, Minneapolis.
Abstract
PURPOSE: The purpose of this study was to identify factors associated with healthcare-acquired catheter-associated urinary tract infections (HA-CAUTIs) using multiple data sources and data mining techniques. SUBJECTS AND SETTING: Three data sets were integrated for analysis: electronic health record data from a university hospital in the Midwestern United States was combined with staffing and environmental data from the hospital's National Database of Nursing Quality Indicators and a list of patients with HA-CAUTIs. METHODS: Three data mining techniques were used for identification of factors associated with HA-CAUTI: decision trees, logistic regression, and support vector machines. RESULTS: Fewer total nursing hours per patient-day, lower percentage of direct care RNs with specialty nursing certification, higher percentage of direct care RNs with associate's degree in nursing, and higher percentage of direct care RNs with BSN, MSN, or doctoral degree are associated with HA-CAUTI occurrence. The results also support the association of the following factors with HA-CAUTI identified by previous studies: female gender; older age (>50 years); longer length of stay; severe underlying disease; glucose lab results (>200 mg/dL); longer use of the catheter; and RN staffing. CONCLUSIONS: Additional findings from this study demonstrated that the presence of more nurses with specialty nursing certifications can reduce HA-CAUTI occurrence. While there may be valid reasons for leaving in a urinary catheter, findings show that having a catheter in for more than 48 hours contributes to HA-CAUTI occurrence. Finally, the findings suggest that more nursing hours per patient-day are related to better patient outcomes.
PURPOSE: The purpose of this study was to identify factors associated with healthcare-acquired catheter-associated urinary tract infections (HA-CAUTIs) using multiple data sources and data mining techniques. SUBJECTS AND SETTING: Three data sets were integrated for analysis: electronic health record data from a university hospital in the Midwestern United States was combined with staffing and environmental data from the hospital's National Database of Nursing Quality Indicators and a list of patients with HA-CAUTIs. METHODS: Three data mining techniques were used for identification of factors associated with HA-CAUTI: decision trees, logistic regression, and support vector machines. RESULTS: Fewer total nursing hours per patient-day, lower percentage of direct care RNs with specialty nursing certification, higher percentage of direct care RNs with associate's degree in nursing, and higher percentage of direct care RNs with BSN, MSN, or doctoral degree are associated with HA-CAUTI occurrence. The results also support the association of the following factors with HA-CAUTI identified by previous studies: female gender; older age (>50 years); longer length of stay; severe underlying disease; glucose lab results (>200 mg/dL); longer use of the catheter; and RN staffing. CONCLUSIONS: Additional findings from this study demonstrated that the presence of more nurses with specialty nursing certifications can reduce HA-CAUTI occurrence. While there may be valid reasons for leaving in a urinary catheter, findings show that having a catheter in for more than 48 hours contributes to HA-CAUTI occurrence. Finally, the findings suggest that more nursing hours per patient-day are related to better patient outcomes.
Authors: Bonnie L Westra; Kay S Lytle; Luann Whittenburg; Mischa Adams; Samira Ali; Meg Furukawa; Stephanie Hartleben; Mary Hook; Steve Johnson; Sarah Collins Rossetti; Tess Theresa Settergren Journal: J Am Med Inform Assoc Date: 2020-11-01 Impact factor: 4.497
Authors: Andrea M Simi; Graham C Chapman; Jacqueline Zillioux; Sarah Martin; Emily A Slopnick Journal: Neurourol Urodyn Date: 2022-03-29 Impact factor: 2.367