Electronic Surveillance For Catheter-Associated Urinary Tract Infection Using Natural Language Processing

Catheter-associated urinary tract infection (CAUTI) is a common and costly healthcare-associated infection, yet measuring it accurately is challenging and resource-intensive. Electronic surveillance promises to make this task more objective and efficient in an era of new financial and regulatory imperatives, but previous surveillance approaches have used a simplified version of the definition. We applied a complete definition, including subjective elements identified through natural language processing of clinical notes. Through examination of documentation practices, we defined a set of rules that identified positively and negatively asserted symptoms of CAUTI. Our algorithm was developed on a training set of 1421 catheterizedpatients and prospectively validated on 1567 catheterizedpatients. Compared to gold standard chart review, our tool had a sensitivity of 97.1%, specificity of 94.5% PPV of 66.7% and NPV of 99.6% for identifying CAUTI. We discuss sources of error and suggestions for more computable future definitions.

[1]  N. Petersen,et al.  Accuracy of a urinary catheter surveillance protocol. , 2012, American journal of infection control.

[2]  Implementation of electronic surveillance of catheter use and catheter-associated urinary tract infection at Nurses Improving Care for Healthsystem Elders (NICHE) hospitals. , 2014, American journal of infection control.

[3]  Yu-Sheng Lo,et al.  Utilization of Electronic Medical Records to Build a Detection Model for Surveillance of Healthcare-Associated Urinary Tract Infections , 2012, Journal of Medical Systems.

[4]  H. Wald,et al.  Nonpayment for harms resulting from medical care: catheter-associated urinary tract infections. , 2007, JAMA.

[5]  D. Maki,et al.  The Direct Costs of Nosocomial Catheter-Associated Urinary Tract Infection in the Era of Managed Care , 2002, Infection Control & Hospital Epidemiology.

[6]  Guy Divita,et al.  Detecting the presence of an indwelling urinary catheter and urinary symptoms in hospitalized patients using natural language processing. , 2017, Journal of biomedical informatics.

[7]  R. Gaynes,et al.  Accuracy of Reporting Nosocomial Infections In Intensive-Care–Unit Patients to the National Nosocomial Infections Surveillance System: A Pilot Study , 1998, Infection Control & Hospital Epidemiology.

[8]  H. Wald,et al.  Accuracy of Electronic Surveillance of Catheter-Associated Urinary Tract Infection at an Academic Medical Center , 2014, Infection Control & Hospital Epidemiology.

[9]  John Jernigan,et al.  The changing face of surveillance for health care-associated infections. , 2004, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[10]  Michael Klompas,et al.  Automated surveillance of health care-associated infections. , 2009, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[11]  Valmeek Kudesia,et al.  Natural Language Processing for Real-Time Catheter-Associated Urinary Tract Infection Surveillance: Results of a Pilot Implementation Trial , 2015, Infection Control & Hospital Epidemiology.

[12]  Yohan Vetteth,et al.  Using electronic medical records to increase the efficiency of catheter-associated urinary tract infection surveillance for National Health and Safety Network reporting. , 2014, American journal of infection control.

[13]  Sanjay Saint,et al.  Diagnosis, prevention, and treatment of catheter-associated urinary tract infection in adults: 2009 International Clinical Practice Guidelines from the Infectious Diseases Society of America. , 2010, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[14]  R M Gardner,et al.  Computer surveillance of hospital-acquired infections and antibiotic use. , 1986, JAMA.

[15]  D. Calfee,et al.  Infection Control and Cost Control in the Era of Managed Care , 2002, Infection Control & Hospital Epidemiology.

[16]  John B Lynch,et al.  An Electronic Catheter-Associated Urinary Tract Infection Surveillance Tool , 2011, Infection Control & Hospital Epidemiology.

[17]  Joshua A. Doherty,et al.  Quality of traditional surveillance for public reporting of nosocomial bloodstream infection rates. , 2010, JAMA.

[18]  Mandatory reporting of hospital-acquired infections: steps for success. , 2005, The Journal of law, medicine & ethics : a journal of the American Society of Law, Medicine & Ethics.

[19]  Sanjay Saint,et al.  Effect of Nonpayment for Hospital-Acquired, Catheter-Associated Urinary Tract Infection , 2012, Annals of Internal Medicine.

[20]  Elaine Larson,et al.  A comparison of methods to detect urinary tract infections using electronic data. , 2010, Joint Commission journal on quality and patient safety.

[21]  S. Saint,et al.  Preventing hospital-acquired urinary tract infection in the United States: a national study. , 2008, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[22]  D. Cardo,et al.  Estimating Health Care-Associated Infections and Deaths in U.S. Hospitals, 2002 , 2007, Public health reports.

[23]  Harry C. Karadimas,et al.  An Intranet-Based Automated System for the Surveillance of Nosocomial Infections: Prospective Validation Compared with Physicians' Self-Reports , 2003, Infection Control & Hospital Epidemiology.