Electronic Surveillance For Catheter-Associated Urinary Tract Infection Using Natural Language Processing. Sanger, P. C., Granich, M., Olsen-Scribner, R., Jain, R., Lober, W. B., Stapleton, A., & Pottinger, P. S. AMIA ... Annual Symposium proceedings. AMIA Symposium, 2017:1507–1516, 2017. abstract bibtex 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.
@article{sanger_electronic_2017,
title = {Electronic {Surveillance} {For} {Catheter}-{Associated} {Urinary} {Tract} {Infection} {Using} {Natural} {Language} {Processing}},
volume = {2017},
issn = {1942-597X},
abstract = {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.},
language = {eng},
journal = {AMIA ... Annual Symposium proceedings. AMIA Symposium},
author = {Sanger, Patrick C. and Granich, Marion and Olsen-Scribner, Robin and Jain, Rupali and Lober, William B. and Stapleton, Ann and Pottinger, Paul S.},
year = {2017},
pmid = {29854220},
pmcid = {PMC5977673},
keywords = {Algorithms, Catheter-Related Infections, Cross Infection, Data Mining, Documentation, Electronic Health Records, Humans, Monitoring, Physiologic, Natural Language Processing, Patient Acuity, Prospective Studies, Urinary Tract Infections},
pages = {1507--1516},
}
Downloads: 0
{"_id":"ySkxktngLmNMzoBij","bibbaseid":"sanger-granich-olsenscribner-jain-lober-stapleton-pottinger-electronicsurveillanceforcatheterassociatedurinarytractinfectionusingnaturallanguageprocessing-2017","author_short":["Sanger, P. C.","Granich, M.","Olsen-Scribner, R.","Jain, R.","Lober, W. B.","Stapleton, A.","Pottinger, P. S."],"bibdata":{"bibtype":"article","type":"article","title":"Electronic Surveillance For Catheter-Associated Urinary Tract Infection Using Natural Language Processing","volume":"2017","issn":"1942-597X","abstract":"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.","language":"eng","journal":"AMIA ... Annual Symposium proceedings. AMIA Symposium","author":[{"propositions":[],"lastnames":["Sanger"],"firstnames":["Patrick","C."],"suffixes":[]},{"propositions":[],"lastnames":["Granich"],"firstnames":["Marion"],"suffixes":[]},{"propositions":[],"lastnames":["Olsen-Scribner"],"firstnames":["Robin"],"suffixes":[]},{"propositions":[],"lastnames":["Jain"],"firstnames":["Rupali"],"suffixes":[]},{"propositions":[],"lastnames":["Lober"],"firstnames":["William","B."],"suffixes":[]},{"propositions":[],"lastnames":["Stapleton"],"firstnames":["Ann"],"suffixes":[]},{"propositions":[],"lastnames":["Pottinger"],"firstnames":["Paul","S."],"suffixes":[]}],"year":"2017","pmid":"29854220","pmcid":"PMC5977673","keywords":"Algorithms, Catheter-Related Infections, Cross Infection, Data Mining, Documentation, Electronic Health Records, Humans, Monitoring, Physiologic, Natural Language Processing, Patient Acuity, Prospective Studies, Urinary Tract Infections","pages":"1507–1516","bibtex":"@article{sanger_electronic_2017,\n\ttitle = {Electronic {Surveillance} {For} {Catheter}-{Associated} {Urinary} {Tract} {Infection} {Using} {Natural} {Language} {Processing}},\n\tvolume = {2017},\n\tissn = {1942-597X},\n\tabstract = {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.},\n\tlanguage = {eng},\n\tjournal = {AMIA ... Annual Symposium proceedings. AMIA Symposium},\n\tauthor = {Sanger, Patrick C. and Granich, Marion and Olsen-Scribner, Robin and Jain, Rupali and Lober, William B. and Stapleton, Ann and Pottinger, Paul S.},\n\tyear = {2017},\n\tpmid = {29854220},\n\tpmcid = {PMC5977673},\n\tkeywords = {Algorithms, Catheter-Related Infections, Cross Infection, Data Mining, Documentation, Electronic Health Records, Humans, Monitoring, Physiologic, Natural Language Processing, Patient Acuity, Prospective Studies, Urinary Tract Infections},\n\tpages = {1507--1516},\n}\n\n\n\n","author_short":["Sanger, P. C.","Granich, M.","Olsen-Scribner, R.","Jain, R.","Lober, W. B.","Stapleton, A.","Pottinger, P. S."],"key":"sanger_electronic_2017","id":"sanger_electronic_2017","bibbaseid":"sanger-granich-olsenscribner-jain-lober-stapleton-pottinger-electronicsurveillanceforcatheterassociatedurinarytractinfectionusingnaturallanguageprocessing-2017","role":"author","urls":{},"keyword":["Algorithms","Catheter-Related Infections","Cross Infection","Data Mining","Documentation","Electronic Health Records","Humans","Monitoring","Physiologic","Natural Language Processing","Patient Acuity","Prospective Studies","Urinary Tract Infections"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"http://bibbase.org/zotero-group/lober/2427847","dataSources":["K7F7TwXAn7H3rFsQm"],"keywords":["algorithms","catheter-related infections","cross infection","data mining","documentation","electronic health records","humans","monitoring","physiologic","natural language processing","patient acuity","prospective studies","urinary tract infections"],"search_terms":["electronic","surveillance","catheter","associated","urinary","tract","infection","using","natural","language","processing","sanger","granich","olsen-scribner","jain","lober","stapleton","pottinger"],"title":"Electronic Surveillance For Catheter-Associated Urinary Tract Infection Using Natural Language Processing","year":2017}