Tags

Type your tag names separated by a space and hit enter

Exploring the frontier of electronic health record surveillance: the case of postoperative complications.
Med Care. 2013 Jun; 51(6):509-16.MC

Abstract

BACKGROUND

The aim of this study was to build electronic algorithms using a combination of structured data and natural language processing (NLP) of text notes for potential safety surveillance of 9 postoperative complications.

METHODS

Postoperative complications from 6 medical centers in the Southeastern United States were obtained from the Veterans Affairs Surgical Quality Improvement Program (VASQIP) registry. Development and test datasets were constructed using stratification by facility and date of procedure for patients with and without complications. Algorithms were developed from VASQIP outcome definitions using NLP-coded concepts, regular expressions, and structured data. The VASQIP nurse reviewer served as the reference standard for evaluating sensitivity and specificity. The algorithms were designed in the development and evaluated in the test dataset.

RESULTS

Sensitivity and specificity in the test set were 85% and 92% for acute renal failure, 80% and 93% for sepsis, 56% and 94% for deep vein thrombosis, 80% and 97% for pulmonary embolism, 88% and 89% for acute myocardial infarction, 88% and 92% for cardiac arrest, 80% and 90% for pneumonia, 95% and 80% for urinary tract infection, and 77% and 63% for wound infection, respectively. A third of the complications occurred outside of the hospital setting.

CONCLUSIONS

Computer algorithms on data extracted from the electronic health record produced respectable sensitivity and specificity across a large sample of patients seen in 6 different medical centers. This study demonstrates the utility of combining NLP with structured data for mining the information contained within the electronic health record.

Authors+Show Affiliations

Tennessee Valley Healthcare System, Veterans Affairs Medical Center, Nashville, TN, USA.No affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info available

Pub Type(s)

Journal Article
Research Support, U.S. Gov't, Non-P.H.S.

Language

eng

PubMed ID

23673394

Citation

FitzHenry, Fern, et al. "Exploring the Frontier of Electronic Health Record Surveillance: the Case of Postoperative Complications." Medical Care, vol. 51, no. 6, 2013, pp. 509-16.
FitzHenry F, Murff HJ, Matheny ME, et al. Exploring the frontier of electronic health record surveillance: the case of postoperative complications. Med Care. 2013;51(6):509-16.
FitzHenry, F., Murff, H. J., Matheny, M. E., Gentry, N., Fielstein, E. M., Brown, S. H., Reeves, R. M., Aronsky, D., Elkin, P. L., Messina, V. P., & Speroff, T. (2013). Exploring the frontier of electronic health record surveillance: the case of postoperative complications. Medical Care, 51(6), 509-16. https://doi.org/10.1097/MLR.0b013e31828d1210
FitzHenry F, et al. Exploring the Frontier of Electronic Health Record Surveillance: the Case of Postoperative Complications. Med Care. 2013;51(6):509-16. PubMed PMID: 23673394.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Exploring the frontier of electronic health record surveillance: the case of postoperative complications. AU - FitzHenry,Fern, AU - Murff,Harvey J, AU - Matheny,Michael E, AU - Gentry,Nancy, AU - Fielstein,Elliot M, AU - Brown,Steven H, AU - Reeves,Ruth M, AU - Aronsky,Dominik, AU - Elkin,Peter L, AU - Messina,Vincent P, AU - Speroff,Theodore, PY - 2013/5/16/entrez PY - 2013/5/16/pubmed PY - 2013/8/2/medline SP - 509 EP - 16 JF - Medical care JO - Med Care VL - 51 IS - 6 N2 - BACKGROUND: The aim of this study was to build electronic algorithms using a combination of structured data and natural language processing (NLP) of text notes for potential safety surveillance of 9 postoperative complications. METHODS: Postoperative complications from 6 medical centers in the Southeastern United States were obtained from the Veterans Affairs Surgical Quality Improvement Program (VASQIP) registry. Development and test datasets were constructed using stratification by facility and date of procedure for patients with and without complications. Algorithms were developed from VASQIP outcome definitions using NLP-coded concepts, regular expressions, and structured data. The VASQIP nurse reviewer served as the reference standard for evaluating sensitivity and specificity. The algorithms were designed in the development and evaluated in the test dataset. RESULTS: Sensitivity and specificity in the test set were 85% and 92% for acute renal failure, 80% and 93% for sepsis, 56% and 94% for deep vein thrombosis, 80% and 97% for pulmonary embolism, 88% and 89% for acute myocardial infarction, 88% and 92% for cardiac arrest, 80% and 90% for pneumonia, 95% and 80% for urinary tract infection, and 77% and 63% for wound infection, respectively. A third of the complications occurred outside of the hospital setting. CONCLUSIONS: Computer algorithms on data extracted from the electronic health record produced respectable sensitivity and specificity across a large sample of patients seen in 6 different medical centers. This study demonstrates the utility of combining NLP with structured data for mining the information contained within the electronic health record. SN - 1537-1948 UR - https://www.unboundmedicine.com/medline/citation/23673394/Exploring_the_frontier_of_electronic_health_record_surveillance:_the_case_of_postoperative_complications_ L2 - https://doi.org/10.1097/MLR.0b013e31828d1210 DB - PRIME DP - Unbound Medicine ER -