Informatics and the American College of Surgeons National Surgical Quality Improvement Program: Automated Processes Could Replace Manual Record Review

• Published in: Journal of the American College of Surgeons Vol. 208; no. 1; pp. 37 - 41
• Main Authors: Hanauer, David A., MD, MS, Englesbe, Michael J., MD, Cowan, John A., MD, Campbell, Darrell A., MD, FACS
• Format: Journal Article
• Language: English
• Published: New York, NY Elsevier Inc 01.01.2009; Elsevier
• Subjects: Automatic Data Processing; Biological and medical sciences; Data Collection - standards; Feasibility Studies; Forms and Records Control; General aspects; General Surgery - standards; Health participants; Humans; Medical Audit; Medical Informatics; Medical Records; Medical Records Systems, Computerized; Medical sciences; Myocardial Infarction - epidemiology; Outcome Assessment (Health Care) - statistics & numerical data; Postoperative Complications - epidemiology; Public health. Hygiene; Public health. Hygiene-occupational medicine; Pulmonary Embolism - epidemiology; Quality Assurance, Health Care; Quality of Health Care; Surgery; United States; United States; North America; America; NSQIP; MedLEE; natural language processing; American College of Surgeons; myocardial infarction; surgical clinical nurse reviewers; VA; Department of Veterans Affairs; SCNRs; ACS; Medical Language Extraction and Encoding; NLP; Electronic Medical Record Search Engine; PE; EMERSE; National Surgical Quality Improvement Program; MI; pulmonary embolism; Medicine; Improvement; Program; Treatment; American; Surgery; Quality; Manuals; Review; Automatic analysis; Surgeon; Bibliographic review
• ISSN: 1072-7515; 1879-1190
• DOI: 10.1016/j.jamcollsurg.2008.08.030

Background The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) provides reliable, risk-adjusted outcomes data using standardized definitions and end points. Collection of the data is time consuming, and the surgical clinical nurse reviewers (SCNRs) can sample only a subset of all surgical cases. We sought to test the feasibility of using an informatics tool to automatically identify postoperative complications stored as free-text documents in our electronic medical record. Study Design We used a locally developed electronic medical record search engine (EMERSE) to build sets of terminology that could accurately identify postoperative complications of both myocardial infarction (MI) and pulmonary embolism (PE) as defined by the ACS-NSQIP. All complications had been previously identified by our SCNRs and these were considered the gold standard. We used 5,894 cases from 2001 to 2004 from our institution's ACS-NSQIP dataset for building the terminology and 4,898 cases from 2005 to 2006 for validation. False-positive cases were then further reviewed manually. Results We achieved sensitivities of 100.0% and 92.8% for identifying postoperative myocardial infarction and pulmonary embolism, respectively, with somewhat lower specificities of 93.0% and 95.9%, respectively. These results compared favorably with results from the SCNRs, especially because our manual review uncovered cases previously missed. Conclusions Informatics has the potential to improve the efficiency and accuracy of chart abstraction by SCNRs for the ACS-NSQIP. Using such tools may eventually allow all cases at an institution to be reviewed rather than a small subset.