Automated identification of postoperative complications within an electronic medical record using natural language processing.

CONTEXT Currently most automated methods to identify patient safety occurrences rely on administrative data codes; however, free-text searches of electronic medical records could represent an additional surveillance approach. OBJECTIVE To evaluate a natural language processing search-approach to identify postoperative surgical complications within a comprehensive electronic medical record. DESIGN, SETTING, AND PATIENTS Cross-sectional study involving 2974 patients undergoing inpatient surgical procedures at 6 Veterans Health Administration (VHA) medical centers from 1999 to 2006. MAIN OUTCOME MEASURES Postoperative occurrences of acute renal failure requiring dialysis, deep vein thrombosis, pulmonary embolism, sepsis, pneumonia, or myocardial infarction identified through medical record review as part of the VA Surgical Quality Improvement Program. We determined the sensitivity and specificity of the natural language processing approach to identify these complications and compared its performance with patient safety indicators that use discharge coding information. RESULTS The proportion of postoperative events for each sample was 2% (39 of 1924) for acute renal failure requiring dialysis, 0.7% (18 of 2327) for pulmonary embolism, 1% (29 of 2327) for deep vein thrombosis, 7% (61 of 866) for sepsis, 16% (222 of 1405) for pneumonia, and 2% (35 of 1822) for myocardial infarction. Natural language processing correctly identified 82% (95% confidence interval [CI], 67%-91%) of acute renal failure cases compared with 38% (95% CI, 25%-54%) for patient safety indicators. Similar results were obtained for venous thromboembolism (59%, 95% CI, 44%-72% vs 46%, 95% CI, 32%-60%), pneumonia (64%, 95% CI, 58%-70% vs 5%, 95% CI, 3%-9%), sepsis (89%, 95% CI, 78%-94% vs 34%, 95% CI, 24%-47%), and postoperative myocardial infarction (91%, 95% CI, 78%-97%) vs 89%, 95% CI, 74%-96%). Both natural language processing and patient safety indicators were highly specific for these diagnoses. CONCLUSION Among patients undergoing inpatient surgical procedures at VA medical centers, natural language processing analysis of electronic medical records to identify postoperative complications had higher sensitivity and lower specificity compared with patient safety indicators based on discharge coding.

[1]  L I Iezzoni,et al.  Identifying Complications of Care Using Administrative Data , 1994, Medical care.

[2]  F. Grover,et al.  The Department of Veterans Affairs' NSQIP: the first national, validated, outcome-based, risk-adjusted, and peer-controlled program for the measurement and enhancement of the quality of surgical care. National VA Surgical Quality Improvement Program. , 1998, Annals of surgery.

[3]  Marlene R. Miller,et al.  Administrative data based patient safety research: a critical review , 2003, Quality & safety in health care.

[4]  George Hripcsak,et al.  Mining complex clinical data for patient safety research: a framework for event discovery , 2003, J. Biomed. Informatics.

[5]  Patrick S. Romano,et al.  Applying Patient Safety Indicators (PSIs) Across Health Care Systems: Achieving Data Comparability , 2005 .

[6]  C. Christiansen,et al.  Evaluating the Patient Safety Indicators: How Well Do They Perform on Veterans Health Administration Data? , 2005, Medical care.

[7]  Steven H. Brown,et al.  Evaluation of the content coverage of SNOMED CT: ability of SNOMED clinical terms to represent clinical problem lists. , 2006, Mayo Clinic proceedings.

[8]  Theodore Speroff,et al.  eQuality: electronic quality assessment from narrative clinical reports. , 2006, Mayo Clinic proceedings.

[9]  A. Rosen,et al.  Tracking Rates of Patient Safety Indicators Over Time: Lessons From the Veterans Administration , 2006, Medical care.

[10]  John F. Hurdle,et al.  Automated identification of adverse events related to central venous catheters , 2007, J. Biomed. Informatics.

[11]  W. Henderson,et al.  Assessment of the reliability of data collected for the Department of Veterans Affairs national surgical quality improvement program. , 2007, Journal of the American College of Surgeons.

[12]  Anne Elixhauser,et al.  How often are potential patient safety events present on admission? , 2008, Joint Commission journal on quality and patient safety.

[13]  Darrell A Campbell,et al.  Do the AHRQ Patient Safety Indicators Flag Conditions That Are Present at the Time of Hospital Admission? , 2008, Medical care.

[14]  S. Trent Rosenbloom,et al.  eQuality for All: Extending Automated Quality Measurement of Free Text Clinical Narratives , 2008, AMIA.

[15]  John F. Hurdle,et al.  Extracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research , 2008, Yearbook of Medical Informatics.

[16]  C. Christiansen,et al.  Validity of selected AHRQ patient safety indicators based on VA National Surgical Quality Improvement Program data. , 2009, Health services research.

[17]  A. Rosen,et al.  Using administrative data to identify surgical adverse events: an introduction to the Patient Safety Indicators. , 2009, American journal of surgery.

[18]  Sowmya R. Rao,et al.  Use of electronic health records in U.S. hospitals. , 2009, The New England journal of medicine.

[19]  K. Itani.  Fifteen years of the National Surgical Quality Improvement Program in review. , 2009, American journal of surgery.

[20]  Patrick S. Romano,et al.  How Valid is the ICD-9-CM Based AHRQ Patient Safety Indicator for Postoperative Venous Thromboembolism? , 2009, Medical care.

[21]  D. Blumenthal.  Launching HITECH. , 2010, The New England journal of medicine.