A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date: Oct 20, 2014

Abstract

BACKGROUND: Venous thromboembolisms (VTEs), which include deep vein thrombosis (DVT) and pulmonary embolism (PE), are associated with significant mortality, morbidity, and cost in hospitalized patients. To evaluate the success of preventive measures, accurate and efficient methods for monitoring VTE rates are needed. Therefore, we sought to determine the accuracy of statistical natural language processing (NLP) for identifying DVT and PE from electronic health record data.

Authors

  • Christian M Rochefort
    Faculty of Medicine, Ingram School of Nursing, McGill University, Montreal, Canada McGill Clinical and Health Informatics Research Group, McGill University, Montreal, Canada Department of Epidemiology, Biostatics and Occupational Health, Faculty of Medicine, McGill University, Montreal, Canada.
  • Aman D Verma
    McGill Clinical and Health Informatics Research Group, McGill University, Montreal, Canada Department of Epidemiology, Biostatics and Occupational Health, Faculty of Medicine, McGill University, Montreal, Canada.
  • Tewodros Eguale
    McGill Clinical and Health Informatics Research Group, McGill University, Montreal, Canada Brigham and Women's Hospital, Boston, Massachusetts, USA.
  • Todd C Lee
    McGill University Health Centre (MUHC), Montreal, Canada.
  • David L Buckeridge
    Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, Québec, Canada.

Keywords

External Resources

Popular Topics
Recent Journals