TraumaICD Bidirectional Encoder Representation From Transformers: A Natural Language Processing Algorithm to Extract Injury International Classification of Diseases, 10th Edition Diagnosis Code From Free Text.

Journal: Annals of surgery
Published Date:

Abstract

OBJECTIVE: To develop and validate TraumaICDBERT, a natural language processing algorithm to predict injury International Classification of Diseases, 10th edition (ICD-10) diagnosis codes from trauma tertiary survey notes.

Authors

  • Jeff Choi
    From the Division of General Surgery (J.C., K.M., D.I.H., J.D.F.), Department of Surgery, Department of Biomedical Data Science (J.C.), Stanford University; Program in Epithelial Biology (N.Y.L.), Stanford University School of Medicine; and Department of Computer Science (A.P., K.C.), Stanford University, Stanford, California.
  • Yifu Chen
    Department of Chemical and Biological Engineering, University of Wisconsin-Madison, Madison 53706, USA.
  • Alexander Sivura
    Center for Professional Development, Stanford University, Stanford, CA.
  • Edward B Vendrow
    Department of Computer Science, Stanford University, Stanford, CA.
  • Jenny Wang
    Department of Surgery, Stanford University, Stanford, CA.
  • David A Spain