A comparative study on deep learning models for text classification of unstructured medical notes with various levels of class imbalance.

Journal: BMC medical research methodology
Published Date:

Abstract

BACKGROUND: Discharge medical notes written by physicians contain important information about the health condition of patients. Many deep learning algorithms have been successfully applied to extract important information from unstructured medical notes data that can entail subsequent actionable results in the medical domain. This study aims to explore the model performance of various deep learning algorithms in text classification tasks on medical notes with respect to different disease class imbalance scenarios.

Authors

  • Hongxia Lu
    Schmid College of Science and Technology, Chapman University, 1 University Dr, Orange, CA, 92866, USA.
  • Louis Ehwerhemuepha
    CHOC Children's, Orange, CA, 92868, USA. lehwerhemuepha@choc.org.
  • Cyril Rakovski
    Schmid College of Science & Technology, Chapman University, Orange, CA, USA.