Natural Language Processing Accurately Differentiates Cancer Symptom Information in Electronic Health Record Narratives.

Journal: JCO clinical cancer informatics
Published Date: Aug 1, 2024

Abstract

PURPOSE: Identifying cancer symptoms in electronic health record (EHR) narratives is feasible with natural language processing (NLP). However, more efficient NLP systems are needed to detect various symptoms and distinguish observed symptoms from negated symptoms and medication-related side effects. We evaluated the accuracy of NLP in (1) detecting 14 symptom groups (ie, pain, fatigue, swelling, depressed mood, anxiety, nausea/vomiting, pruritus, headache, shortness of breath, constipation, numbness/tingling, decreased appetite, impaired memory, disturbed sleep) and (2) distinguishing observed symptoms in EHR narratives among patients with cancer.

Authors

  • Alaa Albashayreh
    College of Nursing, The University of Iowa, Iowa City, United States.
  • Anindita Bandyopadhyay
    Tippie College of Business, University of Iowa, Iowa City, IA.
  • Nahid Zeinali
    Department of Computer Science, The University of Iowa, Iowa City, United States.
  • Min Zhang
    Department of Infectious Disease, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Weiguo Fan
    Departments of Biomedical Sciences and Pathobiology (Awaysheh, Wilcke, Zimmerman), Virginia Tech, Blacksburg, VAPopulation Health Sciences (Elvinger), Virginia Tech, Blacksburg, VABusiness Information Technology (Rees), Virginia Tech, Blacksburg, VAAccounting and Information Systems (Fan), Virginia Tech, Blacksburg, VA.
  • Stephanie Gilbertson White
    College of Nursing, University of Iowa, Iowa City, IA.

Keywords

External Resources

Popular Topics
Recent Journals