Combining Rule-based NLP-lite with Rapid Iterative Chart Adjudication for Creation of a Large, Accurately Curated Cohort from EHR data: A Case Study in the Context of a Clinical Trial Emulation.

Journal: AMIA ... Annual Symposium proceedings. AMIA Symposium
Published Date:

Abstract

The aim of this work was to create a gold-standard curated cohort of 10,000+ cases from the Veteran Affairs (VA) corporate data warehouse (CDW) for virtual emulation of a randomized clinical trial (CSP#592). The trial had six inclusion/exclusion criteria lacking adequate structured data. We therefore used a hybrid computer/human approach to extract information from clinical notes. Rule-based NLP output was iteratively adjudicated by a panel of trained non-clinician content experts and non-experts using an easy-to-use spreadsheet-based rapid adjudication display. This group-adjudication process iteratively sharpened both the computer algorithm and clinical decision criteria, while simultaneously training the non-experts. The cohort was successfully created with each inclusion/exclusion decision backed by a source document. Less than 0.5% of cases required referral to specialist clinicians. It is likely that such curated datasets capturing specialist reasoning and using a process-supervised approach will acquire greater importance as training tools for future clinical AI applications.

Authors

  • Pradeep Mutalik
    VA Cooperative Studies Program Clinical Epidemiology Research Center (CSP-CERC), VA Connecticut Healthcare System, West Haven, CT.
  • Kei-Hoi Cheung
    Department of Emergency Medicine, Yale Center for Medical Informatics, Yale University School of Medicine, New Haven, CT USA ; VA Connecticut Healthcare System, West Haven, CT USA ; Extracellular RNA Communication Consortium (ERCC), ᅟ, ᅟ
  • Jennifer Green
    Department of Obstetrics & Gynaecology, North West Anglia NHS Foundation Trust, Peterborough, UK.
  • Melissa Buelt-Gebhardt
    VA Minneapolis Health Care System, Minneapolis, MN.
  • Karen F Anderson
    VA Cooperative Studies Program Clinical Epidemiology Research Center (CSP-CERC), VA Connecticut Healthcare System, West Haven, CT.
  • Vales Jeanpaul
    VA Cooperative Studies Program Clinical Epidemiology Research Center (CSP-CERC), VA Connecticut Healthcare System, West Haven, CT.
  • Linda McDonald
    Cooperative Studies Program Coordinating Center, VA Connecticut Healthcare System, West Haven, Connecticut.
  • Michael Wininger
    Yale University, New Haven, CT, USA VA Connecticut Healthcare System, West Haven, CT, USA University of Hartford, West Hartford, CT, USA michael.wininger@va.gov.
  • Yuli Li
    VA Cooperative Studies Program Clinical Epidemiology Research Center (CSP-CERC), VA Connecticut Healthcare System, West Haven, CT.
  • Nallakkandi Rajeevan
    VA Cooperative Studies Program Clinical Epidemiology Research Center (CSP-CERC), VA Connecticut Healthcare System, West Haven, CT.
  • Peter M Jessel
    VA Portland Health Care System, Portland, OR.
  • Hans Moore
    Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC; Georgetown University, Washington, DC; Uniformed Services University, Washington, DC.
  • Selçuk Adabag
    VA Minneapolis Health Care System, Minneapolis, MN.
  • Merritt H Raitt
    Portland Veterans Affairs Health Care System Knight Cardiovascular Institute, Oregon Health and Sciences University Portland OR USA.
  • Mihaela Aslan
    VA Clinical Epidemiology Research Center (CERC), VA Connecticut Healthcare System, West Haven, CT, United States of America.