A modular pipeline for natural language processing-screened human abstraction of a pragmatic trial outcome from electronic health records.

Background: Natural language processing allows efficient extraction of clinical variables and outcomes from electronic health records (EHRs). However, measuring pragmatic clinical trial outcomes may demand accuracy that exceeds natural language processing performance. Combining natural language proc...

Descripción completa

Detalles Bibliográficos
Publicado en:Clinical Trials Vol. 23; no. 2; pp. 145 - 155
Autores principales: Lee, Robert Y, Li, Kevin S, Sibley, James, Cohen, Trevor, Lober, William B, O'Brien, Janaki, LeDuc, Nicole, Mallon Andrews, Kasey, Ungar, Anna, Walsh, Jessica, Nielsen, Elizabeth L, Dotolo, Danae G, Kross, Erin K
Formato: research tables/charts Journal Article
Publicado: Sage Publications, Ltd. Apr2026
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=192767427&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 192767427
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        17407745
        AB6
      jtl: Clinical Trials
      issn: 17407745
      maglogo: N
    pubinfo:
      dt: Apr2026
      vid: 23
      iid: 2
      pid: 33180
      pub: Sage Publications, Ltd.
      place: <Blank>
    artinfo:
      ui:
        192767427
        191558123
        192767427
        192767427
        10.1177/17407745251405386
        192767427
      ppf: 145
      ppct: 10
      formats:
      tig:
        atl: A modular pipeline for natural language processing-screened human abstraction of a pragmatic trial outcome from electronic health records.
      aug:
        au:
          Lee, Robert Y
          Li, Kevin S
          Sibley, James
          Cohen, Trevor
          Lober, William B
          O'Brien, Janaki
          LeDuc, Nicole
          Mallon Andrews, Kasey
          Ungar, Anna
          Walsh, Jessica
          Nielsen, Elizabeth L
          Dotolo, Danae G
          Kross, Erin K
        affil: Division of Pulmonary, Critical Care, and Sleep Medicine, University of Washington School of Medicine, Seattle, WA, USA
      sug:
        subj:
          Natural Language Processing
          Electronic Health Records
          Clinical Trials
          Outcome Assessment
          Funding Source
          Human
          Inpatients
          Goals and Objectives
          Descriptive Statistics
          Critical Illness
          Communication
          Sensitivity and Specificity
          Confidence Intervals
      ab: Background: Natural language processing allows efficient extraction of clinical variables and outcomes from electronic health records (EHRs). However, measuring pragmatic clinical trial outcomes may demand accuracy that exceeds natural language processing performance. Combining natural language processing with human adjudication can address this gap, yet few software solutions support such workflows. We developed a modular, scalable system for natural language processing-screened human abstraction to measure the primary outcomes of two clinical trials. Methods: In two clinical trials of hospitalized patients with serious illness, a deep-learning natural language processing model screened electronic health record passages for documented goals-of-care discussions. Screen-positive passages were referred for human adjudication using a REDCap-based system to measure the trial outcomes. Dynamic pooling of passages using structured query language within the REDCap database reduced unnecessary abstraction while ensuring data completeness. Results: In the first trial (N = 2512), natural language processing identified 22,187 screen-positive passages (0.8%) from 2.6 million electronic health record passages. Human reviewers adjudicated 7494 passages over 34.3 abstractor-hours to measure the cumulative incidence and time to first documented goals-of-care discussion for all patients with 92.6% patient-level sensitivity. In the second trial (N = 617), natural language processing identified 8952 screen-positive passages (1.6%) from 559,596 passages at a threshold with near-100% sensitivity. Human reviewers adjudicated 3509 passages over 27.9 abstractor-hours to measure the same outcome for all patients. Discussion: We present the design and source code for a scalable and efficient pipeline for measuring complex electronic health record-derived outcomes using natural language processing-screened human abstraction. This implementation is adaptable to diverse research needs, and its modular pipeline represents a practical middle ground between custom software and commercial platforms.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N