EUVIMEDObjevte EUVIMED
Open access

TrialTriage, a Semiautonomous Prescreening Workflow for Resolving Ambiguity in Phase I Oncology Trial Eligibility: Development and Proof-of-Concept Study Using Synthetic Cases

Kenneth A Kern iD

JMIR Formative Research · 2026-08-05 · 10 · e100779-e100779

DOI: 10.2196/100779 ↗

At a glance

Journal article in JMIR Formative Research, published online on 2026-08-05. Written by Kenneth A Kern. Institution: Affiliate Faculty, Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, United States. Major MEDLINE topics: Workflow, Eligibility Determination, Clinical Trials, Phase I as Topic, Patient Selection. 49 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Enrollment in phase I oncology trials remains low largely because potentially eligible patients are not identified and evaluated quickly enough. Current clinical trial matching systems can identify candidate patients from the electronic health record, but cases with missing or uncertain eligibility data are often routed for offline manual review. This delay impedes clarification and prolongs the final eligibility determination.

Objective

This study evaluated TrialTriage, a semiautonomous system built on the n8n platform and designed to resolve eligibility ambiguity during prescreening for phase I oncology trials. When eligibility information is missing or uncertain, TrialTriage emails the investigator, captures the reply, and reruns classification within the same workflow.

Methods

TrialTriage combined large language model–based variable extraction from free-text clinical narratives and investigator email replies with a deterministic rule engine applying a prespecified 7-criterion protocol. Each case was classified as eligible, not eligible, or ambiguous. Ambiguous cases triggered a structured email query to the investigator, followed by reclassification after a reply. Two requests were sent at 24-hour intervals; after 48 hours without a reply, the case was referred for manual review. The system was tested on 90 synthetic patient cases generated independently by Claude Sonnet 4.6, Gemini 3.1, and Grok 4, with 30 cases per model and balanced distributions of eligible, not eligible, and ambiguous cases. Answer keys were reviewed for accuracy before system execution. Five independent reviewers classified the Claude dataset using a uniform survey form.

Results

TrialTriage’s classifications were 100% concordant with the author-confirmed ground truth in all 90 synthetic cases (95% CI 96.0%-100.0%). All ambiguous cases were correctly escalated to investigator query. The mean processing time was 2.3 (SD 0.5) minutes per 30-case dataset (range 1.8-2.8 min, approximately 3.5-5.5 s per case). The 5 reviewers achieved a mean accuracy of 96.7% (SD 3.3%), with a Fleiss κ of 0.910, and required a mean of 9.8 (SD 4.8) minutes to review 30 cases. In a subset test of 6 first-pass ambiguous cases, 4 of 6 were reclassified definitively after investigator response, while 2 remained ambiguous because the replies lacked actionable information.

Conclusions

TrialTriage demonstrates the feasibility of a semiautonomous prescreening workflow in which ambiguous cases trigger an immediate investigator email query and are reclassified after reply capture with new information within the same system. The main contribution is the integration of email ambiguity resolution into the workflow rather than immediate deferral to offline manual review. Because the evaluation used synthetic cases and label definitions aligned with the same protocol rules used to design the rule engine, these findings should be interpreted as proof of concept and implementation fidelity rather than evidence of real-world clinical performance. Prospective validation using data from real-world electronic health records would be a plausible next step.

Subjects

MeSH terms (MEDLINE)

WorkflowEligibility DeterminationClinical Trials, Phase I as TopicPatient SelectionMedical OncologyHumans

Author keywords

LLMclinical trial matchingclinical trialsfeasibility studylarge language modelnatural language processingoncologypatient accrualpatient eligibilityphase Iprescreeningsemiautonomous AIworkflow automation

Authors and institutions

  • Affiliate Faculty, Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, United States.
  • Oncology Breakthrough Advisory Group, LLC, 1804 Garnet Avenue, Suite 701, San Diego, CA, 92109, United States, 1 (619) 354-1026.

ORCID profiles: Kenneth A Kern

Cite

APA

Kern, K. A. (2026). TrialTriage, a Semiautonomous Prescreening Workflow for Resolving Ambiguity in Phase I Oncology Trial Eligibility: Development and Proof-of-Concept Study Using Synthetic Cases. JMIR Formative Research, 10, e100779-e100779. https://doi.org/10.2196/100779

Vancouver

Kern KA. TrialTriage, a Semiautonomous Prescreening Workflow for Resolving Ambiguity in Phase I Oncology Trial Eligibility: Development and Proof-of-Concept Study Using Synthetic Cases. JMIR Formative Research. 2026;10:e100779-e100779. doi:10.2196/100779

BibTeX
@article{Kern2026,
  author = {Kern, Kenneth A},
  title = {TrialTriage, a Semiautonomous Prescreening Workflow for Resolving Ambiguity in Phase I Oncology Trial Eligibility: Development and Proof-of-Concept Study Using Synthetic Cases},
  journal = {JMIR Formative Research},
  year = {2026},
  volume = {10},
  pages = {e100779--e100779},
  doi = {10.2196/100779}
}
Start for free →