JMIR Publications

ABSTRACT

Background:

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 final eligibility determination.

Objective:

Objective:

This study evaluated TrialTriage, a semi-autonomous 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:

Methods:

TrialTriage combined LLM-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 (E), Not Eligible (NE), or Ambiguous (A). Ambiguous cases triggered a structured email query to the investigator, followed by reclassification after reply. Two requests were sent at 24-hour intervals; after 48 hours without 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:

Results:

TrialTriage's classifications were 100% concordant with the author-confirmed ground truth in all 90 synthetic cases (95% CI 96.0% to 100.0%). All ambiguous cases were correctly escalated to investigator query. Mean processing time was 2.3 minutes per 30-case dataset (range 1.8 to 2.8 minutes, approximately 3.5 to 5.5 seconds per case). The five reviewers achieved a mean accuracy of 96.7%, with a Fleiss' κ of 0.910, and required a mean of 9.78 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:

Conclusions:

TrialTriage demonstrates the feasibility of a semi-autonomous 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 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.