Informatics-assisted detection of immune-related side effects to improve biorepository enrollment

A Non-Interventional Pragmatic Clinical Trial of NLP Models for the Detection of Immune-Related Adverse Events

Phase1; Phase2 Interventional Brigham and Women's Hospital · NCT06789601

This project tests whether an automated system that reads electronic health records can help identify cancer patients on immunotherapy who are having immune-related side effects so they can be enrolled in a biorepository.

Quick facts

PhasePhase1; Phase2
Study typeInterventional
Enrollment100 (estimated)
SexAll
SponsorBrigham and Women's Hospital Academic / other
Drugs / interventionsimmunotherapy
Locations2 sites (Boston, Massachusetts and 1 other locations)
Trial IDNCT06789601 on ClinicalTrials.gov

What this trial studies

This single-institution, randomized controlled study at Dana-Farber/Brigham Cancer Center will compare standard monitoring versus an informatics system that daily analyzes EHR notes to flag possible immune-related adverse events (irAEs). About 100 patients receiving immunotherapy will be randomized to either usual eligibility monitoring or informatics-assisted monitoring. Co-primary endpoints are feasibility of daily EHR inferencing and whether the system increases registration rates onto a prospective irAE biorepository. Secondary endpoints include time from irAE to data entry and expert-reviewed irAE capture rate.

Who should consider this trial

Good fit: Ideal participants are cancer patients receiving or who have received immuno-oncology therapies at the participating institutions and whose care is documented in the local EHR.

Not a fit: Patients not treated at the participating centers, not receiving immunotherapy, or without relevant EHR documentation of an irAE are unlikely to benefit from this study.

Why it matters

Potential benefit: If successful, this approach could increase and speed enrollment of immunotherapy patients with irAEs into a biorepository, improving sample availability for research that may lead to better understanding and management of these side effects.

How similar studies have performed: Natural language processing and EHR-based surveillance have shown promise for detecting adverse events in prior work, but applying automated detection specifically to improve biorepository registration is relatively novel.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Received or receiving a regimen containing one or more immuno-oncology therapeutics

Where this trial is running

Boston, Massachusetts and 1 other locations

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions MalignancyImmune Related Adverse Eventsmalignancyadverse drug eventhealth informaticsnatural language processing
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.