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
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
| Phase | Phase1; Phase2 |
|---|---|
| Study type | Interventional |
| Enrollment | 100 (estimated) |
| Sex | All |
| Sponsor | Brigham and Women's Hospital Academic / other |
| Drugs / interventions | immunotherapy |
| Locations | 2 sites (Boston, Massachusetts and 1 other locations) |
| Trial ID | NCT06789601 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
- Brigham and Women's Hospital — Boston, Massachusetts, United States (Recruiting)
- Dana-Farber Cancer Institute — Boston, Massachusetts, United States (Recruiting)
Study contacts
- Study coordinator: Danielle Bitterman, MD
- Email: dbitterman@bwh.harvard.edu
- Phone: 617-632-5734
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.