AI to detect immune-related side effects after cancer immunotherapy
Official title: Informatics strategies to improve immune-related adverse event detection in cancer patients
Funded at Brigham and Women's Hospital · NIH-11174438 · Data updated 2026-11-12
This project uses AI language models to find and flag immune-related side effects in medical records of people treated with immune checkpoint inhibitor cancer therapies.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Brigham and Women's Hospital NIH-funded |
| Lab location | 1 site (Boston, United States) |
| Project start | September 1, 2024 |
| Project end | August 31, 2029 |
| Funding year | 2025 |
| Award (this year) | $406,537 |
| NIH project number | 5R01CA294033-02 |
| Project ID | NIH-11174438 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are people with cancer who received immune checkpoint inhibitors and have electronic health records at Brigham and Women's Hospital or participating Alliance clinical sites.
✕Less likely to help
Patients who never received checkpoint inhibitor therapy or who do not have accessible medical records at participating centers are unlikely to benefit directly from this project.
What this research studies
If you had cancer and received immune checkpoint inhibitor treatment, this project aims to read your medical records (notes and data) with AI to identify inflammatory or autoimmune side effects that can show up long after treatment. The team will build and test neural language models that combine free-text clinic notes with structured EHR data to pull out these events accurately. They will run a clinical trial of the AI-assisted approach to see if it helps clinicians register patients into an irAE biorepository (Alliance A151804) for further study. The goal is to validate the tool in real clinical settings so it can be used to improve follow-up and research for survivors living with these side effects.
Why it matters
Potential benefit: If successful, this could help spot immune-related side effects earlier and make it easier for patients to be enrolled in research that improves long-term care.
How similar studies have gone: AI and NLP tools have been used to extract clinical events from EHRs before, but applying them specifically for irAE detection and using them to drive biorepository enrollment is relatively new.
Where this research is happening
-
Brigham and Women's Hospital
Boston, United States Active
Researchers
- Principal investigator: Bitterman, Danielle S — Brigham and Women's Hospital
- Study coordinator: Bitterman, Danielle S
Related research
Other NIH-funded projects on the same topics.
-
Informatics tools to better detect immune-related side effects in cancer patients
A new informatics approach using smart language models will help doctors identify and track immune-related side effects from cancer immunotherapy in electronic health records, aiming to improve patient care.
-
Improving detection of immune-related side effects in cancer patients
This study is looking to make it easier to spot side effects that can happen to cancer patients using new immune treatments, so if you join, your health records will help us learn how to better track and understand these issues for better care.
-
Mycophenolate mofetil with prednisone for immune-related hepatitis from cancer therapy
This study tests whether starting mycophenolate mofetil plus prednisone can help liver inflammation caused by immune checkpoint inhibitors in adults with moderate to severe immune-related hepatitis.
-
Thymosin Alpha-1 plus PD-1 therapy in older adults with advanced melanoma
This trial tests whether adding Thymosin Alpha-1 to a PD-1 antibody helps people age 60 and up with advanced melanoma.
-
Inhaled budesonide to prevent recurrent checkpoint inhibitor–related pneumonitis
This study tests whether adding inhaled budesonide to usual care can prevent recurrence of pneumonitis in adults who developed grade 2 or higher lung inflammation from checkpoint inhibitor immunotherapy.
-
Investigating serum ferritin as a biomarker for immune-related adverse events
This study is testing if a blood marker called serum ferritin can help doctors identify and predict immune-related side effects in patients with cancer receiving different types of treatment.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.