Yili Zhang
Georgetown University, DC·Computer Science
Immune checkpoint inhibitors (ICIs) are cancer drugs that release the brakes on the immune system so it can attack tumors. They help many patients, but they can also cause the immune system to attack healthy organs.
- Fields
Computer Science
Medicine & Clinical Research
Public Health & Epidemiology
- Topics
immune checkpoint inhibitors
immune-related adverse events
irAE
- Grants
- 1 known grant, through Jun 2028
What they work on
- Develop a large language model–based natural language processing pipeline that extracts immune-related adverse event evidence, type and grade from de-identified clinical notes, creating a reusable annotated corpus.
- Build hybrid machine learning models that predict irAE risk in patients on immune checkpoint inhibitors by combining static features with lab trends over time, interpreted with explainable AI and reviewed by oncologists.
- Test whether the irAE prediction model generalizes across institutions through external validation on 1,300 patients from Hackensack Meridian Health's John Theurer Cancer Center.
More about the research
These side effects, called immune-related adverse events (irAEs), often force doctors to pause or stop treatment. Research on irAEs is held back because the details are buried in doctors' written notes and must be labeled by hand. This project proposes artificial intelligence tools to extract irAE information automatically and to flag patients at risk early in treatment.
Why it matters
Patients receiving immune checkpoint inhibitors for cancer can develop serious immune-related side effects that interrupt treatment. Automated curation from clinical notes and an interpretable risk model could help oncologists spot at-risk patients earlier and manage treatment more safely. Publicly shared tools could also make large irAE datasets cheaper to build for researchers across cancer types.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Robert Winchester
Columbia University, NY·Microbiology & Immunology
Test whether immune checkpoint inhibitors convert PD-1+ tissue-resident memory (TRM) T cells in osteoarthritic joints into inflammatory effector T cells, using a longitudinal patient study that traces T-cell receptor (TCR) clonotypes as lineage barcodes.
Bao Vuong
CUNY City College, NY·Medicine & Clinical Research
Describe the immune biology of skin side effects from immune checkpoint inhibitors using biological samples from an expanded cancer patient cohort.
Selen Bozkurt
Emory University, GA·Medicine & Clinical Research
Translate clinical trial protocol eligibility text into computable phenotypes and query packages tied to standard vocabularies, and validate them against expert references and prescreening logs.
The school
Georgetown University: 14 labs on PI Pages, $377M a year on research, 206 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.