On Jan. 20, 2026, Dana-Farber researchers announced developing an AI-based oncologist’s assistant that shows the potential for AI to help oncologists keep up with the fast pace of approvals of precision cancer medicines.

There are over 100 precision medicines approved for the treatment of cancer. These therapies work to shut down the cancer-driving effects of specific mutations.  Matching a patient to a medicine — the practice of precision oncology — is complex and advancing rapidly. However, there is no easy, standardized way for oncologists to stay informed of advances.

“The clinicians we engaged with said that catching up with FDA approvals is far from seamless,” says Helena Jun, PhD, a computational biologist working in the lab of Eliezer Van Allen, MD, chief of the Division of Population Sciences at Dana-Farber.  To make the process simpler, Jun and Van Allen created an AI-based oncologist’s assistant to help clinicians identify approved therapies that might be appropriate for a given patient. To build it, Jun gave the large-language model (LLM) that powers ChatGPT a crash course in precision oncology. 

The final model is available online as a research tool. It has several options, including the ability to choose a region, such as the European Union or United States, because those regions have different regulatory bodies and approvals. In a study published in Cancer Cell, the resulting tool was 93% accurate when tested with about 100 realistic queries submitted by physicians. 

The team is working toward building an AI-based model that combines augmentation with other ideas they are experimenting with. The goal is to create something that is ready to be tested in a clinical trial.