Logo

So you want to train an oncology LLM: Start by getting close to the data

To create targeted LLMs that are suitable for diving into health-related areas like oncology, we must choose our data carefully and get as close to the original source as possible to avoid “playing telephone” with inaccurate information that could affect drug development processes or cancer outcomes.

Explore the patient journey with multimodal RWD

The notoriously complex healthcare system produces enormous quantities of data every moment. A typical care delivery network might generate petabytes of clinical, financial, laboratory, and pharmaceutical information on hundreds of thousands of patients each year – yet only a tiny fraction of this data is currently used to inform treatment decisions, support the development of new therapies, and foster better patient experiences and outcomes.

On the Ground at ISPOR 2023

Healthcare stakeholders gathered in Boston for ISPOR 2023 – the annual meeting to advance the science and practice of health economics and outcomes research (HEOR) around the world. Read insights and takeaways from the COTA team.