# Collaborative framework on responsible AI in LLM-driven CDSS for precision oncology leveraging real-world patient data

## TL;DR

This paper introduces a responsible AI framework for using large language models in precision oncology, supported by real-world patient data and multidisciplinary collaboration.

## Contribution

A novel collaborative framework for responsible LLM integration in precision oncology, co-developed with multidisciplinary experts.

## Key findings

- A framework with five thematic dimensions and ten principles for responsible LLM use in precision oncology is proposed.
- The framework is illustrated through a thought experiment on uterine carcinosarcoma.
- Collaboration with Cancer Core Europe supports the development and application of the framework.

## Abstract

Precision oncology leverages real-world data, essential for identifying biomarkers and therapies. Large language models (LLMs) can aid at structuring unstructured data, overcoming current bottlenecks in precision oncology. We propose a framework for responsible LLM integration into precision oncology, co-developed by multidisciplinary experts and supported by Cancer Core Europe. Five thematic dimensions and ten principles for practice are outlined and illustrated through application to uterine carcinosarcoma in a thought experiment.