Evaluation of Oncotimia: An LLM based system for supporting tumour boards

TL;DR

This paper evaluates ONCOTIMIA, an AI-powered tool that automates lung cancer tumour board documentation using large language models, demonstrating high accuracy and operational viability to reduce clinician workload.

Contribution

The study introduces ONCOTIMIA, a novel modular system integrating LLMs with clinical data management to automate tumour board form completion.

Findings

Achieved up to 80% correct field completion accuracy.

Most LLMs provided clinically acceptable response times.

Larger, recent models improved accuracy without high latency.

Abstract

Multidisciplinary tumour boards (MDTBs) play a central role in oncology decision-making but require manual processes and structuring large volumes of heterogeneous clinical information, resulting in a substantial documentation burden. In this work, we present ONCOTIMIA, a modular and secure clinical tool designed to integrate generative artificial intelligence (GenAI) into oncology workflows and evaluate its application to the automatic completion of lung cancer tumour board forms using large language models (LLMs). The system combines a multi-layer data lake, hybrid relational and vector storage, retrieval-augmented generation (RAG) and a rule-driven adaptive form model to transform unstructured clinical documentation into structured and standardised tumour board records. We assess the performance of six LLMs deployed through AWS Bedrock on ten lung cancer cases, measuring both completion form accuracy and end-to-end latency. The results demonstrate high performance across models, with the best performing configuration achieving an 80% of correct field completion and clinically acceptable response time for most LLMs. Larger and more recent models exhibit best accuracies without incurring prohibitive latency. These findings provide empirical evidence that LLM- assisted autocompletion form is technically feasible and operationally viable in multidisciplinary lung cancer workflows and support its potential to significantly reduce documentation burden while preserving data quality.