<ul><li>ELM (Ensemble of Language Models) is a novel ensemble-based approach introduced to address the bottleneck in manually extracting data from unstructured pathology reports for tumor group assignment.</li><li>ELM leverages both small language models (SLMs) and large language models (LLMs), utilizing six fine-tuned SLMs.</li><li>ELM requires five-out-of-six agreement for tumor group classification, and disagreements are arbitrated by an LLM with a curated prompt.</li><li>Evaluation shows that ELM achieves an average precision and recall of 0.94, outperforming other approaches and enhancing operational efficiencies in the British Columbia Cancer Registry.</li></ul>

ELM: Ensemble of Language Models for Predicting Tumor Group from Pathology Reports

Discover more