Logo image
Beyond Self-consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging
Conference proceeding   Peer reviewed

Beyond Self-consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging

Chia-Hsuan Chang, Mary M. Lucas, Yeawon Lee, Christopher C. Yang and Grace Lu-Yao
ARTIFICIAL INTELLIGENCE IN MEDICINE, PT I, AIME 2024, v 14844, pp 224-228
01 Jan 2024

Abstract

Computer Science, Artificial Intelligence Engineering, Biomedical Science & Technology Computer Science Engineering Technology
Pathologic cancer stage, crucial for treatment decisions, is often buried in unstructured pathology reports. This study investigates using pre-trained clinical LLMs for stage extraction, leveraging prompting techniques like chain-of-thought to enhance model transparency. While self-consistency methods further improve LLM performance, they can introduce inconsistencies in reasoning paths and predictions. We propose an ensemble reasoning approach, aiming for reliable cancer stage extraction. Utilizing an open-source clinical LLM on real-world reports, we demonstrate that the ensemble approach improves consistency and boosts performance, paving the way for utilizing LLMs in healthcare settings where reliability and interpretability are paramount.

Metrics

Details

Logo image