Applying Large Language Models for Causal Structure Learning in Non Small Cell Lung Cancer

TL;DR

This paper explores using Large Language Models to determine causal relationships in medical data, specifically for Non Small Cell Lung Cancer, showing they outperform existing methods in predicting causal directions.

Contribution

It introduces a novel application of LLMs for causal discovery in healthcare, demonstrating their effectiveness in analyzing complex clinical and genomic data.

Findings

LLMs accurately predict causal edge directionality.

LLMs outperform state-of-the-art causal discovery methods.

Results suggest LLMs can enhance understanding of complex medical systems.

Abstract

Causal discovery is becoming a key part in medical AI research. These methods can enhance healthcare by identifying causal links between biomarkers, demographics, treatments and outcomes. They can aid medical professionals in choosing more impactful treatments and strategies. In parallel, Large Language Models (LLMs) have shown great potential in identifying patterns and generating insights from text data. In this paper we investigate applying LLMs to the problem of determining the directionality of edges in causal discovery. Specifically, we test our approach on a deidentified set of Non Small Cell Lung Cancer(NSCLC) patients that have both electronic health record and genomic panel data. Graphs are validated using Bayesian Dirichlet estimators using tabular data. Our result shows that LLMs can accurately predict the directionality of edges in causal graphs, outperforming existing state-of-the-art methods. These findings suggests that LLMs can play a significant role in advancing causal discovery and help us better understand complex systems.