Accelerating Causal Network Discovery of Alzheimer Disease Biomarkers via Scientific Literature-based Retrieval Augmented Generation

2025-04-01

arXiv.org

AI Summary

Manual construction of Alzheimer’s disease (AD) biomarker causal networks suffers from low efficiency and high subjectivity, hindering reliable mechanistic insights. Method: We propose a retrieval-augmented generation (RAG)-based trustworthy reasoning framework tailored for high-stakes clinical scenarios. It integrates biomedical entity recognition, causal relation extraction, and uncertainty quantification to automatically extract AD biomarkers and infer causal edges from 200 peer-reviewed AD publications. Contribution/Results: This work pioneers the incorporation of calibrated uncertainty estimation and a hybrid “human-in-the-loop + automated” evaluation protocol into medical causal discovery—significantly enhancing the interpretability and scientific validity of large language model (LLM)-generated causal relations. Experiments demonstrate RAG’s efficacy in augmenting LLMs for medical causal reasoning and systematically uncover critical limitations of current LLMs in modeling AD pathophysiology. The framework establishes a novel paradigm for AI-driven research on neurodegenerative disorders.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

The causal relationships between biomarkers are essential for disease diagnosis and medical treatment planning. One notable application is Alzheimer's disease (AD) diagnosis, where certain biomarkers may influence the presence of others, enabling early detection, precise disease staging, targeted treatments, and improved monitoring of disease progression. However, understanding these causal relationships is complex and requires extensive research. Constructing a comprehensive causal network of biomarkers demands significant effort from human experts, who must analyze a vast number of research papers, and have bias in understanding diseases' biomarkers and their relation. This raises an important question: Can advanced large language models (LLMs), such as those utilizing retrieval-augmented generation (RAG), assist in building causal networks of biomarkers for further medical analysis? To explore this, we collected 200 AD-related research papers published over the past 25 years and then integrated scientific literature with RAG to extract AD biomarkers and generate causal relations among them. Given the high-risk nature of the medical diagnosis, we applied uncertainty estimation to assess the reliability of the generated causal edges and examined the faithfulness and scientificness of LLM reasoning using both automatic and human evaluation. We find that RAG enhances the ability of LLMs to generate more accurate causal networks from scientific papers. However, the overall performance of LLMs in identifying causal relations of AD biomarkers is still limited. We hope this study will inspire further foundational research on AI-driven analysis of AD biomarkers causal network discovery.

Problem

• Identifying causal relationships among Alzheimer's disease biomarkers efficiently
• Reducing human bias and effort in biomarker causal network construction
• Assessing LLM reliability in generating accurate medical causal networks

Innovation

• Uses retrieval-augmented generation for biomarker analysis
• Applies uncertainty estimation to assess causal edges
• Integrates 25 years of AD research papers