AD-GPT: Large Language Models in Alzheimer's Disease

2025-04-03

AI Summary

To address the limited accuracy and insufficient domain depth of general-purpose large language models (LLMs) in Alzheimer’s disease (AD)–specific knowledge retrieval, this work introduces AD-GPT—the first domain-specialized LLM for AD. AD-GPT innovatively adopts a stacked fusion architecture integrating Llama3 and BERT, enabling systematic support for four core tasks: AD-associated gene retrieval, gene–brain region association assessment, gene–AD causal inference, and brain region–AD neuropathology mapping. It is trained via domain-adaptive pretraining and multi-task fine-tuning, incorporating AD-specific genetic, molecular mechanistic, and neuroanatomical variation knowledge. Experiments demonstrate that AD-GPT significantly outperforms general LLMs (e.g., Llama3, ChatGLM) across all four tasks, achieving substantial improvements in precision and reliability. This establishes AD-GPT as a robust computational tool for elucidating AD pathogenesis and accelerating biomarker discovery.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Large language models (LLMs) have emerged as powerful tools for medical information retrieval, yet their accuracy and depth remain limited in specialized domains such as Alzheimer's disease (AD), a growing global health challenge. To address this gap, we introduce AD-GPT, a domain-specific generative pre-trained transformer designed to enhance the retrieval and analysis of AD-related genetic and neurobiological information. AD-GPT integrates diverse biomedical data sources, including potential AD-associated genes, molecular genetic information, and key gene variants linked to brain regions. We develop a stacked LLM architecture combining Llama3 and BERT, optimized for four critical tasks in AD research: (1) genetic information retrieval, (2) gene-brain region relationship assessment, (3) gene-AD relationship analysis, and (4) brain region-AD relationship mapping. Comparative evaluations against state-of-the-art LLMs demonstrate AD-GPT's superior precision and reliability across these tasks, underscoring its potential as a robust and specialized AI tool for advancing AD research and biomarker discovery.

Problem

• Enhancing accuracy of Alzheimer's disease information retrieval
• Analyzing gene-brain region relationships in AD
• Mapping genetic and neurobiological AD biomarkers

Innovation

• Domain-specific LLM for Alzheimer's disease research
• Integrated biomedical data for genetic analysis
• Stacked Llama3 and BERT architecture optimization