NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning

2026-02-14

AI Summary

This study addresses the limitations of conventional fMRI analyses that rely on static functional connectivity, which fail to capture the dynamic brain network alterations characteristic of autism spectrum disorder (ASD). To overcome this, the authors propose the first end-to-end framework that integrates dynamic graph neural networks, the Mamba state space model, and a large language model (LLM) to directly learn adaptive, time-varying functional connectivity from raw BOLD signals. By freezing the LLM backbone and fine-tuning with LoRA, the model effectively suppresses motion artifacts, captures long-range temporal dependencies, and achieves high diagnostic accuracy for ASD while generating clinically interpretable textual explanations. This approach significantly advances the accuracy and semantic interpretability of dynamic fMRI analysis in neurodevelopmental disorders.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Large Language Models (LLMs) have demonstrated strong semantic reasoning across multimodal domains. However, their integration with graph-based models of brain connectivity remains limited. In addition, most existing fMRI analysis methods rely on static Functional Connectivity (FC) representations, which obscure transient neural dynamics critical for neurodevelopmental disorders such as autism. Recent state-space approaches, including Mamba, model temporal structure efficiently, but are typically used as standalone feature extractors without explicit high-level reasoning. We propose NeuroMambaLLM, an end-to-end framework that integrates dynamic latent graph learning and selective state-space temporal modelling with LLMs. The proposed method learns the functional connectivity dynamically from raw Blood-Oxygen-Level-Dependent (BOLD) time series, replacing fixed correlation graphs with adaptive latent connectivity while suppressing motion-related artifacts and capturing long-range temporal dependencies. The resulting dynamic brain representations are projected into the embedding space of an LLM model, where the base language model remains frozen and lightweight low-rank adaptation (LoRA) modules are trained for parameter-efficient alignment. This design enables the LLM to perform both diagnostic classification and language-based reasoning, allowing it to analyze dynamic fMRI patterns and generate clinically meaningful textual reports.

Problem

• functional connectivity
• autism
• dynamic graph learning
• fMRI
• neurodevelopmental disorders

Innovation

• Dynamic Functional Connectivity
• Mamba State-Space Model
• Large Language Model (LLM)
• Latent Graph Learning
• Low-Rank Adaptation (LoRA)