NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning
arXiv:2602.13770v3 Announce Type: replace-cross 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 wi
The proliferation of advanced AI architectures like Mamba and the increasing sophistication of Large Language Models (LLMs) enable more nuanced analysis of complex biological data, particularly in neuroimaging.
This development represents a significant step towards leveraging advanced AI for understanding neurodevelopmental disorders, potentially leading to earlier diagnosis and more targeted interventions for conditions like autism.
The ability to dynamically model brain functional connectivity using LLM reasoning and state-space models moves fMRI analysis beyond static representations, offering deeper insights into transient neural dynamics.
- · Neuroscience researchers
- · AI/ML developers in healthcare
- · Pharmaceutical companies investigating neurological disorders
- · Patients with neurodevelopmental disorders
- · Traditional static fMRI analysis methods
- · Diagnostic approaches solely reliant on behavioral observations
Improved diagnostic tools and personalized treatment strategies for autism and other neurological conditions.
Accelerated discovery of biomarkers and therapeutic targets through a more comprehensive understanding of brain function.
Ethical and societal considerations around advanced neuro-AI diagnostics and potential for early, even prenatal, detection of complex disorders.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG