AI and Large Language Models for Translational Neuroscience and Beyond

Artificial intelligence (AI) and large language models (LLMs) are transforming the landscape of translational neuroscience, bridging fundamental discoveries and clinical practice. Recent years have seen an explosion in AI-driven tools capable of extracting meaning from unstructured clinical notes, multimodal patient data, and large-scale neuroimaging datasets. Yet, despite these advances, neurological disorders such as Alzheimer’s disease, Parkinson’s disease, multiple sclerosis, epilepsy, stroke, autism, and rare neurodevelopmental conditions continue to impose major global health burdens. Early diagnosis and personalized intervention remain limited by the complexity and heterogeneity of neurological phenotypes, disparate data sources, and inequitable access to specialist expertise. While emerging studies have demonstrated how machine learning can improve diagnostic and prognostic accuracy, significant challenges persist in generalizability, interpretability, ethical deployment, and clinical integration. A refined interdisciplinary dialogue among neuroscientists, clinicians, data scientists, and ethicists is therefore crucial to translate these technologies responsibly and effectively into healthcare settings.This Research Topic aims to explore the transformative potential of AI and LLMs in advancing the diagnosis, monitoring, and treatment of neurological diseases. It seeks to elucidate how intelligent computational systems can synthesize multimodal datasets—from genomics and neuroimaging to electrophysiology and patient-reported outcomes—to drive precision medicine in neuroscience. Contributors are encouraged to address fundamental questions such as: How can LLMs capture and utilize subtle linguistic and clinical cues for disease phenotyping? What architectures or frameworks best integrate imaging, omics, and behavioral data? How might explainable models foster trust among clinicians and patients, mitigating bias and ensuring equitable outcomes? The goal is to bridge algorithmic innovation with experimental and clinical validation, fostering applications that are interpretable, generalizable, and ethically grounded.The scope of this Research Topic spans the intersection of artificial intelligence, computational neuroscience, and translational medicine, with particular attention to practical, scalable, and equitable solutions. Studies are anticipated to combine methodological novelty with translational value, leveraging both retrospective and prospective data.To gather further insights in this evolving area, we welcome articles addressing, but not limited to, the following themes:o Applications of LLMs for processing electronic health records, radiology and pathology reports, and clinical narrativeso Multimodal AI integrating neuroimaging, electrophysiology, omics, and clinical data for enhanced diagnosticso AI-based prognostic modelling for disease progression, treatment response, and patient outcomeso Scalable population-level screening and early detection frameworks enabled by AIo Explainability, uncertainty quantification, and human-AI collaboration in neurological decision supporto Bias, fairness, and equity in model training and deployment across diverse populationso Benchmarking, reproducibility, and regulatory validation of AI tools for clinical neurologyWe welcome original research articles, systematic reviews, methodological papers, and perspectives that combine computational innovation with real-world clinical validation. Topic editors: Abdur Rasool, Hazrat Ali Source: https://www.frontiersin.org/research-topics/82165/ai-and-large-language-models-for-translational-neuroscience-and-beyond