Artificial Intelligence in Cellular Neuropathology: Toward Precision Neurology and Pandemic Preparedness

Infectious agents are increasingly recognized as an important risk factor for neurological diseases, with growing evidence linking both acute and persistent infections to neuroinflammation, cellular dysfunction, and the development or progression of neurodegenerative disorders, including Alzheimer’s disease, Parkinson’s disease, and amyotrophic lateral sclerosis. Rather than acting in isolation, these agents interact with host genetics, immune responses, aging, and environmental factors (e.g. pollutants, diet, lifestyle, and physical injury) to disrupt cellular homeostasis and trigger neurodegenerative processes. Understanding these complex, multidimensional interactions across molecular, cellular, and tissue levels remains a major challenge in neuroscience. The COVID-19 pandemic brought this challenge into sharp focus, demonstrating how a newly emerged virus could access the central nervous system and trigger a broad spectrum of neurological manifestations alongside persistent cognitive and neuropsychiatric sequelae. At the same time, the pandemic highlighted significant gaps in our ability to predict individual susceptibility, detect early neuropathological changes, and identify those at greatest risk of long-term neurological complications.Addressing these challenges requires analytical approaches capable of integrating the large-scale and diverse datasets that characterize modern biomedical research. Artificial intelligence (AI) and machine learning (ML) have emerged as powerful computational tools capable of identifying complex biological patterns and relationships that are difficult to detect using conventional analytical approaches. Advanced computational methods enable the integration of multi-omics and environmental exposure data (including genomics, transcriptomics, proteomics, metabolomics, digital pathology, neuroimaging, environmental exposure profiles, electronic health records, and clinical phenotypes) to identify early cellular signatures of disease, model host–pathogen interactions, characterise molecular pathways disrupted by infection, and predict disease susceptibility and progression. By bridging cellular neuropathology with systems biology and precision medicine, AI has the potential to transform our understanding of neurological disease, accelerate biomarker and therapeutic discovery, and improve early diagnosis and pandemic preparedness.This Research Topic aims to bring together experts in neuroscience, neuropathology, artificial intelligence, computational biology, genetics, and infectious diseases to address a central question: how can AI deepen our understanding of neuropathology and its broader biological context? We welcome original research, reviews, methods, and perspectives that apply computational and AI approaches to investigate the cellular and molecular mechanisms underlying neurological disease, with attention to methodological rigor, reproducibility, interpretability, and clear translational potential, fostering interdisciplinary collaborations that bridge fundamental neuroscience and computational innovation.Subtopics of interest include, but are not limited to:• AI-driven modelling of CNS invasion and host–pathogen interactions: Computational and predictive approaches to model how neurotropic viruses (e.g., SARS-CoV-2, influenza) enter the CNS and disrupt specific cellular and molecular pathways.• Computational neuropathology of infectious diseases: AI-driven approaches to investigate neuropathological changes, disease progression, and acute and long-term neurological consequences associated with viral, bacterial, fungal, and parasitic infections of the nervous system.• The gene-environment intersection: AI-enabled studies of how genetic susceptibility, epigenetic regulation, aging, diet, pollutants, toxicants, climate-related factors, and traumatic brain injury interact to influence neurological disease.• AI for cellular and molecular neuropathology: ML approaches for the analysis of histopathology, single-cell, spatial, and multi-omics datasets to uncover cellular organization, molecular mechanisms, and disease-associated pathways.• Neuroinflammation and immune dysregulation: AI-based investigation of inflammatory signalling, cytokine networks, blood–brain barrier dysfunction, microglial activation, and immune-mediated mechanisms associated with infectious and neurodegenerative diseases.• Biomarker discovery and precision diagnostics: AI approaches for identifying imaging, molecular, genetic, and biofluid biomarkers to enable the early detection of post-infectious neurological sequelae, improve diagnosis and prognosis, and support disease monitoring.• Predictive modelling of neurological risk: AI models integrating genomic, clinical, and environmental exposure data to identify individuals at risk of neurological complications and predict long-term outcomes following emerging infectious diseases.• AI-Driven Digital Pathology and Neuroimaging: AI-assisted analysis of microscopy, digital pathology, MRI, PET, CT, and multimodal neuroimaging datasets to improve disease detection, classification, biomarker discovery, and mechanistic understanding of neurological disorders.• Systems biology and AI-simulation models: Computational models integrating multi-scale biological data to simulate disease mechanisms, host responses, and therapeutic interventions in neurological disorders.• AI for therapeutic discovery and drug development: AI and ML approaches for identifying therapeutic targets, predicting drug responses, and accelerating the development of treatments for neurological diseases associated with infection and inflammation.• Pandemic preparedness through predictive AI: AI models supporting early detection of neurological risk and rapid characterisation of neurotropic pathogens to strengthen readiness for future emerging infectious disease outbreaks.• Translational and clinical applications of AI: Computational approaches that bridge basic neuroscience, neuropathology, and clinical practice to advance precision medicine, personalized risk assessment, and evidence-based healthcare decision-making.• Foundation models and multimodal AI in neuroscience: Emerging generative AI, large language models, and multimodal foundation models that integrate omics, imaging, pathology, and clinical data to support biomarker discovery, precision medicine, and translational neuroscience. Topic editors: Romina Vuono, Nigel James Temperton, Ayodeji Ibitoye, Kieren Allinson Source: https://www.frontiersin.org/research-topics/82695/artificial-intelligence-in-cellular-neuropathology-toward-precision-neurology-and-pandemic-preparedness