Artificial intelligence in central nervous system autoimmune diseases: from clinical decision support to mechanistic discovery and translation
6 affiliations
- 1School of Biomedical Engineering, Tsinghua University, Beijing, China
- 2Institute for Hospital Management of Tsinghua University, Tsinghua University, Shenzhen, China
- 3Departments of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
- 4Departments of Neurology, Tianjin Medical University General Hospital, Tianjin, China
- 5National Institute of Health Data Science, Peking University, Beijing, China
- 6KingMed Diagnostic Laboratory, Guangzhou, China
Abstract
Central nervous system (CNS) autoimmune diseases, including multiple sclerosis (MS), neuromyelitis optica spectrum disorder (NMOSD), autoimmune encephalitis (AE), and myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD), remain difficult to diagnose, stratify, and treat because clinical phenotypes overlap, biomarkers are imperfect, and the disease course requires longitudinal observation. Artificial intelligence (AI) is increasingly being evaluated to integrate clinical, imaging, immunological, and molecular data for decision-making in neuroimmunology. Clinical applications include automated neuroimaging analysis, differential diagnosis, disease classification, relapse prediction, prognostic stratification, and risk-informed care planning. Evidence is unevenly distributed: MS has the largest body of published work, particularly in neuroimaging, whereas studies in NMOSD, AE, and MOGAD are smaller, more heterogeneous, and often lack external validation. Computational approaches are also being applied to multi-omics, single-cell and spatial data, molecular target prioritisation, drug repositioning, trial enrichment, digital biomarkers, federated learning, and longitudinal modelling; however, these applications generally provide association, prioritisation, or hypothesis-generating evidence rather than validated therapeutic benefit. This Review maps reported applications, evidence patterns, and methodological and implementation needs rather than ranking translational maturity or implying established clinical benefit.
Related
- Clinical Translation of Artificial Intelligence in Oncology: Real-World Validation, Workflow Integration, and Precision Medicine Applications
- Bridging the Artificial Intelligence Translation Gap in Perioperative Pulmonary and Respiratory Complications: A Practical Framework for Institution-Level Implementation
- Editorial: Artificial intelligence and anti-cancer drugs: advancing discovery, personalization, and precision oncology
- Artificial intelligence in emergency trauma perioperative management: applications, performance benchmarks, and translation barriers
- Circulating Biomarkers with Artificial Intelligence for Clinical Risk Assessment and Therapeutic Monitoring: Evidence, Limitations, and Translation
BibTeX
@article{cao2026artificial,
title = {{Artificial intelligence in central nervous system autoimmune diseases: from clinical decision support to mechanistic discovery and translation}},
author = {Zijian Cao and Pei Zheng and Zhihui Qi and Yang Yao and Donglin Xie and Yazi He and Shenghua Zong and Zongjiu Zhang and Fu-Dong Shi},
journal = {EMBO Molecular Medicine},
year = {2026},
month = oct,
doi = {10.1038/s44321-026-00527-0},
url = {https://doi.org/10.1038/s44321-026-00527-0},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Artificial intelligence in central nervous system autoimmune diseases: from clinical decision support to mechanistic discovery and translation
AU - Zijian Cao
AU - Pei Zheng
AU - Zhihui Qi
AU - Yang Yao
AU - Donglin Xie
AU - Yazi He
AU - Shenghua Zong
AU - Zongjiu Zhang
AU - Fu-Dong Shi
PY - 2026
DA - 2026/10/13
JO - EMBO Molecular Medicine
DO - 10.1038/s44321-026-00527-0
UR - https://doi.org/10.1038/s44321-026-00527-0
AB - Central nervous system (CNS) autoimmune diseases, including multiple sclerosis (MS), neuromyelitis optica spectrum disorder (NMOSD), autoimmune encephalitis (AE), and myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD), remain difficult to diagnose, stratify, and treat because clinical phenotypes overlap, biomarkers are imperfect, and the disease course requires longitudinal observation. Artificial intelligence (AI) is increasingly being evaluated to integrate clinical, imaging, immunological, and molecular data for decision-making in neuroimmunology. Clinical applications include automated neuroimaging analysis, differential diagnosis, disease classification, relapse prediction, prognostic stratification, and risk-informed care planning. Evidence is unevenly distributed: MS has the largest body of published work, particularly in neuroimaging, whereas studies in NMOSD, AE, and MOGAD are smaller, more heterogeneous, and often lack external validation. Computational approaches are also being applied to multi-omics, single-cell and spatial data, molecular target prioritisation, drug repositioning, trial enrichment, digital biomarkers, federated learning, and longitudinal modelling; however, these applications generally provide association, prioritisation, or hypothesis-generating evidence rather than validated therapeutic benefit. This Review maps reported applications, evidence patterns, and methodological and implementation needs rather than ranking translational maturity or implying established clinical benefit.
SN - 1757-4676
SN - 1757-4684
ER -