Artificial Intelligence-Driven Integration of Gastrointestinal Microbiome Multi-Omics for Autoimmune Disease Prediction and Precision Medicine: A Scoping Review

Abstract

Context: The gut microbiome is increasingly recognized as a key regulator of immune homeostasis and host metabolism. Accumulating evidence indicates that microbial dysbiosis contributes to the initiation and progression of autoimmune diseases by altering immune signaling, intestinal barrier integrity, and metabolic pathways. Advances in multi-omics technologies, including metagenomics, metatranscriptomics, metaproteomics, and metabolomics, have enabled comprehensive characterization of host–microbiome interactions. In parallel, artificial intelligence and machine learning approaches have emerged as powerful tools for analyzing complex biological datasets and supporting precision medicine applications. This scoping review aimed to evaluate the current evidence on artificial intelligence-driven integration of gut microbiome multi-omics data for autoimmune disease prediction, biomarker discovery, therapeutic response assessment, and precision medicine implementation. Evidence Acquisition: A comprehensive literature search was conducted in PubMed, Scopus, Web of Science, and Google Scholar to identify studies published between January 2020 and March 2026. The final search was performed on March 15, 2026. Review articles, clinical investigations, experimental studies, and artificial intelligence-based analyses focusing on microbiome multi-omics integration were included. Extracted data were evaluated with respect to omics technologies, artificial intelligence methodologies, predictive performance, disease applications, biomarker identification, and translational relevance. A total of 38 studies met the inclusion criteria and were included in the qualitative synthesis. Results: The reviewed evidence demonstrated that integrating microbiome-derived multi-omics data with artificial intelligence algorithms improved disease classification, biomarker discovery, and prediction of therapeutic outcomes compared with conventional single-omics approaches. Machine learning models, including Random Forest, Support Vector Machine, and XGBoost, successfully identified microbial and metabolic signatures associated with rheumatoid arthritis, systemic lupus erythematosus, inflammatory bowel disease, and multiple sclerosis. Deep learning architectures, including convolutional neural networks, autoencoders, and graph neural networks, enabled the identification of complex host–microbiome interactions and disease-associated molecular pathways. Multimodal artificial intelligence frameworks integrating microbiome, metabolomic, genomic, and clinical datasets achieved improved predictive performance and facilitated patient stratification for personalized therapeutic interventions. Emerging technologies, such as explainable artificial intelligence, federated learning, generative artificial intelligence, and digital twin systems, demonstrated considerable potential to improve model interpretability, treatment optimization, and individualized healthcare delivery. Discussion: Artificial intelligence-assisted integration of gut microbiome multi-omics data is a promising strategy for improving the prediction of autoimmune disease and advancing precision medicine. By combining microbial, molecular, immunological, and clinical information, these approaches facilitate biomarker discovery, patient stratification, and personalized therapeutic decision-making. Despite challenges related to data heterogeneity, standardization, interpretability, and clinical validation, ongoing advances in explainable artificial intelligence, multimodal learning, federated learning, and generative artificial intelligence are expected to accelerate the translation of microbiome-based precision medicine into routine clinical practice.