Artificial intelligence, machine learning and omic data integration in osteoarthritis

OBJECTIVE: Artificial intelligence (AI), particularly its subfield of machine learning (ML), offer promising tools for integrating and interpreting high-dimensional omic data to advance our understanding of osteoarthritis (OA), a complex, multifactorial disease. The objective of this review is to summarize recent progress in applying ML approaches to single and integrative multi-omic data in OA and to highlight emerging trends, challenges, and opportunities. METHOD: We conducted a literature search of PubMed and preprint databases upto April 2025. This search identified studies that applied ML techniques including supervised learning, unsupervised clustering, deep learning, and integrative modeling to OA datasets. These datasets included transcriptomic, epigenomic, proteomic, metabolomic, and multi-omic profiles in human OA samples and relevant preclinical models. We synthesized findings across omic types, ML methodologies, and clinical or mechanistic OA outcomes, highlighting key trends in multi-omic integration strategies and their implications for OA research. RESULTS: Recent studies have applied ML to identify transcriptomic and epigenomic biomarkers, stratify OA patient subtypes, and predict disease progression. Advanced approaches such as variational autoencoders, contrastive learning, and multimodal transformers are emerging as powerful tools for multi-omic integration. However, challenges remain related to small sample sizes, overfitting, lack of external validation, model interpretability, and demographic underrepresentation in omic datasets. CONCLUSIONS: ML techniques are advancing OA research by enabling nuanced analysis of complex omic datasets. Addressing current limitations and embracing new developments in spatial and single-cell omics, generative models, and federated learning will be essential to unlock the full potential of multi-omic integration for personalized OA diagnosis and treatment.