Artificial intelligence, machine learning and omic data integration in osteoarthritis
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.020 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.006 | 0.010 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".