An interpretable metabolomic-driven machine learning model for early prediction of knee structural OA progression
Bibliographic record
Abstract
OBJECTIVES: Osteoarthritis (OA) is the most prevalent chronic musculoskeletal disease. Early identification of individuals at risk of knee structural progression is essential for targeted interventions. This study aimed to develop and validate a machine/deep learning (ML/DL)-based prognostic model for knee OA progression using serum metabolomics. METHODS: Baseline serum metabolomic factors from two independent cohorts were analysed: Tasmanian Older Adult Cohort (n = 180) for model development and Licofelone trial (n = 137) for external validation. Participants were categorized by likelihood of knee structural progression using MRI and X-ray data. Four metabolomic scenarios were evaluated: metabolites alone (104), plus their ratios or inverse ratios (each 5460) and all combined (10 816), alongside age, sex, BMI. Metabolomic profiling used high-throughput omics. Batch effects were corrected via ComBat. Feature selection combined variable clustering with elastic net regularization. Top-selected features of each scenario were trained using five ML/DL models, with performance assessed by AUC, accuracy, sensitivity and specificity with 95% CIs. RESULTS: The metabolomic-only scenario, including sex and age, yielded the best performance. Feature clustering reduced to 22, with the top 10 used for training/testing. The Artificial Neural Network with domain-adversarial component outperformed other algorithms with domain shift. The final model, including six metabolites (SM (OH) C22:2, proline, citrulline, LysoPC a C18:0, glutamate and C12-DC), plus sex and age, demonstrated excellent predictive performance (test: AUC 0.98 [0.95, 1], accuracy 0.89 [0.84, 0.94]; validation: AUC 0.89 [0.83, 0.95], accuracy 0.85 [0.79, 0.91]). CONCLUSION: This validated metabolomics DL framework (https://github.com/AFSHINJAM/KOA_Prediction_Metabolomics_Ratios) introduces a novel approach for predicting knee OA structural progression, enabling personalized risk assessment and early intervention.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".