An interpretable metabolomic-driven machine learning model for early prediction of knee structural OA progression.

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.