Background: Osteoarthritis (OA) is a widespread degenerative joint disorder that poses substantial socioeconomic challenges. Despite progress in genetic and environmental insights, early detection is hindered by the onset of subtle symptoms and the absence of precise biomarkers.

Objectives: To identify plasma proteins associated with future risk of OA and develop a predictive model.

Methods: We conducted a large-scale proteomic analysis of 45,307 participants from the UK Biobank, excluding those with baseline OA. Plasma samples were analyzed using the Olink Explore Proximity Extension Assay, and 1,463 unique proteins were measured. Clinical variables and OA outcomes were extracted and linked to electronic health records. A predictive model was constructed using the LightGBM machine learning method, and the SHapley Additive exPlanations (SHAP) was applied to evaluate the importance of variables.

Results: We identified a panel of proteins significantly associated with the risk of developing OA. Notably, after adjusting for multiple confounders, COL9A1 and CRTAC1 were the most predictive of all incident OA, with hazard ratios (HR) of 1.54 and 1.65. The predictive model, developed using the LightGBM algorithm, integrated these proteins with clinical covariates and demonstrated an area under the curve (AUC) of 0.733 for 5-year OA prediction, 0.724 for 10-year, and 0.727 for all incident OA when combined with demographic factors. The predictive accuracy of the model was further enhanced for hip and knee OA, achieving AUCs of 0.813 and 0.818, respectively, for 5-year predictions. SHAP analysis elucidated the individual contribution of each protein and clinical variable to the model, revealing the multifactorial nature of OA risk prediction. The temporal trajectories of plasma proteins indicated that the levels of COL9A1 and CRTAC1 began to deviate from normal for more than a decade before OA onset, suggesting their potential use in early detection strategies.

Conclusion: Our study revealed the power of plasma proteomics for early OA risk prediction, emphasizing the critical role of preemptive measures. The innovative model, blending proteomic biomarkers with clinical data, provides a dependable instrument for assessing risk, potentially revolutionizing OA management and prevention tactics.

REFERENCES: [1] Global, regional, and national burden of osteoarthritis, 1990-2020 and projections to 2050: a systematic analysis for the Global Burden of Disease Study 2021. Lancet Rheumatol 2023;5:e508–22.

[2] Waheed A, Rai MF. Osteoarthriris year in review 2023: genetics, genomics, and epigenetics. Osteoarthr Cartil 2024;32:128–37.

Acknowledgements: NIL.

Disclosure of Interests: None declared.

© The Authors 2025. This abstract is an open access article published in Annals of Rheumatic Diseases under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ ). Neither EULAR nor the publisher make any representation as to the accuracy of the content. The authors are solely responsible for the content in their abstract including accuracy of the facts, statements, results, conclusion, citing resources etc.