Background:
Relieving pain is central to the early management of knee osteoarthritis, with a plethora of pharmacological agents licensed for this purpose. Intra-articular corticosteroid injections are a widely used option, albeit with variable efficacy.

Aim:
To develop a machine learning model that predicts which patients will benefit from corticosteroid injections.

Methods:
Data from two prospective cohort studies (OAI and MOST) was combined. The primary outcome was patient-reported pain score following corticosteroid injection, assessed using the WOMAC pain scale, with significant change defined using Minimally Clinically Important Difference and Meaningful Within Person Change. A machine learning algorithm was developed, utilising Linear Discriminant Analysis, to predict symptomatic improvement, and examine the association between pain scores and patient factors by calculating the sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and F2 score.

Results:
A total of 330 patients were included, with a mean age of 63.4 (SD: 8.3). The mean WOMAC pain score was 5.2 (SD: 4.1), with only 25.5% of patients achieving significant improvement in pain following corticosteroid injection. The machine learning model generated an accuracy of 67.8% (95 CI: 64.6% – 70.9%), F1 score of 30.8%, and an AUC score of 0.60.

Conclusion:
The model demonstrated feasibility to assist clinicians with decision-making in patient selection for corticosteroid injections. Further studies are required to improve the model prior to testing in clinical settings.