In this research, an artificial intelligence approach (SVM) was applied to recognize gait patterns of patients with knee OA before and after knee replacement surgery using spatio-temporal gait parameters. The SVM classifier was able to effectively recognize gait parameters that are altered due to knee OA condition before knee replacement surgery using two gait parameters (97% accuracy). Furthermore, the SVM detected improvement in gait function due to surgical intervention at 2 months following knee replacement. These results have clinical relevance in the assessment of knee OA, suggesting that gait measures should be monitored after surgery to assess treatment outcome and recovery.