Objective: To reveal the gait patterns differences between higher-mileage runners (HMR) and low-mileage runners (LMR) by using the deep learning, and to investigate the role of Layer-wise relevance propagation (LRP) in explaining the classification decision of the deep neural network (DNN) classifier model. Methods: Through DNN to train and classify 1200 groups of gait feature data from HMR and LMR. Then, the LRP was used to calculate the relevance score (RS) of relevant variables at each time point, and the high relevance variables were extracted to analyze the interpretability of gait pattern differences. Results: The DNN model achieves 91.25% accuracy in gait feature classification between HMR and LMR. The contribution of variables during the 1%-47% stance phase was higher than the contribution of variables during the 48%-100% stance phase to the successful classification. Conclusion: The ankle and knee provide considerable information that can help recognize gait features between HMR and LMR, especially in the sagittal and transverse planes. The early stages of the stance are very important in the term of gait pattern recognition because it contains more effective information about gait patterns. LRP completes a feasible interpretation of the predicted results of the model, thus providing more interesting insights and more effective information for analyzing gait patterns.