To facilitate the early intelligent screening of pediatric genu valgum, this study develops a deep learning–based gait recognition model tailored for clinical application. The model is constructed upon a three-dimensional residual network architecture and incorporates a triplet attention module alongside a spatial hierarchical pooling module, jointly enhancing feature interaction across temporal, spatial, and channel dimensions. This design ensures an optimal balance between representational capacity and computational efficiency. Evaluated on a self-constructed dataset, the model achieves precision of 98.0%, 97.1%, and 96.5%, recall rates of 97.5%, 97.0%, and 95.0%, and F1-scores of 0.980, 0.970, and 0.960 on the training, validation, and test sets, respectively, demonstrating excellent recognition performance and strong generalization ability. Ablation experiments confirm the importance of the proposed model’s core components in improving performance, and comparative experiments further highlight its significant advantages in recognition accuracy and robustness. Visualization experiments reveal that the model effectively focuses on key regions of gait images, with attention regions aligning closely with clinical anatomical landmarks, thereby enhancing the interpretability of the model’s decision-making in clinical applications. In summary, the proposed model not only offers an efficient and reliable technical solution for early intelligent screening of genu valgum in children, but also provides a practical pathway for applying gait recognition technology in medical diagnosis.