Application of Deep Learning Models in Classification of Sagittal Gait Patterns Based on Rodda’s Classification System in Patients with Cerebral Palsy

Gait classification has been extensively employed in the context of cerebral palsy (CP) to facilitate clinical decision-making and to assess various treatment outcomes. However, relying solely on clinical judgment can introduce inconsistencies. This study assessed the performance of deep learning models, i.e., LSTM, GRU, and Attention-LSTM in automatic classification of the CP gait patterns, based on Rodda’s classification system, in order to enhance both objectivity and accuracy. Kinematic data from 317 CP patients (634 limbs for two trials) were recorded using a Vicon motion capture system, focusing on hip, knee, and ankle angles. The data were preprocessed, normalized, and then segregated into training, validation, and test sets. The deep learning models provided moderate classification performances, in a range of $\mathbf{6 2 \%}$ to 73%. The LSTM model delivered the highest accuracy ($\mathbf{7 3. 2 2 \%}$), followed by GRU ($\mathbf{7 0. 8 6 \%}$), and Attention-LSTM ($62.55 \%$). The higher performance of the LSTM model was attributed to its ability to retain long-term temporal information. It was concluded that the deep learning models are promising tools for automatic classification of the gait pattern of CP individuals and can be well employed as a decision support system to help inexperienced clinicians. However, for more accurate classification results, they need a larger dataset of the kinematics data of CP individuals and their gait trials, as well as an even sample distribution across $C P$ groups.