Subject-Level Classification of Osteonecrosis of the Femoral Head from Wearable IMU Gait Data Using Multilevel Feature Fusion.

Imaging underpins the diagnosis and structural staging of osteonecrosis of the femoral head (ONFH) but does not directly quantify functional impairment during weight-bearing walking. We developed a subject-level ONFH classification framework using multilevel gait features acquired with wearable inertial measurement units (IMUs). Thirty healthy controls and 21 participants with imaging-confirmed ONFH completed self-paced walking trials recorded at 100 Hz. Gait cycles were segmented from bilateral foot-contact events, normalized to 120 points, and represented as 17-channel kinematic waveforms, 22-dimensional cycle-level scalar features, and 7-channel dynamic absolute asymmetry waveforms. These inputs were encoded by CNN-CBAM-BiLSTM, multilayer perceptron, and one-dimensional convolutional branches, respectively, and fused at the feature level. Evaluation used 51-fold leave-one-subject-out cross-validation, training-fold-only preprocessing, within-subject probability averaging, and five predefined random seeds. The five-seed ensemble achieved an accuracy of 0.9412, sensitivity of 0.8571, specificity of 1.0000, F1-score of 0.9231, and area under the receiver operating characteristic curve of 0.9556. Ablation analysis identified the scalar-feature vector as the principal source of incremental performance; the dynamic asymmetry branch contributed complementary information only in the complete model. These findings provide preliminary evidence for further evaluation of wearable gait-based ONFH classification in independent cohorts and objective functional assessment.