ABSTRACT
Introduction: Children's walking patterns evolve with age, exhibiting less repetitiveness at a young age and more variability than adults. Three-dimensional gait analysis (3DGA) is crucial for understanding and treating lower limb movement disorders in children, traditionally performed using Optical Motion Capture (OMC). Inertial Measurement Units (IMUs) offer a cost-effective alternative to OMC, although challenges like drift errors persist. Machine learning (ML) models can mitigate these issues in adults, prompting an investigation into their applicability to a heterogeneous pediatric population. This study aimed at 1) quantifying personalized and generalized ML models' performance for predicting gait time series in typically developed (TD) children using IMUs data, 2) Comparing random forest (RF) and convolutional neural networks (CNN) models' performance, 3) Finding the optimal number of IMUs required for accurate predictions. Methodology: Seventeen TD children, aged 6 to 15, participated in data collection involving OMC, force plates, and IMU sensors. Joint kinematics and kinetics (targets) were computed from OMC and force plates' data using OpenSim. Tsfresh, a Python package, extracted features from raw IMU data. Each target's ten most important features were input in the development of personalized and generalized RF and CNN models. This procedure was initially conducted with 7 IMUs placed on all lower limb segments and then performed using only two IMUs on the feet. Results: Findings suggested that the RF and CNN models demonstrated comparable performance. RF predicted joint kinematics with a 9.5% and 19.9% NRMSE for personalized and generalized models, respectively, and joint kinetics with an NRMSE of 10.7% for personalized and 15.2% for generalized models in TD children. Personalized models provided accurate estimations from IMU data in children, while generalized models lacked accuracy due to the limited dataset. Furthermore, reducing the number of IMUs from 7 to 2 did not affect the results, and the performance remained consistent. Discussion: This study proposed a promising personalized approach for gait time series prediction in children, involving an RF model and two IMUs on the feet.
ABSTRACT
Background: Pedicle screw (PS) placement has been widely used in fusion surgeries on the thoracic spine. Achieving cost-effective yet accurate placements through nonradiation techniques remains challenging. Questions/Purposes: Novel noncovering lock-mechanism bilateral vertebra-specific drill guides for PS placement were designed/fabricated, and their accuracy for both nondeformed and deformed thoracic spines was tested. Methods: One nondeformed and 1 severe scoliosis human thoracic spine underwent computed tomographic (CT) scanning, and 2 identical proportions of each were 3-dimensional (3D) printed. Pedicle-specific optimal (no perforation) drilling trajectories were determined on the CT images based on the entry point/orientation/diameter/length of each PS. Vertebra-specific templates were designed and 3D printed, assuring minimal yet firm contacts with the vertebrae through a noncovering lock mechanism. One model of each patient was drilled using the freehand and one using the template guides (96 pedicle drillings). Postoperative CT scans from the models with the inserted PSs were obtained and superimposed on the preoperative planned models to evaluate deviations of the PSs. Results: All templates fitted their corresponding vertebra during the simulated operations. As compared with the freehand approach, PS placement deviations from their preplanned positions were significantly reduced: for the nonscoliosis model, from 2.4 to 0.9 mm for the entry point, 5.0° to 3.3° for the transverse plane angle, 7.1° to 2.2° for the sagittal plane angle, and 8.5° to 4.1° for the 3D angle, improving the success rate from 71.7% to 93.5%. Conclusions: These guides are valuable, as the accurate PS trajectory could be customized preoperatively to match the patients' unique anatomy. In vivo studies will be required to validate this approach.
