Abstract：
OBJECTIVE: Estimating loading of the knee joint may be helpful in managing degenerative joint diseases. Contemporary methods to estimate loading involve calculating knee joint contact forces using musculoskeletal modeling and simulation from motion capture (MOCAP) data, which must be collected in a specialized environment and analyzed by a trained expert. To make the estimation of knee joint loading more accessible, simple input predictors should be used for predicting knee joint loading using artificial neural networks.
METHODS: We trained feedforward artificial neural networks (ANNs) to predict knee joint loading peaks from the mass, height, age, sex, walking speed, and knee flexion angle (KFA) of subjects using their existing MOCAP data. We also collected an independent MOCAP dataset while recording walking with a video camera (VC) and inertial measurement units (IMUs). We quantified the prediction accuracy of the ANNs using walking speed and KFA estimates from (1) MOCAP data, (2) VC data, and (3) IMU data separately (i.e., we quantified three sets of prediction accuracy metrics).
RESULTS: Using portable modalities, we achieved prediction accuracies between 0.13 and 0.37 root mean square error normalized to the mean of the musculoskeletal analysis-based reference values. The correlation between the predicted and reference loading peaks varied between 0.65 and 0.91. This was comparable to the prediction accuracies obtained when obtaining predictors from motion capture data.
CONCLUSIONS: The prediction results show that both VCs and IMUs can be used to estimate predictors that can be used in estimating knee joint loading outside the motion laboratory. Future studies should investigate the usability of the methods in an out-of-laboratory setting.
METHODS: We trained feedforward artificial neural networks (ANNs) to predict knee joint loading peaks from the mass, height, age, sex, walking speed, and knee flexion angle (KFA) of subjects using their existing MOCAP data. We also collected an independent MOCAP dataset while recording walking with a video camera (VC) and inertial measurement units (IMUs). We quantified the prediction accuracy of the ANNs using walking speed and KFA estimates from (1) MOCAP data, (2) VC data, and (3) IMU data separately (i.e., we quantified three sets of prediction accuracy metrics).
RESULTS: Using portable modalities, we achieved prediction accuracies between 0.13 and 0.37 root mean square error normalized to the mean of the musculoskeletal analysis-based reference values. The correlation between the predicted and reference loading peaks varied between 0.65 and 0.91. This was comparable to the prediction accuracies obtained when obtaining predictors from motion capture data.
CONCLUSIONS: The prediction results show that both VCs and IMUs can be used to estimate predictors that can be used in estimating knee joint loading outside the motion laboratory. Future studies should investigate the usability of the methods in an out-of-laboratory setting.
摘要：
目的：估计膝关节的负荷可能有助于治疗退行性关节疾病。当代估计载荷的方法涉及使用肌肉骨骼建模和运动捕获（MOCAP）数据模拟来计算膝关节接触力，必须在专门的环境中收集并由训练有素的专家进行分析。为了使膝关节负荷的估计更容易，简单的输入预测因子应用于使用人工神经网络预测膝关节负荷。
方法：我们训练了前馈人工神经网络（ANN），以根据质量预测膝关节负荷峰值，高度,年龄,性别,步行速度,和使用现有MOCAP数据的受试者的膝关节屈曲角度（KFA）。我们还收集了一个独立的MOCAP数据集，同时使用摄像机（VC）和惯性测量单元（IMU）记录步行。我们使用来自(1)MOCAP数据的步行速度和KFA估计来量化ANN的预测精度，（2）VC数据，和(3)IMU数据分别(即，我们量化了三组预测准确性指标)。
结果：使用便携式模式，我们的预测准确度为0.13~0.37均方根误差,归一化为基于肌肉骨骼分析的参考值的平均值.预测和参考负载峰之间的相关性在0.65和0.91之间变化。这与从运动捕捉数据获得预测因子时获得的预测精度相当。
结论：预测结果表明，VC和IMU均可用于估计预测因子，这些预测因子可用于在运动实验室之外估计膝关节负荷。未来的研究应该调查这些方法在实验室外环境中的可用性。
方法：我们训练了前馈人工神经网络（ANN），以根据质量预测膝关节负荷峰值，高度,年龄,性别,步行速度,和使用现有MOCAP数据的受试者的膝关节屈曲角度（KFA）。我们还收集了一个独立的MOCAP数据集，同时使用摄像机（VC）和惯性测量单元（IMU）记录步行。我们使用来自(1)MOCAP数据的步行速度和KFA估计来量化ANN的预测精度，（2）VC数据，和(3)IMU数据分别(即，我们量化了三组预测准确性指标)。
结果：使用便携式模式，我们的预测准确度为0.13~0.37均方根误差,归一化为基于肌肉骨骼分析的参考值的平均值.预测和参考负载峰之间的相关性在0.65和0.91之间变化。这与从运动捕捉数据获得预测因子时获得的预测精度相当。
结论：预测结果表明，VC和IMU均可用于估计预测因子，这些预测因子可用于在运动实验室之外估计膝关节负荷。未来的研究应该调查这些方法在实验室外环境中的可用性。
