Department of Bioengineering, Stanford University, Stanford, CA, USA.
Department of Mechanical Engineering, Stanford University, Stanford, CA, USA; Musculoskeletal Research Lab, VA Palo Alto Healthcare System, Palo Alto, CA, USA.
Osteoarthritis Cartilage. 2021 Mar;29(3):346-356. doi: 10.1016/j.joca.2020.12.017. Epub 2021 Jan 7.
The knee adduction moment (KAM) can inform treatment of medial knee osteoarthritis; however, measuring the KAM requires an expensive gait analysis laboratory. We evaluated the feasibility of predicting the peak KAM during natural and modified walking patterns using the positions of anatomical landmarks that could be identified from video analysis.
Using inverse dynamics, we calculated the KAM for 86 individuals (64 with knee osteoarthritis, 22 without) walking naturally and with foot progression angle modifications. We trained a neural network to predict the peak KAM using the 3-dimensional positions of 13 anatomical landmarks measured with motion capture (3D neural network). We also trained models to predict the peak KAM using 2-dimensional subsets of the dataset to simulate 2-dimensional video analysis (frontal and sagittal plane neural networks). Model performance was evaluated on a held-out, 8-person test set that included steps from all trials.
The 3D neural network predicted the peak KAM for all test steps with r( Murray et al., 2012) 2 = 0.78. This model predicted individuals' average peak KAM during natural walking with r( Murray et al., 2012) 2 = 0.86 and classified which 15° foot progression angle modifications reduced the peak KAM with accuracy = 0.85. The frontal plane neural network predicted peak KAM with similar accuracy (r( Murray et al., 2012) 2 = 0.85) to the 3D neural network, but the sagittal plane neural network did not (r( Murray et al., 2012) 2 = 0.14).
Using the positions of anatomical landmarks from motion capture, a neural network accurately predicted the peak KAM during natural and modified walking. This study demonstrates the feasibility of measuring the peak KAM using positions obtainable from 2D video analysis.
膝关节内收力矩（KAM）可用于指导膝关节骨关节炎的治疗；然而，测量 KAM 需要昂贵的步态分析实验室。我们评估了使用从视频分析中识别的解剖标志位置，在自然和改良的行走模式下预测 KAM 峰值的可行性。
我们使用逆动力学，计算了 86 名个体（64 名膝关节骨关节炎患者，22 名无膝关节骨关节炎患者）自然行走和足进角改变时的 KAM。我们使用运动捕捉测量的 13 个解剖标志的 3 维位置训练神经网络来预测 KAM 峰值（3D 神经网络）。我们还训练了模型，使用数据集的 2 维子集来预测 KAM 峰值，以模拟 2 维视频分析（额状面和矢状面神经网络）。使用包括所有试验步骤的 8 人测试集评估模型性能。
3D 神经网络可预测所有测试步骤的 KAM 峰值，r（Murray 等人，2012）2=0.78。该模型预测个体在自然行走中的平均 KAM 峰值，r（Murray 等人，2012）2=0.86，并以准确率=0.85准确分类 15°足进角改变可降低 KAM 峰值。额状面神经网络预测 KAM 峰值的准确性与 3D 神经网络相似（r（Murray 等人，2012）2=0.85），但矢状面神经网络则不然（r（Murray 等人，2012）2=0.14）。
使用运动捕捉的解剖标志位置，神经网络准确预测了自然和改良行走时的 KAM 峰值。本研究表明，使用从 2D 视频分析中获得的位置测量 KAM 峰值是可行的。
