Predicting Knee Joint Contact Forces During Normal Walking Using Kinematic Inputs With a Long-Short Term Neural Network

Knee joint contact forces are commonly estimated via surrogate measures (i.e., external knee adduction moments or musculoskeletal modeling). Despite its capabilities, modeling is not optimal for clinicians or persons with limited experience. The purpose of this study was to design a novel prediction method for knee joint contact forces that is simplistic in terms of required inputs. This study included marker trajectories and instrumented knee forces during normal walking from the "Grand Challenge" (n = 6) and "CAMS" (n = 2) datasets. Inverse kinematics were used to derive stance phase hip (sagittal, frontal, transverse), knee (sagittal, frontal), ankle (sagittal), and trunk (frontal) kinematics. A long-short term memory network (LSTM) was created using matlab to predict medial and lateral knee force waveforms using combinations of the kinematics. The Grand Challenge and CAMS datasets trained and tested the network, respectively. Musculoskeletal modeling forces were derived using static optimization and joint reaction tools in OpenSim. Waveform accuracy was determined as the proportion of variance and root-mean-square error between network predictions and in vivo data. The LSTM network was highly accurate for medial forces (R2 = 0.77, RMSE = 0.27 BW) and required only frontal hip and knee and sagittal hip and ankle kinematics. Modeled medial force predictions were excellent (R2 = 0.77, RMSE = 0.33 BW). Lateral force predictions were poor for both methods (LSTM R2 = 0.18, RMSE = 0.08 BW; modeling R2 = 0.21, RMSE = 0.54 BW). The designed LSTM network outperformed most reports of musculoskeletal modeling, including those reached in this study, revealing knee joint forces can accurately be predicted by using only kinematic input variables.

Tibiofemoral Load Magnitude and Distribution During Load Carriage

Chronic exposure to high tibiofemoral joint (TFJ) contact forces can be detrimental to knee joint health. Load carriage increases TFJ contact forces, but it is unclear whether medial and lateral tibiofemoral compartments respond similarly to incremental load carriage. The purpose of our study was to compare TFJ contact forces when walking with 15% and 30% added body weight. Young healthy adults (n = 24) walked for 5 minutes with no load, 15% load, and 30% load on an instrumented treadmill. Total, medial, and lateral TFJ contact peak forces and impulses were calculated via an inverse dynamics informed musculoskeletal model. Results of 1-way repeated measures analyses of variance (α = .05) demonstrated total, medial, and lateral TFJ first peak contact forces and impulses increased significantly with increasing load. Orthogonal polynomial trends demonstrated that the 30% loading condition led to a curvilinear increase in total and lateral TFJ impulses, whereas medial first peak TFJ contact forces and impulses responded linearly to increasing load. The total and lateral compartment impulse increased disproportionally with load carriage, while the medial did not. The medial and lateral compartments responded differently to increasing load during walking, warranting further investigation because it may relate to risk of osteoarthritis.