Peak Tibiofemoral Contact Forces Estimated Using IMU-Based Approaches Are Not Significantly Different from Motion Capture-Based Estimations in Patients with Knee Osteoarthritis

Predicting Knee Joint Contact Force Peaks During Gait Using a Video Camera or Wearable Sensors

PURPOSE

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.

DISCUSSION

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.

Population-based in silico modeling of anatomical shape variation of the knee and its impact on joint loading in knee osteoarthritis

Anatomical knee joint features and osteoarthritis (OA) severity are associated, however confirming causals link to altered knee loading is challenging. This study leverages statistical shape models (SSM) to investigate the relationship between joint shape/alignment and knee loading during gait in knee OA (KOA) patients to understand their contribution to elevated medial knee loading in OA. Musculoskeletal (MSK) models were created for the mean as well as the first eight SSM principal modes of variation (-3,-2,-1, +1, +2, +3 standard deviations for each mode) and used as input to a MSK modeling framework. Using an identical KOA gait pattern (i.e., joint kinematics and ground reaction forces), we ran simulations for each MSK model and evaluated medial compartment loading magnitude and contact distribution at the instant of first and second peak of knee joint loading. An increase in external rotation, posterior tibia translation and a decrease in medial joint space and medial femoral condylar size predisposed the medial compartment knee joint to overloading during gait. This was coupled with an anterior and medial shift in contact location with increasing external rotated tibial position and increasing posterior tibial translation with respect to the femur. Next, results also highlighted a posterior shift of the medial compartment loading location with decreasing medial joint space. This study provides important population-based insights on how knee shape and alignment predispose individuals with KOA to elevated medial compartmental knee loading. This information can be crucial in assessing the risk for medial KOA development and progression.

On the prediction of tibiofemoral contact forces for healthy individuals and osteoarthritis patients during gait: a comparative study of regression methods

Knee osteoarthritis (OA) is a public health problem affecting millions of people worldwide. The intensity of the tibiofemoral contact forces is related to cartilage degeneration, and so is the importance of quantifying joint loads during daily activities. Although simulation with musculoskeletal models has been used to calculate joint loads, it demands high-cost equipment and a very time-consuming process. This study aimed to evaluate consolidated machine learning algorithms to predict tibiofemoral forces during gait analysis of healthy individuals and knee OA patients. Also, we evaluated three different datasets to train each model, considering different combinations of primary kinematic and kinetic data, and post-processing data. We evaluated 14 patients with severe unilateral knee OA and 14 healthy individuals during 3-5 gait trials. Data were split into 70% and 30% of the samples as training and test data. Test data was independently evaluated considering a mixture of pathological and healthy individuals, and only OA and Control patients. The main results showed that accurate predictions of the tibiofemoral contact forces were achieved using machine learning methods and that the predictions were sensitive to changes in the input data as training. The present study provided insights into the most promising regressions methods to predict knee contact forces representing an important starting point for the broader application of biomechanical analysis in clinical environments.

Concurrent validity of smartphone-based markerless motion capturing to quantify lower-limb joint kinematics in healthy and pathological gait

Markerless motion capturing has the potential to provide a low-cost and accessible alternative to traditional marker-based systems for real-world biomechanical assessment. However, before these systems can be put into practice, we need to rigorously evaluate their accuracy in estimating joint kinematics for various gait patterns. This study evaluated the accuracy of a low-cost, open-source, and smartphone-based markerless motion capture system, namely OpenCap, for measuring 3D joint kinematics in healthy and pathological gait compared to a marker-based system. 21 healthy volunteers were instructed to walk with four different gait patterns: physiological, crouch, circumduction, and equinus gait. Three-dimensional kinematic data were simultaneously recorded using the markerless and a marker-based motion capture system. The root mean square error (RMSE) and the peak error were calculated between every joint kinematic variable obtained by both systems. We found an overall RMSE of 5.8 (SD: 1.8 degrees) and a peak error of 11.3 degrees (SD: 3.9). A repeated measures ANOVA with post hoc tests indicated significant differences in RMSE and peak errors between the four gait patterns (p ¡ 0.05). Physiological gait presented the lowest, crouch and circumduction gait the highest errors. Our findings indicate a roughly comparable accuracy to IMU-based approaches and commercial markerless multi-camera solutions. However, errors are still above clinically desirable thresholds of two to five degrees. While our findings highlight the potential of markerless systems for assessing gait kinematics, they also underpin the need to further improve the underlying deep learning algorithms to make markerless pose estimation a valuable tool in clinical settings.