Computational modelling of articular joints with biphasic cartilage: recent advances, challenges and opportunities.

Biphasic models have been widely used to simulate the time-dependent biomechanical response of soft tissues. Modelling techniques of joints with biphasic weight-bearing soft tissues have been markedly improved over the last decade, enhancing our understanding of the function, degenerative mechanism and outcomes of interventions of joints. This paper reviews the recent advances, challenges and opportunities in computational models of joints with biphasic weight-bearing soft tissues. The review begins with an introduction of the function and degeneration of joints from a biomechanical aspect. Different constitutive models of articular cartilage, in particular biphasic materials, are illustrated in the context of the study of contact mechanics in joints. Approaches, advances and major findings of biphasic models of the hip and knee are presented, followed by a discussion of the challenges awaiting to be addressed, including the convergence issue, high computational cost and inadequate validation. Finally, opportunities and clinical insights in the areas of subject-specific modeling and tissue engineering are provided and discussed.

Prediction of medial knee contact force using multisource fusion recurrent neural network and transfer learning.

Estimation of knee contact force (KCF) during gait provides essential information to evaluate knee joint function. Machine learning has been employed to estimate KCF because of the advantages of low computational cost and real-time. However, the existing machine learning models do not adequately consider gait-related data's temporal-dependent, multidimensional, and highly heterogeneous nature. This study is aimed at developing a multisource fusion recurrent neural network to predict the medial condyle KCF. First, a multisource fusion long short-term memory (MF-LSTM) model was established. Then, we developed a transfer learning strategy based on the MF-LSTM model for subject-specific medial KCF prediction. Four subjects with instrumented tibial prostheses were obtained from the literature. The results showed that the MF-LSTM model could predict medial KCF to a certain high level of accuracy (the mean of ρ = 0.970). The transfer learning model improved the prediction accuracy (the mean of ρ = 0.987). This study shows that the MF-LSTM model is a powerful and accurate computational tool for medial KCF prediction. Introducing transfer learning techniques could further improve the prediction performance for the target subject. This coupling strategy can help clinicians accurately estimate and track joint contact forces in real time.

[Three-dimensional reconstruction of femur based on Laplace operator and statistical shape model].

Reconstructing three-dimensional (3D) models from two-dimensional (2D) images is necessary for preoperative planning and the customization of joint prostheses. However, the traditional statistical modeling reconstruction shows a low accuracy due to limited 3D characteristics and information loss. In this study, we proposed a new method to reconstruct the 3D models of femoral images by combining a statistical shape model with Laplacian surface deformation, which greatly improved the accuracy of the reconstruction. In this method, a Laplace operator was introduced to represent the 3D model derived from the statistical shape model. By coordinate transformations in the Laplacian system, novel skeletal features were established and the model was accurately aligned with its 2D image. Finally, 50 femoral models were utilized to verify the effectiveness of this method. The results indicated that the precision of the method was improved by 16.8%-25.9% compared with the traditional statistical shape model reconstruction. Therefore, the method we proposed allows a more accurate 3D bone reconstruction, which facilitates the development of personalized prosthesis design, precise positioning, and quick biomechanical analysis.

The novel magnesium-titanium hybrid cannulated screws for the treatment of vertical femoral neck fractures: Biomechanical evaluation.

Background: Conventional cannulated screws are commonly used for internal fixation in the treatment of vertical femoral neck fractures. However, the noticeably high rates of undesirable outcomes such as nonunion, malunion, avascular necrosis, and fixation failure still troubled the patients and surgeons. It is urgent to develop new cannulated screws to improve the above clinical problems. The purpose of this study was to design a novel magnesium-titanium hybrid cannulated screw and to further evaluate its biomechanical performance for the treatment of vertical femoral neck fractures. Methods: A novel magnesium-titanium hybrid cannulated screw was designed, and the conventional titanium cannulated screw was also modeled. The finite element models for vertical femoral neck fractures with magnesium-titanium hybrid cannulated screws and conventional cannulated screws were respectively established. The hip joint contact force during walking gait calculated by a subject-specific musculoskeletal multibody dynamics model, was used as loads and boundary conditions for both finite element models. The stress and displacement distributions of the cannulated screws and the femur, the micromotion of the fracture surfaces of the femoral neck, and the overall stiffness were calculated and analyzed using finite element models. The biomechanical performance of the Magnesium-Titanium hybrid cannulated screws was evaluated. Results: The maximum stresses of the magnesium-titanium hybrid cannulated screws and the conventional cannulated screws were 451.5 â€‹MPa and 476.8 â€‹MPa, respectively. The maximum stresses of the femur with the above different cannulated screws were 140.3 â€‹MPa and 164.8 â€‹MPa, respectively. The maximum displacement of the femur with the hybrid cannulated screws was 6.260 â€‹mm, lower than the femur with the conventional cannulated screws, which was 7.125 â€‹mm. The tangential micromotions in the two orthogonal directions at the fracture surface of the femoral neck with the magnesium-titanium hybrid cannulated screws were comparable to those with the conventional cannulated screws. The overall stiffness of the magnesium-titanium hybrid cannulated screw system was 490.17 â€‹N/mm, higher than that of the conventional cannulated screw system, which was 433.92 â€‹N/mm. Conclusion: The magnesium-titanium hybrid cannulated screw had superior mechanical strength and fixation stability for the treatment of the vertical femoral neck fractures, compared with those of the conventional cannulated screw, indicating that the magnesium-titanium hybrid cannulated screw has great potential as a new fixation strategy in future clinical applications.The translational potential of this article: This study highlights an innovative design of the magnesium-titanium hybrid cannulated screw for the treatment of vertical femoral neck fractures. The novel magnesium-titanium hybrid cannulated screw not only to provide sufficient mechanical strength and fixation stability but also to contribute to the promotion of fracture healing, which could provide a better treatment for the vertical femoral neck fractures, beneficially reducing the incidence of nonunion and reoperation rates.

Revealing the composite fretting-corrosion mechanisms of Ti6Al4V alloy against zirconia-toughened alumina ceramic in simulated body fluid.

The composite fretting-corrosion damage due to combinations of radial, tangential, rotational, and other fretting causes local adverse tissue reactions and failure of artificial joints. Previous studies have mainly focused on the single fretting mode, while ignoring the coupled effects of multimode fretting. The fretting-corrosion mechanisms between the components are not yet fully understood. In this study, the tangential-radial composite fretting was realized by applying a normal alternating load to the tangential fretting. The composite fretting corrosion behavior of zirconia toughened alumina ceramic/Ti6Al4V alloy used for the head-neck interface of an artificial hip joint under simulated body fluid was investigated. The effects of displacement and alternating load amplitude were considered. The alternating load amplitude was given by the maximum normal load and minimum normal load ratio R. The results showed that the composite fretting damage mechanisms of this pair were mainly abrasion and tribocorrosion. Cracking also existed under large displacement. The effect of alternating load on fretting corrosion was found to be mainly caused by changes in the contact area and instantaneous contact state. In addition, the alternating load during the composite fretting promoted the formation of the three-body layer in the contact area. A decrease in load ratio caused fretting to change from gross to partial slip. In the case of small displacement, the load ratio had little effect on the friction work or wear scar profile. The corrosion rate of materials and the concentration of metal ions released into the solution increased as load ratio decreased. In cases of large and medium displacement, load ratio reduction increased the friction work and expanded the wear scar. The reduction in load ratio also caused the corrosion rate of the material to increase and then decrease, and the metal ion concentration decreased.

Friction and neuroimaging of active and passive tactile touch.

Two types of exploratory touch including active sliding and passive sliding are usually encountered in the daily life. The friction behavior of the human finger against the surface of objects is important in tactile perception. The neural mechanisms correlating to tribological behavior are not fully understood. This study investigated the tactile response of active and passive finger friction characterized with functional near-infrared spectroscopy (fNIRS). The friction test and fNIRS test were performed simultaneously using the tactile stimulus of polytetrafluoroethylene (PTFE) specimens. Results showed that the sliding modes did not obviously influence the friction property of skin. While three cortex regions were activated in the prefrontal cortex (PFC), showing a higher activation level of passive sliding. This revealed that the tribological performance was not a simple parameter to affect tactile perception, and the difference in cortical hemodynamic activity of active and passive touch was also recognised. The movement-related blood flow changes revealed the role of PFC in integrating tactile sensation although there was no estimation task on roughness perception.

[Musculoskeletal multibody dynamics investigation for the different medial-lateral installation position of the femoral component in unicompartmental knee arthroplasty].

The surgical installation accuracy of the components in unicompartmental knee arthroplasty (UKA) is an important factor affecting the joint function and the implant life. Taking the ratio of the medial-lateral position of the femoral component relative to the tibial insert (a/A) as a parameter, and considering nine installation conditions of the femoral component, this study established the musculoskeletal multibody dynamics models of UKA to simulate the patients' walking gait, and investigated the influences of the medial-lateral installation positions of the femoral component in UKA on the contact force, joint motion and ligament force of the knee joint. The results showed that, with the increase of a/A ratio, the medial contact force of the UKA implant was decreased and the lateral contact force of the cartilage was increased; the varus rotation, external rotation and posterior translation of the knee joint were increased; and the anterior cruciate ligament force, posterior cruciate ligament force and medial collateral ligament force were decreased. The medial-lateral installation positions of the femoral component in UKA had little effect on knee flexion-extension movement and lateral collateral ligament force. When the a/A ratio was less than or equalled to 0.375, the femoral component collided with the tibia. In order to prevent the overload on the medial implant and lateral cartilage, the excessive ligament force, and the collision between the femoral component and the tibia, it is suggested that the a/A ratio should be controlled within the range of 0.427-0.688 when the femoral component is installed in UKA. This study provides a reference for the accurate installation of the femoral component in UKA.

A novel algorithm to efficiently calculate the impingement-free range of motion of irregularly-shaped total hip arthroplasty components.

There is great difficulty in quickly calculating the impingement-free range of motion (IFROM) of hip components with complex shapes after total hip arthroplasty. We have established a new algorithm to investigate the effect of different shapes of hip components on the IFROM and impingement-free safe zone (IFSZ). Then find the best combination of hip prosthesis and the optimal mounting position of the elevated-rim liner under different radiographic anteversion (RA) and radiographic inclination (RI) of the cup. We found the larger the opening angle of the beveled-rim liner and the smaller the cross-sectional area of the stem neck with an inverted teardrop cross-sectional shape, the greater the IFROM of the hip component. The beveled-rim liner in combination with the stem neck with an inverted teardrop-shaped cross-section could provide the greatest IFSZ (excluding the flat-rim liner). The optimal orientation of the elevated-rim liner was the posterior-inferior side (RI ≤ 37°), posterior-superior side (RI ≥ 45°), and posterior side (37° ≤ RI ≤ 45°). Our novel algorithm provides a solution to analyze the IFROM of any hip prosthesis with any complex shape. The shape and size of the cross-section of the stem neck, the orientation of the elevated rim, and the shape and opening angle of the liner are all critical factors for the quantitative calculation of the IFROM and mounting safe zone of the prosthesis. Stem necks with inverted teardrop cross-section and beveled-rim liner improved the IFSZ. The optimal direction of the elevated rim is not constant but varies with RI and RA.

Fretting corrosion behavior of Ti6Al4V alloy against zirconia-toughened alumina ceramic in simulated body fluid.

The fretting corrosion at the head-neck interface of artificial hip joints is an important reason for the failure of prostheses. The Ti6Al4V alloy-zirconia-toughened alumina (ZTA) ceramic combination has been widely used to make the head and neck of artificial hip joints. In this study, its fretting corrosion behavior in simulated body fluid was studied by electrochemical monitoring, surface morphology characterization, and chemical composition analysis. A running condition fretting map (RCFM) of load and displacement was established, including three regimes, namely partial slip regime (PSR), mixed fretting regime (MFR), and gross slip regime (GSR). The friction dissipation energy increased gradually from the PSR to MFR and GSR. In the PSR, the damage mechanisms were slight abrasive wear and tribocorrosion at the edge of contact area, as well as extremely slight adhesive wear at the center. In the MFR, the damage mechanisms were mainly adhesive wear, abrasive wear, and corrosive wear. In the GSR, the damage mechanism was serious abrasive wear, fatigue wear, and corrosive wear combined with slight adhesive wear. Finally, an ion-concentration map was created, displaying the material-loss transition of different displacements and loads. The material loss increased with the increased displacement, and increased first and then decreased with the increased load.

Conformity design can change the effect of tibial component malrotation on knee biomechanics after total knee arthroplasty.

BACKGROUND: Component alignment is essential to improve knee function and survival in total knee arthroplasty. However, it is still unclear whether the conformity design of tibiofemoral component can mitigate abnormal knee biomechanics caused by component malrotation. The purpose of this study was to investigate whether the sagittal/coronal conformity design of the tibial component could change the effect of the tibial component malrotation on knee biomechanics in total knee arthroplasty. METHODS: A developed patient-specific musculoskeletal multi-body dynamics model of total knee arthroplasty was used to investigate the effects of the sagittal/coronal conformity of the tibial component on knee contact forces and kinematics caused by tibial component malrotation during the walking gait. FINDINGS: Medial and lateral contact forces, internal-external rotation, and anterior-posterior translation were significantly affected by tibial component malrotation after total knee arthroplasty during the walking gait. The lower sagittal conformity of the tibial component can mitigate the abnormal internal-external rotation caused by tibial component malrotation in total knee arthroplasty, the higher coronal conformity of the tibial component can mitigate the abnormal medial-lateral translation caused by tibial component malrotation in total knee arthroplasty. INTERPRETATION: This study highlights the importance of the tibiofemoral conformity designs on knee biomechanics caused by component malrotation in total knee arthroplasty. The optimization of the tibiofemoral conformity designs should be thoroughly considered in the design of new implants and in the planning of surgical procedures.

Natural polymer derived hydrogel bioink with enhanced thixotropy improves printability and cellular preservation in 3D bioprinting.

Three-dimensional (3D) bioprinting is evolving into a promising technology by spatially controlling the distribution of living cells for the biomedical field. However, maintaining high printability while protecting cells from damage due to shear stress remains the key challenge for extrusion-based 3D bioprinting. Herein, we developed a novel "protein-polyphenol-polysaccharide" extrusion-based bioink named Gel-TA-Alg@Ca2+ using gelatin (Gel), tannic acid (TA) and sodium alginate (Alg) with quantitative thixotropy by pre-crosslinking with a series of low concentrations of CaCl2 at 0.03, 0.04, 0.05 and 0.06 M, respectively. Our experimental design quantitatively presented the positive proportional functional relationship between the thixotropy of Gel-TA-Alg@Ca2+ and printability (including injectability and formability) for the first time. Importantly, the thixotropy proportionately and significantly elevated cellular viability after 3D bioprinting due to the reduced extrusion force involved in printing. 3D bioprinted constructs composed of Gel-TA-Alg@Ca2+ and MG-63 cells exhibited a good cell viability rate for more than 14 days. These findings provide valuable insights into the rational design of thixotropic bioink and offer more opportunities to probe the relationship between the thixotropy and the success of 3D bioprinting.

Decomposition of micromotion at the head-neck interface in total hip arthroplasty during walking.

Fretting corrosion as one of the leading causes for failure of modular hip prostheses has been associated with micromotion at head-neck taper junction. Decomposition of micromotion is helpful to promote the development of more realistic experiments investigating failure mechanisms of the head-neck junction in total hip arthroplasty. The aim of this study was to decompose the complex three-dimensional micromotion at the head-neck junction into multiple fundamental modes, including three translational and three rotational components. A three-dimensional finite element model composed of head-neck junction, liner and acetabular cup with a typical 12/14 taper size, as well as the taper mismatch of -4', was developed during walking. The analysis was divided into three procedures: a) the assembly simulation of the head and neck during surgery, b) verification with a simplified axisymmetric model, and c) three-dimensional modelling under normal walking. This study revealed that the main forms of micromotion contained circumferential, longitudinal micromotion and longitudinal rolling toggling, and were closely related to the state of motion. The maximum translational micromotion was predicted to be 10.9 µm during the walking gait, with the predominant modes of the circumferential translation of 9.6 µm, the longitudinal translation of 5.5 µm and the longitudinal rotation of 0.29° along the taper junction. These findings may provide design considerations for further experimental testing about fretting and facilitate the understanding of the fretting mechanisms in hip prostheses.

Articular geometry can affect joint kinematics, contact mechanics, and implant-bone micromotion in total ankle arthroplasty.

Implant loosening and bearing surface wear remain the most common failure problems of total ankle arthroplasty (TAA). One of the main factors leading to these problems is the nonphysiologic design of articular surfaces. The goals of this study were to reveal the effects of the anatomical medial-lateral borders height differences, coronal and sagittal radii on the joint kinematics, contact mechanics, and implant-bone micromotion in TAA. A previously developed and validated musculoskeletal (MSK) multibody dynamics (MBD) modeling method of TAA based on AnyBody generic MSK MBD model (five simulations for each implant) was used by combining with a finite element analysis. Five ankle implant models with different articular surface morphologies were created according to the anatomic characteristics of Chinese measurement data, marked as Implant A to E. The total ankle forces and motions during walking simulation were predicted by MSK MBD models and the contact mechanics of the bearing surface and the micromotion of the implant-bone interface of TAA were predicted by FE models. Compared with Implant A, the internal-external rotation in Implant E increased by 12.14%, the maximum of anterior-posterior translation in Implant E increased by 5.62%, the maximum reduction of tibial micromotion in Implant E was 59.98%, and for talar, micromotion was 15.36%. The ankle implant with similar anatomic articular surface has the potential to allow patients to recover better motions and reduce the risk of early loosening. This study would provide design guidance for the development of new ankle implants and further advance the development of TAA. Clinical Significance: This study promoted the improvement of ankle implant design and made contributions to improve the service life of ankle implant and patient satisfaction.

Stress-dependent design and optimization methodology of gradient porous implant and application in femoral stem.

Gradient porous structure made by additive manufacturing (AM) technology is potential to improve the long-term stability of orthopaedic implants through bone ingrowth while maintaining mechanical safety. In this study, a parametrical optimization methodology for the customized gradient porous implants was developed based on a stress-dependent design algorithm. Clinical requirements and manufacturing capabilities of AM were considered in the design procedure. A femoral stem with a minimum bone loss proportion of 2.4% by optimizing the control parameters. This study provided a feasible and flexible design approach for the customized implant with gradient porous structure or material components.

Prediction of knee biomechanics with different tibial component malrotations after total knee arthroplasty: conventional machine learning vs. deep learning.

The precise alignment of tibiofemoral components in total knee arthroplasty is a crucial factor in enhancing the longevity and functionality of the knee. However, it is a substantial challenge to quickly predict the biomechanical response to malrotation of tibiofemoral components after total knee arthroplasty using musculoskeletal multibody dynamics models. The objective of the present study was to conduct a comparative analysis between a deep learning method and four conventional machine learning methods for predicting knee biomechanics with different tibial component malrotation during a walking gait after total knee arthroplasty. First, the knee contact forces and kinematics with different tibial component malrotation in the range of ±5° in the three directions of anterior/posterior slope, internal/external rotation, and varus/valgus rotation during a walking gait after total knee arthroplasty were calculated based on the developed musculoskeletal multibody dynamics model. Subsequently, deep learning and four conventional machine learning methods were developed using the above 343 sets of biomechanical data as the dataset. Finally, the results predicted by the deep learning method were compared to the results predicted by four conventional machine learning methods. The findings indicated that the deep learning method was more accurate than four conventional machine learning methods in predicting knee contact forces and kinematics with different tibial component malrotation during a walking gait after total knee arthroplasty. The deep learning method developed in this study enabled quickly determine the biomechanical response with different tibial component malrotation during a walking gait after total knee arthroplasty. The proposed method offered surgeons and surgical robots the ability to establish a calibration safety zone, which was essential for achieving precise alignment in both preoperative surgical planning and intraoperative robotic-assisted surgical navigation.

[Design and biomechanical analysis of a self-force source power-assisted knee orthotics actuated by liquid spring].

A micro silicone oil liquid spring was designed and manufactured in this article. The performance of the liquid spring was studied by simulation analysis and mechanical test. A self-force source power-assisted knee orthosis was designed based on the liquid spring. This power-assisted knee orthosis can convert the kinetic energy of knee flexion into the elastic potential energy of liquid spring for storage, and release elastic potential energy to generate assisted torque which drives the knee joint for extension. The results showed that the average maximum reset force of the liquid spring was 1 240 N, and the average maximum assisted torque for the knee joint was 29.8 N·m. A musculoskeletal multibody dynamic model was used to analyze the biomechanical effect of the knee orthosis on the joint during knee bending (90°knee flexion). The results showed that the power-assisted knee orthosis could effectively reduce the biomechanical load of the knee joint for the user with a body weight of 80 kg. The maximum forces of the femoral-tibial joint force, patellar-femoral joint force, and quadriceps-ligament force were reduced by 24.5%, 23.8%, and 21.2%, respectively. The power-assisted knee orthosis designed in this article provides sufficient assisted torque for the knee joint. It lays a foundation for the subsequent commercial application due to its small size and lightweight.

[Rapid femur modeling method based on statistical shape model].

The geometric bone model of patients is an important basis for individualized biomechanical modeling and analysis, formulation of surgical planning, design of surgical guide plate, and customization of artificial joint. In this study, a rapid three-dimensional (3D) reconstruction method based on statistical shape model was proposed for femur. Combined with the patient plain X-ray film data, rapid 3D modeling of individualized patient femur geometry was realized. The average error of 3D reconstruction was 1.597-1.842 mm, and the root mean square error was 1.453-2.341 mm. The average errors of femoral head diameter, cervical shaft angle, offset distance and anteversion angle of the reconstructed model were 0.597 mm, 1.163°, 1.389 mm and 1.354°, respectively. Compared with traditional modeling methods, the new method could achieve rapid 3D reconstruction of femur more accurately in a shorter time. This paper provides a new technology for rapid 3D modeling of bone geometry, which is helpful to promote rapid biomechanical analysis for patients, and provides a new idea for the selection of orthopedic implants and the rapid research and development of customized implants.

Effect of Hip Joint Center on Multi-body Dynamics and Contact Mechanics of Hip Arthroplasty for Crowe IV Dysplasia.

OBJECTIVE: To investigate the hip joint forces, Von Mises stress, contact pressure and micro-motion of hip prosthesis for developmental dysplasia of the hip (DDH) patients under different hip joint centers using musculoskeletal (MSK) multi-body dynamics and finite element analysis. METHODS: Both MSK multi-body dynamics model and finite element (FE) model were based on CT data of a young female DDH patient with total hip replacement and were developed to study the biomechanics of the S-ROM hip prosthesis. The same offset of hip joint center along all six orientations compared with the standard position was set to predict its effects on both MSK multi-body dynamics and contact mechanics during one gait cycle. RESULTS: The hip joint forces in the entire walking gait cycle showed two peak values and clear differences between them under different hip joint centers. The hip joint force increased when the hip joint center moved posteriorly (2101 N) and laterally (1969 N) to the anatomical center (1848 N) at the first peak by 13.7% and 6.6%, respectively. The hip joint force increased sharply when the hip center deviated laterally (2115 N) and anteriorly (2407 N), respectively, from the standard position (1742 N) at the second peak. For the sleeve of the S-ROM prosthesis, the maximum Von Mises stress and contact pressure of the sleeve increased if the hip joint center deviated from the anatomical center posteriorly at the first peak. However, the Von Mises stresses and contact pressure increased at anterior and lateral orientations, compared to that of the standard position at the second peak. Small changes were observed for the maximum relative sliding distance along most of the orientations at both peaks except in the lateral and medial orientations, in which an increase of 8.6% and a decrease of 13.6% were observed, respectively. CONCLUSION: The hip joint center obviously influenced the hip joint forces, stress, contact pressure and micro-motion of the hip implant for this female patient.

Prediction on the medial knee contact force in patients with knee valgus using transfer learning approaches: Application to rehabilitation gaits.

The Knee contact force (KCF) is a key factor in evaluating knee joint function of patients with knee osteoarthritis. In vivo measurement of KCF based on the instrumented implants is limited due to the ethical issues and technical complexities. Machine learning can be used to predict tibiofemoral compartment contact forces. However, anthropometric differences between individuals make the accurate predictions challenging. The purpose of this study was to develop transfer learning models to predict the medial KCF of patients with knee valgus in rehabilitation gaits. Four subjects with instrumented tibial prostheses were considered, including one with knee valgus and three with normal knee joint alignment. Two transfer learning models were proposed: a fine-tuning model and an adaptive model. In particular, a synchronization method for extracting experimental data in a complete gait cycle was developed, since different types of experimental data have different sampling frequencies. The transfer learning models were pre-trained by the experiment data of patients with normal knee joint alignment, and re-trained by the data of the patient with knee valgus. Predictions of the transfer learning models and traditional machine learning model were validated against the in vivo measurements. The proposed transfer learning models were tested within two levels: the single subject (Level 1) and multiple subjects (Level 2). The results show that the two transfer learning models could more accurately predict the medial KCF of patients with knee valgus than the traditional machine learning model. The performance of the fine-tuning model is better than that of the adaptive model. Compared with the traditional machine learning and inverse dynamics analysis, transfer learning represents a much easier and more accurate method. It can be introduced to help clinicians validate and adjust the rehabilitation gait for specific patients.