Bayesian parameter estimation of ligament properties based on tibio-femoral kinematics during squatting

Bartsoen, Laura; Faes, Matthias; Andersen, Michael Skipper; Wirix-Speetjens, Roel; Moens, David; Jonkers, Ilse; Sloten, Jos Vander

doi:10.1016/j.ymssp.2022.109525

Cited by 8 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, physics-based models simplify the human body using parameterized formulas, where parameters were traditionally determined empirically or using population averages. Alternatively, these parameters can be learned from collected data using machine learning [102, 103].…”

Section: Discussionmentioning

confidence: 99%

Towards Out-of-Lab Anterior Cruciate Ligament Injury Prevention and Rehabilitation Assessment: A Review of Portable Sensing Approaches

Tan

Gatti

Fan

et al. 2022

Preprint

View full text Add to dashboard Cite

Anterior cruciate ligament (ACL) injury and ACL reconstruction (ACLR) surgery are common. Many ACL-injured subjects develop osteoarthritis within a decade of injury, a major cause of disability without cure. Laboratory-based biomechanical assessment can evaluate ACL injury risk and rehabilitation progress after ACLR; however, lab-based measurements are expensive and inaccessible to a majority of people. Portable sensors such as wearables and cameras can be deployed during sporting activities, in clinics, and in patient homes for biomechanical assessment. Although many portable sensing approaches have demonstrated promising results during various assessments related to ACL injury, they have not yet been widely adopted as tools for ACL injury prevention training, evaluation of ACL reconstructions, and return-to-sport decision making. The purpose of this review is to summarize research on out-of-lab portable sensing applied to ACL and ACLR and offer our perspectives on new opportunities for future research and development. We identified 49 original research articles on out-of-lab ACL-related assessment; the most common sensing modalities were inertial measurement units (IMUs), depth cameras, and RGB cameras. The studies combined portable sensors with direct feature extraction, physics-based modeling, or machine learning to estimate a range of biomechanical parameters (e.g., knee kinematics and kinetics) during jump-landing tasks, cutting, squats, and gait. Many of the reviewed studies depict proof-of-concept methods for potential future clinical applications including ACL injury risk screening, injury prevention training, and rehabilitation assessment. By synthesizing these results, we describe important opportunities that exist for using sophisticated modeling techniques to enable more accurate assessment along with standardization of data collection and creation of large benchmark datasets. If successful, these advances will enable widespread use of portable-sensing approaches to identify ACL injury risk factors, mitigate high-risk movements prior to injury, and optimize rehabilitation paradigms.

show abstract

Section: Discussionmentioning

confidence: 99%

Towards Out-of-Lab Anterior Cruciate Ligament Injury Prevention and Rehabilitation Assessment: A Review of Portable Sensing Approaches

Tan

Gatti

Fan

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…These safe zones will be referred to as SZ D , SZ D&S , and SZ D&K , respectively. Further details on the definition of the posterior distributions can be found in Bartsoen et al (2023) .…”

Section: Methodsmentioning

confidence: 99%

“…The transitional Markov chain Monte Carlo (TMCMC) ( Ching and Chen, 2007 ; Betz et al, 2016 ) algorithm is used to perform the BPE. For further details on the implementation, we refer to Bartsoen et al (2023) . This study determines the possible ligament properties based on experimental measurement data of the kinematics of a squat motion.…”

Section: Methodsmentioning

confidence: 99%

“…This results in a network with respectively 51 and 45 input parameters for the native and post-TKA MSKM. Further information on the ANN for the native MSKM can be found in Bartsoen et al (2023) . Although, where the native ANN is trained on the entire input parameter range has been given in Table 2 , this is not required for the post-TKA ANN.…”

Section: Methodsmentioning

confidence: 99%

“…In addition, almost no or very limited information on the reference strain is available. Bartsoen et al (2023) estimated a collection of sets of ligament properties while accounting for physiologically relevant ligament strains, based on in vitro experimental squatting data of a knee rig experiment, which typically suffers from measurement errors. The study failed to identify a narrow range of ligament properties applicable to multiple tested specimens.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Probabilistic planning for ligament-balanced TKA—Identification of critical ligament properties

Bartsoen

Faes

Wirix-Speetjens

et al. 2022

Front. Bioeng. Biotechnol.

Self Cite

View full text Add to dashboard Cite

Total knee arthroplasty (TKA) failures are often attributed to unbalanced knee ligament loading. The current study aims to develop a probabilistic planning process to optimize implant component positioning that achieves a ligament-balanced TKA. This planning process accounts for both subject-specific uncertainty, in terms of ligament material properties and attachment sites, and surgical precision related to the TKA process typically used in clinical practice. The consequent uncertainty in the implant position parameters is quantified by means of a surrogate model in combination with a Monte Carlo simulation. The samples for the Monte Carlo simulation are generated through Bayesian parameter estimation on the native knee model in such a way that each sample is physiologically relevant. In this way, a subject-specific uncertainty is accounted for. A sensitivity analysis, using the delta-moment-independent sensitivity measure, is performed to identify the most critical ligament parameters. The designed process is capable of estimating the precision with which the targeted ligament-balanced TKA can be realized and converting this into a success probability. This study shows that without additional subject-specific information (e.g., knee kinematic measurements), a global success probability of only 12% is estimated. Furthermore, accurate measurement of reference strains and attachment sites critically improves the success probability of the pre-operative planning process. To allow more precise planning, more accurate identification of these ligament properties is required. This study underlines the relevance of investigating in vivo or intraoperative measurement techniques to minimize uncertainty in ligament-balanced pre-operative planning results, particularly prioritizing the measurement of ligament reference strains and attachment sites.

show abstract

A multi-resolution physics-informed recurrent neural network: formulation and application to musculoskeletal systems

Taneja,

He,

et al. 2023

Comput Mech

View full text Add to dashboard Cite

This work presents a multi-resolution physics-informed recurrent neural network (MR PI-RNN), for simultaneous prediction of musculoskeletal (MSK) motion and parameter identification of the MSK systems. The MSK application was selected as the model problem due to its challenging nature in mapping the high-frequency surface electromyography (sEMG) signals to the low-frequency body joint motion controlled by the MSK and muscle contraction dynamics. The proposed method utilizes the fast wavelet transform to decompose the mixed frequency input sEMG and output joint motion signals into nested multi-resolution signals. The prediction model is subsequently trained on coarser-scale input–output signals using a gated recurrent unit (GRU), and then the trained parameters are transferred to the next level of training with finer-scale signals. These training processes are repeated recursively under a transfer-learning fashion until the full-scale training (i.e., with unfiltered signals) is achieved, while satisfying the underlying dynamic equilibrium. Numerical examples on recorded subject data demonstrate the effectiveness of the proposed framework in generating a physics-informed forward-dynamics surrogate, which yields higher accuracy in motion predictions of elbow flexion–extension of an MSK system compared to the case with single-scale training. The framework is also capable of identifying muscle parameters that are physiologically consistent with the subject’s kinematics data.

show abstract

Bayesian parameter estimation of ligament properties based on tibio-femoral kinematics during squatting

Cited by 8 publications

References 30 publications

Towards Out-of-Lab Anterior Cruciate Ligament Injury Prevention and Rehabilitation Assessment: A Review of Portable Sensing Approaches

Towards Out-of-Lab Anterior Cruciate Ligament Injury Prevention and Rehabilitation Assessment: A Review of Portable Sensing Approaches

Probabilistic planning for ligament-balanced TKA—Identification of critical ligament properties

A multi-resolution physics-informed recurrent neural network: formulation and application to musculoskeletal systems

Contact Info

Product

Resources

About