A neural network to predict the knee adduction moment in patients with osteoarthritis using anatomical landmarks obtainable from 2D video analysis

Boswell, Melissa A; Uhlrich, Scott D.; Kidziński, Łukasz; Thomas, Kevin A.; Kolesar, Julie A; Gold, Garry E.; Beaupré, Gary S.; Delp, Scott L.

doi:10.1016/j.joca.2020.12.017

Cited by 41 publications

(57 citation statements)

References 48 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Using the positions of anatomical landmarks from motion tracking, a neural network could accurately predict the peak KAM during both natural and modified walking. Their study validated the feasibility of measuring the peak KAM using positions obtainable from OpenPose analysis [38]. The most prevalent ADHD subtypes are ADHD-C and ADHD-H (78.0-81.7%), followed by ADHD-I (18.3-22.0%) [39][40][41].…”

Section: Discussionmentioning

confidence: 95%

“…OpenPose is a method of localizing anatomical key points or "parts," and it has largely been employed for identifying an individual's body parts. This method has been used in the diagnosis and monitoring of Parkinson's disease [36], epilepsy [37], osteoarthritis [38], and other human movements [26]. Sato et al used OpenPose to analyze the daily clinical video recordings of patients with Parkinson's disease recorded from the frontal angle and to convert normal gait video recordings to sequential joint coordinate data.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Therapeutic Effects of ADHD Medication Objectively by Movement Quantification with a Video-Based Skeleton Analysis

Ouyang

Chiu

Chiang

et al. 2021

IJERPH

View full text Add to dashboard Cite

Attention-deficit/hyperactivity disorder (ADHD) is the most common neuropsychiatric disorder in children. Several scales are available to evaluate ADHD therapeutic effects, including the Swanson, Nolan, and Pelham (SNAP) questionnaire, the Vanderbilt ADHD Diagnostic Rating Scale, and the visual analog scale. However, these scales are subjective. In the present study, we proposed an objective and automatic approach for evaluating the therapeutic effects of medication in patients with (ADHD). The approach involved using movement quantification of patients’ skeletons detected automatically with OpenPose in outpatient videos. Eleven skeleton parameter series were calculated from the detected skeleton sequence, and the corresponding 33 features were extracted using autocorrelation and variance analysis. This study enrolled 25 patients with ADHD. The outpatient videos were recorded before and after medication treatment. Statistical analysis indicated that four features corresponding to the first autocorrelation coefficients of the original series of four skeleton parameters and 11 features each corresponding to the first autocorrelation coefficients of the differenced series and the averaged variances of the original series of 11 skeleton parameters significantly decreased after the use of methylphenidate, an ADHD medication. The results revealed that the proposed approach can support physicians as an objective and automatic tool for evaluating the therapeutic effects of medication on patients with ADHD.

show abstract

Section: Discussionmentioning

confidence: 95%

Section: Discussionmentioning

confidence: 99%

Evaluating Therapeutic Effects of ADHD Medication Objectively by Movement Quantification with a Video-Based Skeleton Analysis

Ouyang

Chiu

Chiang

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…As knee osteoarthritis patients at a higher weight have a larger weight-normalized KAM than their lean age-matched osteoarthritic controls [35], further investigation is warranted to determine the effect, if any, of weight on KAM reduction and gait retraining outcomes. In a previous study, a neural network trained on 3D anatomical features from 86 subjects was used to classify whether an individual would increase or reduce their first peak KAM with toe-in or toe-out gait modifications, attaining accuracies of up to 85% [36]. The most salient features of their model included those related to the position of the pelvis, knee angle in the frontal plane, and sway of the trunk; in the future, a sensor-fusion approach that combines wearable sensing and advances in markerless motion capture could make use of these additional pelvis and trunk features to improve our predictive model.…”

Section: Discussionmentioning

confidence: 99%

Predicting Knee Adduction Moment Response to Gait Retraining with Minimal Clinical Data

Rokhmanova

Kuchenbecker

et al. 2021

Preprint

View full text Add to dashboard Cite

Knee osteoarthritis is a progressive disease mediated by high joint loads. Foot progression angle modifications that reduce the knee adduction moment (KAM), a surrogate of knee loading, have demonstrated efficacy in alleviating pain and improving function. Although changes to the foot progression angle are overall beneficial, KAM reductions are not consistent across patients. Moreover, customized interventions are time-consuming and require instrumentation not commonly available in the clinic. We present a model that uses minimal clinical data to predict the extent of first peak KAM reduction after toe-in gait retraining. For such a model to generalize, the training data must be large and variable. Given the lack of large public datasets that contain different gaits for the same patient, we generated this dataset synthetically. Insights learned from ground-truth datasets with both baseline and toe-in gait trials (N=12) enabled the creation of a large (N=138) synthetic dataset for training the predictive model. On a test set of data collected by a separate research group (N=15), the first peak KAM reduction was predicted with a mean absolute error of 0.134% body weight * height (%BW*HT). This error is smaller than the test set’s subject average standard deviation of the first peak during baseline walking (0.306%BW*HT). This work demonstrates the feasibility of training predictive models with synthetic data and may provide clinicians with a streamlined pathway to identify a patient-specific gait retraining outcome without requiring gait lab instrumentation.

show abstract

“…This approach offers significant advantages over a single camera view, in part because occlusions occur and out-of-plane motions are not well-captured by a single camera; however, this approach also has potential drawbacks associated with setup and computational complexity. Last, it is also possible to use the pose estimation output as an input for further processing by neural networks designed to predict specific metrics of interest [32][33][34]. Subsequent processing by neural networks may be appropriate when predicting a scalar value such as peak knee flexion during walking or clinical ratings, but this approach may be less accurate when predicting frame-by-frame time-series data.…”

Section: What Is Pose Estimation?mentioning

confidence: 99%

“…Gait in Parkinson's disease [25,33,123] Knee kinetics in osteoarthritis [32] Gait in cerebral palsy [34] Simulated abnormal gait [72,74] Gait in older adults [73] Fall detection [76][77][78] Dyskinesias in Parkinson's disease [118][119][120] Gait in older adults with dementia…”

Section: Clinical Motor Assessmentmentioning

confidence: 99%

Applications of Pose Estimation in Human Health and Performance across the Lifespan

Stenum

Cherry‐Allen

Pyles

et al. 2021

Sensors

View full text Add to dashboard Cite

The emergence of pose estimation algorithms represents a potential paradigm shift in the study and assessment of human movement. Human pose estimation algorithms leverage advances in computer vision to track human movement automatically from simple videos recorded using common household devices with relatively low-cost cameras (e.g., smartphones, tablets, laptop computers). In our view, these technologies offer clear and exciting potential to make measurement of human movement substantially more accessible; for example, a clinician could perform a quantitative motor assessment directly in a patient’s home, a researcher without access to expensive motion capture equipment could analyze movement kinematics using a smartphone video, and a coach could evaluate player performance with video recordings directly from the field. In this review, we combine expertise and perspectives from physical therapy, speech-language pathology, movement science, and engineering to provide insight into applications of pose estimation in human health and performance. We focus specifically on applications in areas of human development, performance optimization, injury prevention, and motor assessment of persons with neurologic damage or disease. We review relevant literature, share interdisciplinary viewpoints on future applications of these technologies to improve human health and performance, and discuss perceived limitations.

show abstract

A neural network to predict the knee adduction moment in patients with osteoarthritis using anatomical landmarks obtainable from 2D video analysis

Cited by 41 publications

References 48 publications

Evaluating Therapeutic Effects of ADHD Medication Objectively by Movement Quantification with a Video-Based Skeleton Analysis

Evaluating Therapeutic Effects of ADHD Medication Objectively by Movement Quantification with a Video-Based Skeleton Analysis

Predicting Knee Adduction Moment Response to Gait Retraining with Minimal Clinical Data

Applications of Pose Estimation in Human Health and Performance across the Lifespan

Contact Info

Product

Resources

About