MétaCan
Menu
Back to cohort
Record W4415571051 · doi:10.1302/1358-992x.2025.11.028

MARKERLESS MOTION CAPTURE IS SENSITIVE TO BIOMECHANICAL CHANGES IN GAIT KINEMATICS FOR ORTHOPAEDIC PATIENTS

2025· article· en· W4415571051 on OpenAlexaff
Elise Laende, Jereme Outerleys, Gavin Wood, Stephen Mann, Kevin J. Deluzio

Bibliographic record

VenueOrthopaedic Proceedings · 2025
Typearticle
Languageen
FieldMedicine
TopicScoliosis diagnosis and treatment
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsMotion captureKinematicsRange of motionPopulationGaitOsteoarthritisMotion analysisMotion (physics)

Abstract

fetched live from OpenAlex

The use of biomechanical data to inform clinical decision making in orthopaedics has been rare, largely due to practical limitations in obtaining motion capture data. Traditional marker-based motion capture systems are resource- and time-intensive with significant data collection burden for patients. Markerless motion capture technology using computer vision and machine learning approaches to obtain biomechanical data from standard video images offers significant advantages for ease of data collection, but must demonstrate the ability to produce relevant outcome metrics in a clinical population. The objectives of our pilot study were to (1) determine the feasibility of using markerless motion capture technology to record kinematics during a variety of tasks in an orthopaedic population by examining the task completion by participants and ability of the markerless system to track body segments and (2) to compare gait waveform data collected on a severe knee osteoarthritis (OA) population to a control group, to replaced knee joints, and to historical marker-based data for similar groups. Orthopaedic patients with knee OA were recruited directly from an orthopaedic assessment clinic after referral to an orthopaedic surgeon for total knee arthroplasty. Participants wore the clothes and shoes they had worn that day. Severe OA patients (n=77) performed functional tasks during markerless motion capture: timed up-and-go (TUG), stair ascent and descent, quiet standing (balance), walking at self-selected speed, and fast walking. Previous knee replacements in the contralateral leg were analyzed separately (n=17). The control group consisted of members of the community over 50 years of age (n=29). Markerless motion capture was performed using 8 commercially available video cameras (Sony RX0-II) recorded at 60 Hz and processed using Theia3D (Theia Markerless Inc.). Historical data using a marker-based motion capture system for severe OA post-knee replacement, and control subjects were obtained from a previous publication. The severe OA group was 56% female with mean age 69 years (SD 8). Kinematic data from the markerless system was calculated for all participants for all completed tasks with no discernable tracking issues. The control group (mean age 58 years, 59% female) had a self-selected walking speed of 1.3 m/s compared to 0.9 m/s for the severe OA group. Joint angle waveform data captured with the markerless system show similar patterns to historical data collected with marker-based motion capture for severe OA, post-knee replacement, and control groups (Figure 1). This study demonstrated feasibility of using markerless motion capture on an orthopaedic population directly from a clinic visit with no restrictions on clothing. Kinematic data from markerless motion capture exhibited expected kinematic deviations based on historical marker-based gait data on similar populations. The ease of data collection and the standardized calculation of biomechanical metrics have important implications for clinical implementation as well as longitudinal and multi-centre studies. For any figures or tables, please contact the authors directly.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.043
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.015
GPT teacher head0.283
Teacher spread0.268 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueOrthopaedic ProceedingsSame topicScoliosis diagnosis and treatmentFrench-language works237,207