Validation of markerless motion capture for spatiotemporal gait measures in people with Parkinson’s disease
Bibliographic record
Abstract
Spatiotemporal gait measures are increasingly important for the characterization of gait impairments in people with Parkinson's disease (PD). Hence new assessment methods, like markerless motion capture using Theia3D, are of rising interest. This study aims to validate markerless motion capture in people with PD to retrieve spatiotemporal gait measures during overground and treadmill walking. Overground- and treadmill walking at comfortable speed were assessed in 30 individuals with PD. Markerbased and markerless motion capture were carried out in randomized order with the markerbased method using a model with markers at the heel, the lateral ankle and the toe. The markerless data (Theia Markerless Inc., Kingston, ON, Canada) was analyzed 1) with the same model as the markerbased data and 2) within the automatic report pipeline. Agreement between the measurements was assessed via mean differences, Pearson correlation coefficients, intraclass correlation coefficients and Bland-Altman methods. The results show good to excellent agreement (ICC > 0.75) between spatiotemporal gait measures of the two measurements for overground walking, except for double support time (ICC < 0.5), when analyzed with our custom algorithm. For treadmill walking all outcomes had excellent agreement (ICC > 0.9). Mean differences were below the minimal clinical differences for gait speed and step length. For the results of the automatic report during overground gait agreement between methods was poor except for gait speed and step length. Overall, the markerless motion capture system used in this study provides valid results for the assessment of spatial and temporal gait variables in people with PD, when using a gait detection algorithm that is suitable for this population.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".