A.4 Automating gait analysis in children with Cerebral Palsy using an artificial intelligence-augmented pipeline
Bibliographic record
Abstract
Background: Cerebral palsy (CP) is a neuromotor disorder whereby gait abnormalities are predominant. Motion analysis is instrumental in management. While 3D kinematic labs exist, they are costly to operate, and the expertise required to interpret limits their availability to only a handful of facilities. In response, we have developed an Automated Intelligence (AI) driven pipeline to automate gait evaluation using 2-dimensional video. We assess the performance of this tool in comparison to traditional evaluation using visual assessment by trained human expert. Methods: A dataset of 109 patients with CP (6–37 years) (GMFCS I – II) was processed using our tool. The Edinburgh Visual Gait Score (EVGS) was derived using videos capturing sagittal and coronal views. Algorithm performance was determined by comparing automated EVGS scores against clinical expert scoring. Results: The AI pipeline successfully analysed 105/109 patient videos. For most EVGS parameters (14/17), the algorithm demonstrated moderate to high accuracy (70-94%), while 3 parameters (hindfoot valgus/varus, maximum lateral trunk shift, pelvic rotation at midstance) demonstrated lower accuracy (58-62%). Conclusions: This study validates the feasibility of an AI-augmented pipeline for automating EVGS-based gait assessments. With ongoing development, this technology has potential to improve accessibility to gait analysis and allows deployment outside of traditional settlings.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| 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) | 0.005 | 0.002 |
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".