A new method based on quiet stance baseline is more effective in identifying freezing in Parkinson's disease
Bibliographic record
Abstract
Freezing, an episodic movement breakdown that goes from disrupted gait patterns to complete arrest, is a disabling symptom in Parkinson's disease. Several efforts have been made to objectively identify freezing episodes (FEs), although a standardized methodology to discriminate freezing from normal movement is lacking. Novel mathematical approaches that provide information in the temporal and frequency domains, such as the continuous wavelet transform, have demonstrated promising results detecting freezing, although still with limited effectiveness. We aimed to determine whether a computerized algorithm using the continuous wavelet transform based on baseline (i.e. no movement) rather than on amplitude decrease is more effective detecting freezing. Twenty-six individuals with Parkinson's disease performed two trials of a repetitive stepping-in-place task while they were filmed by a video camera and tracked by a motion capture system. The number of FEs and their total duration were determined from a visual inspection of the videos and from three different computed algorithms. Differences in the number and total duration of the FEs between the video inspection and each of the three methods were obtained. The accuracy to identify the time of occurrence of a FE by each method was also calculated. A significant effect of Method was found for the number (p = 0.016) and total duration (p = 0.013) of the FEs, with the method based on baseline being the closest one to the values reported from the videos. Moreover, the same method was the most accurate in detecting the time of occurrence, and the one reaching the highest sensitivity (88.2%). Findings suggest that threshold detection methods based on baseline and movement amplitude decreases capture different characteristics of Parkinsonian gait, with the first one being more effective at detecting FEs. Moreover, robust approaches that consider both time and frequency characteristics are more sensitive in identifying freezing.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
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".