From Traditional to Transformative: Gait Analysis With Wearable Technology and Machine Learning in CSVD Diagnosis and Research
Bibliographic record
Abstract
Background: Cerebral small vessel disease (CSVD) often manifests with gait impairment, a critical yet overlooked aspect of early disease progression. Our study is aimed at leveraging wearable sensors and machine learning to analyse gait characteristics, providing a cost‐effective and scalable method for early CSVD diagnosis. Methods: We collected baseline and gait data from 115 individuals diagnosed with CSVD and 120 community healthy controls. All participants underwent a quantitative gait assessment utilizing the wearable device Ambulosono. The study applied an affordable digital 6‐min walk test (6MWT) for standardized assessment, employing machine learning to build a prediction model. Results: Traditional binary logistic regression statistical analysis revealed that the most distinguished gait thresholds during a 6‐min walk were walking speed (≤ 70.34 m/min; sensitivity 0.625, specificity 0.791, AUC 0.760) and cadence (≤ 117.45; sensitivity 0.658, specificity 0.748, AUC 0.738). Gait variability was not statistically significantly different. Compared with traditional statistics, the machine learning model greatly improved the ability of gait characteristics to predict CSVD. We used a random forest model to train the selected features, and the AUC of the CSVD prediction mode increased from 0.83 to 0.94 ( p = 0.006 DeLong’s test), with 82% accuracy, 78% specificity, 86% sensitivity, 79% precision, and an F 1‐score of 0.82. Conclusions: Our findings underscore the innovative application of gait features and machine learning in CSVD diagnosis. The integration of the affordable digital 6MWT gait tool with machine learning represents a promising approach for early detection and large‐scale population screening.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".