Hidden Markov model-based similarity measure (HMM-SM) for gait quality assessment of lower-limb prosthetic users using inertial sensor signals
Bibliographic record
Abstract
BACKGROUND: Gait quality indices, such as the Gillette Gait Index or Gait Profile Score (GPS), can provide clinicians with objective, straightforward measures to quantify gait pathology and monitor changes over time. However, these methods often require motion capture or stationary gait analysis systems, limiting their accessibility. Inertial sensors offer a portable, cost-effective alternative for gait analysis. This study aimed to evaluate a novel hidden Markov model-based similarity measure (HMM-SM) for assessing gait quality directly from gyroscope and accelerometer data captured by inertial sensors. METHODS: Walking trials were conducted with 26 lower-limb prosthetic users and 30 able-bodied individuals, using inertial sensors placed at various lower body locations. We computed the HMM-SM score along with other established inertial sensor-based methods, including the Movement Deviation Profile, Dynamic Time Warping, IMU-based Gait Normalcy Index, and Multifeature Gait Score. Spearman correlations with the GPS, a validated measure of gait quality, were assessed, as well as correlations among the inertial sensor methods. Welch's t-tests were used to evaluate the ability to distinguish between prosthetic subgroups. RESULTS: The HMM-SM and other inertial sensor-based methods demonstrated moderate-to-strong correlations with the GPS (0.49 <|r|< 0.77 for significant correlations). Comparisons between different measures highlighted key similarities and differences, both in correlations and in their ability to differentiate between subgroups. Overall, the pelvis and lower leg sensors achieved significant correlations and outperformed the upper leg sensors, which did not achieve significant correlations with the GPS for any of the signal-based measures. CONCLUSION: Results suggest inertial sensors located at the pelvis and lower leg provide valid markers for monitoring overall gait quality, offering the potential to develop nonobtrusive, wearable systems to facilitate long-term monitoring. Such systems could enhance rehabilitation by enabling continuous gait assessment that can be easily integrated in clinical and everyday settings.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".