A Novel Approach for Improving Gait Speed Estimation Using a Single Inertial Measurement Unit Embedded in a Smartphone: Validity and Reliability Study
Bibliographic record
Abstract
Background: Gait speed is a valuable biomarker for mobility and overall health assessment. Existing methods to measure gait speed require expensive equipment or personnel assistance, limiting their use in unsupervised, daily-life conditions. The availability of smartphones equipped with a single inertial measurement unit (IMU) presents a viable and convenient method for measuring gait speed outside of laboratory and clinical settings. Previous works have used the inverted pendulum model to estimate gait speed using a non-smartphone-based IMU attached to the trunk. However, it is unclear whether and how this approach can estimate gait speed using the IMU embedded in a smartphone while being carried in a pants pocket during walking, especially under various walking conditions. Objective: This study aimed to validate and test the reliability of a smartphone IMU-based gait speed measurement placed in the user's front pants pocket in both healthy young and older adults while walking quietly (ie, normal walking) and walking while conducting a cognitive task (ie, dual-task walking). Methods: A custom-developed smartphone application (app) was used to record gait data from 12 young adults and 12 older adults during normal and dual-task walking. The validity and reliability of gait speed and step length estimations from the smartphone were compared with the gold standard GAITRite mat. A coefficient-based adjustment based upon a coefficient relative to the original estimation of step length was applied to improve the accuracy of gait speed estimation. The magnitude of error (ie, bias and limits of agreement) between the gait data from the smartphone and the GAITRite mat was calculated for each stride. The Passing-Bablok orthogonal regression model was used to provide agreement (ie, slopes and intercepts) between the smartphone and the GAITRite mat. Results: The gait speed measured by the smartphone was valid when compared to the GAITRite mat. The original limits of agreement were 0.50 m/s (an ideal value of 0 m/s), and the orthogonal regression analysis indicated a slope of 1.68 (an ideal value of 1) and an intercept of -0.70 (an ideal value of 0). After adjustment, the accuracy of the smartphone-derived gait speed estimation improved, with limits of agreement reduced to 0.34 m/s. The adjusted slope improved to 1.00, with an intercept of 0.03. The test-retest reliability of smartphone-derived gait speed was good to excellent within supervised laboratory settings and unsupervised home conditions. The adjustment coefficients were applicable to a wide range of step lengths and gait speeds. Conclusions: The inverted pendulum approach is a valid and reliable method for estimating gait speed from a smartphone IMU placed in the pockets of younger and older adults. Adjusting step length by a coefficient derived from the original estimation of step length successfully removed bias and improved the accuracy of gait speed estimation. This novel method has potential applications in various settings and populations, though fine-tuning may be necessary for specific data sets.
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 | 0.002 | 0.008 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".