Step Detection Methods in Mobility-impairing Conditions
A systematic review evaluated step detection methods using nine algorithms across various sensor placements and clinical cohorts, including individuals with mobility impairments like Parkinson's disease and multiple sclerosis. Results indicated reliable performance in controlled lab settings, but accuracy decreased significantly in unsupervised, real-world monitoring.
- Tags
- #MSResearch
- Most relevant to
- —
- Human efficacy
- Not established from this source
- Mechanism
- Not reported
- Evidence strength
- Moderate
- Outcome
- Not reported
Why it matters
Understanding performance discrepancies between controlled and real-world settings is crucial for developing effective mobility monitoring tools for people with conditions like MS and Parkinson's.
What this does not prove
The review highlights a limited understanding of how different step detection methods perform across various scenarios, sensor placements, and patient populations.
Next milestone
No next milestone was established from the available source.
Study facts
- Study design
- Systematic review
- Participants / samples
- Not reported
- Randomised
- Not reported
- Controlled
- Not reported
- Primary endpoint met
- Not reported
- Relevant MS type
- Not reported
- Publication date
- 2026-10-16
- Evidence reviewed
- Abstract only
- Regulatory approval
- Not reported
- Research areas
- Not classified
- Biological target
- Not reported
- Pathway
- Not reported
- Population
- people with mobility-impairing conditions such as Parkinson's disease and multiple sclerosis
- Size of effect
- Not reported
- Secondary endpoints
- Not reported
- MRI endpoints
- Not reported
- Biomarkers
- Not reported
- Safety
- Not reported
Original sources
- Primary evidenceA Comparative Review and Benchmarking Evaluation of Step Detection Methods for Longitudinal Gait Assessment. ↗DOI: 10.3390/s26206582
Supporting passages (7)
study designPublication types: Journal Article; Review
subjectsHowever, an understanding of available step detection methods and their comparative performance across sensor placements, clinical populations, and real-world environments remains limited.
populationSecond, nine algorithms drawn from five of these families, all but phase portrait, are benchmarked across three large datasets encompassing healthy adults and people with mobility-impairing conditions such as Parkinson's disease and multiple sclerosis, at multiple sensor placements under both controlled laboratory and free-living conditions.
findingsAccuracy depended on sensor placement, gait pathology and recording environment: step detection proved reliable in structured laboratory settings across most sensor locations and clinical cohorts, whereas unsupervised free-living monitoring produced a substantial degradation for most algorithms.
limitationsHowever, an understanding of available step detection methods and their comparative performance across sensor placements, clinical populations, and real-world environments remains limited.
publication datePublication date: 2026-10-16
peer reviewedPublication types: Journal Article; Review
AI assessment, not yet reviewed by a person · version 1 · Community votes are separate from evidence review.