Methods · published in the open

The method, in the open.

Partners, payers, and clinicians don't adopt marketing — they adopt a method they can check. So we publish ours: every metric, every threshold, every formula, every citation, and every limitation behind the gait number. It's built on Apple's on-device mobility data and a decade of peer-reviewed gait science — and it already runs, transparently, on a person's own phone. This is a methods card, not a brochure. Read it, disagree with it, improve it.

Method v0.9 · July 2026 Runs on-device · nothing uploaded 6 validated metrics 6 peer-reviewed anchors
01 · Why we publish the method

A methods card, the way a model card is one.

A serious AI lab ships a model card — capabilities, evaluations, and limitations stated plainly — because a system you can inspect is one you can trust, build on, and regulate. A serious measurement company owes the same. The gait number is a clinical signal; if we can't show our work, no clinician should act on it and no partner should attach their hardware to it. So the method is the product's front door, not its trade secret. The engine that runs it stays ours; the method is open for anyone to audit.

For partners

A shoe, insole, or exoskeleton team plugs into a documented method, not a black box — their regulatory and clinical staff can read exactly what the number means before they commit a roadmap to it.

For payers & clinicians

Reimbursement and clinical adoption run on defensibility. Published thresholds with citations are the difference between "an app says so" and a measurement a utilization committee will stand behind.

For the record

Rigor is the moat. Anyone can draw a line on a chart; few will state the meaningful-change threshold, cite the study behind it, and name where the method breaks. That discipline is what compounds.

02 · The measurement model

What we measure — and where it comes from.

The method is sensor-agnostic by design: it consumes standard mobility metrics, whatever produced them. The reference implementation reads Apple Health — the mobility metrics an iPhone already computes on-device from its motion coprocessor, with no wearable required. The same fields can arrive from a clinical insole, a camera-pose pipeline, or a partner device.

MetricApple Health identifierUnitWhat it captures
Walking speedwalkingSpeedm/sThe primary signal — gait speed, the 6th vital sign.
Walking steadinessappleWalkingSteadiness% (OK / Low / Very Low)Apple's validated fall-risk classification from iPhone mobility data.
Step lengthwalkingStepLengthcmStride geometry; shortens early in decline.
Walking asymmetrywalkingAsymmetryPercentage%Left/right timing imbalance — a limp signature.
Double-support timewalkingDoubleSupportPercentage%Share of the gait cycle on both feet; rises with instability.
Stair speedsstairAscentSpeed / stairDescentSpeedm/sLoad-bearing challenge; sensitive to lower-limb weakness.

Walking speed is the anchor because it carries the most evidence. The rest sharpen the picture: two people can share a gait speed while one is asymmetric and spending more of each stride double-supported — the earlier warning.

03 · The reference bands cited

The thresholds, and the papers under them.

Bands are not chosen for looks. Each cut point traces to the gait-speed literature — the same numbers used in geriatric assessment and physical therapy.

< 0.60 m/s
High-risk range. Associated with dependency in activities of daily living, higher hospitalization and mortality risk, and household-limited ambulation. Studenski 2011; Fritz & Lusardi 2009.
0.60 – 1.00 m/s
Elevated range. Below the ~1.0 m/s prognostic hinge; a common threshold for frailty screening and further assessment. Studenski 2011; CDC STEADI.
1.00 – 1.20 m/s
Functional. At or above median survival trajectory for age; independent community ambulation typically preserved. Studenski 2011.
≥ 1.20 m/s
Community-strong. Around the speed required to safely cross a signalized street; associated with exceptional survival in older cohorts. Bohannon 1997; Studenski 2011.

Because a raw number means little without context, the method also reports a gait age — the age at which the measured speed equals the population-average comfortable speed — interpolated from Bohannon's age-and-sex reference values (1997). "Your gait moves like the average 72-year-old" lands where "1.02 m/s" does not.

04 · Decline detection

The trend math, written out.

A single reading is noise. The signal is the trajectory — and a change only matters if it clears the threshold research says is meaningful. Here is the entire computation, no hand-waving.

// 1 · Aggregate to one value per day (median rejects single-walk outliers) daily[d] = median( all walkingSpeed samples on day d ) // 2 · The gait number = robust recent central estimate gaitNumber = mean( daily over the trailing 14 days ) // 3 · The trend = ordinary least-squares slope over the window slope = OLS( daily vs. day-index, window = 90 days ) // m/s per day projected90 = slope × 90 // change across the window // 4 · Flag against Perera (2006) meaningful-change thresholds flag = "Slipping" if projected90 ≤ -0.10 // substantial meaningful decline "Watch" if projected90 ≤ -0.05 // small meaningful decline "Steady" otherwise // 5 · Apple Walking Steadiness overrides the trend, regardless of slope if appleWalkingSteadiness == "Low" or "Very Low": escalate flag to at least "Watch" / "Slipping"
Why median, then mean

Day-level median discards a single sprint-for-the-bus or a phone-in-a-bag artifact; the 14-day mean across those clean daily values is a stable "where you are now." Robust first, smooth second.

Why 0.05 and 0.10 m/s

These aren't round numbers — they are the small and substantial meaningful-change values established by Perera et al. (2006), the thresholds physical therapy uses to decide a change is real, not measurement drift.

05 · The evidence base

Every threshold traces to a paper.

The anchors below are load-bearing — each one is why a specific number in this method is what it is.

Studenski S, et al. Gait speed and survival in older adults. JAMA. 2011;305(1):50–58.

Pooled analysis of 9 cohorts, 34,485 older adults: gait speed predicted survival as strongly as age and sex, with each 0.1 m/s increment tracking consistently better survival. Sets the survival bands and the ~1.0 m/s hinge.

Perera S, et al. Meaningful change and responsiveness in common physical performance measures in older adults. J Am Geriatr Soc. 2006;54(5):743–749.

Established the small (~0.05 m/s) and substantial (~0.10 m/s) meaningful-change values for gait speed. Sets the Watch / Slipping decline flags.

Fritz S, Lusardi M. White paper: "Walking speed: the sixth vital sign." J Geriatr Phys Ther. 2009;32(2):2–5.

The clinical case for treating gait speed as a routine vital sign, with interpretive ranges for function and risk. Frames the whole method — and the brand.

Bohannon RW. Comfortable and maximum walking speed of adults aged 20–79 years: reference values and determinants. Age Ageing. 1997;26(1):15–19.

Age- and sex-stratified normative comfortable gait speeds. Powers the gait-age interpolation and the community-strong band.

CDC STEADI (Stopping Elderly Accidents, Deaths & Injuries). Centers for Disease Control and Prevention.

The national screen–assess–intervene framework for fall risk, with gait and mobility as core components. Anchors the screening posture and the elevated-range cut.

Apple Inc. Measuring Walking Quality Through iPhone Mobility Metrics. Apple, 2021 · Apple Heart and Movement Study (Brigham and Women's Hospital).

The published methodology and validation basis for iPhone mobility metrics and Walking Steadiness. Grounds the input data and the steadiness override.

06 · Validation & limitations

What it is — and, honestly, what it is not.

The most important part of a methods card is the part that admits where the method stops. Stated plainly, because a partner's regulatory team will find these anyway — better they find them here.

What the method is

  • A transparent, reproducible measurement of gait speed and its trend, expressed against cited reference bands.
  • Decision support: a signal to inform a conversation, a screening, or a clinician's next step.
  • Built on mobility metrics with a published validation basis (Apple's iPhone methodology) and thresholds from peer-reviewed geriatrics.
  • Sensor-agnostic: the same math applies to any conformant input, so it can be validated once and reused across devices.

What the method is not

  • Not a diagnosis. It does not identify a disease, and a "Steady" result is not medical clearance.
  • Not, as software alone, an FDA-cleared device. The measurement layer is wellness / decision-support; any device or falls-prevention claim runs a separate regulatory pathway (see the clinical-channel spec).
  • Not a fall predictor for any individual. It reports population-referenced risk, not a personal guarantee; falls are multi-factorial.
  • Not lab-grade. Consumer sensing is less precise than an instrumented gait lab; the method is tuned for trend, where consumer data is strongest.
Concurrent validity

The input metrics carry Apple's own validation for iPhone-derived gait parameters. The method's own thresholds are drawn directly from the cited literature rather than fit to a private dataset — so its behavior is auditable from public sources.

Prospective validation — the open work

The claim still to be earned is that a detected decline predicts a future fall in a monitored population. That is a prospective outcome study — named here as the honest next step, not asserted as done. The measurement layer generates that evidence as a by-product of use.

07 · Reproducibility

You don't have to take our word for it.

The method runs where you can watch it: entirely in your own browser, on your own phone's exported health data. Nothing is uploaded — the computation happens on-device and the result never leaves it. Point your own Apple Health export at it and check the number against the formula above.

Same method, any sensor

The identical thresholds and slope logic apply whether the input is Apple Health, a phone-camera pose pipeline, a 3-point AirPods + iPhone + Watch capture, or a partner insole. That invariance is precisely what makes this a method and not a product feature — validate it once, reuse it everywhere.

Versioned & dated

This is Method v0.9 (July 2026). Threshold or formula changes are versioned so any result can be traced to the exact method that produced it — the audit trail a payer or regulator expects.

Run the method on your own data →
08 · For device & shoe partners

Bring your hardware to a documented method.

Your sensor makes the signal. The method makes it mean something.

A better shoe, a smart insole, an exoskeleton, a balance sensor — each produces a raw stream that, on its own, doesn't bill, doesn't screen, and doesn't carry a defensible clinical claim. Feed it into this method and it becomes a gait number, a cited risk band, a decline flag, and a monitorable trend — with the science already published for your regulatory and clinical teams to read before they sign anything.

Your deviceraw gait signal
The MotionSole methodthis page
Number + risk band + trenddefensible output
Screening & RPM/RTMclinical + reimbursed

You keep your brand and your hardware. We supply the measurement layer, the published method, and the clinical rail — the half most hardware teams choose not to build. If you build things that measure how people move, the method is open for you to check today, and the conversation is open too.

Start a partner conversation → Read the platform spec
About this method. This page documents a measurement method for informational and decision-support purposes. It is not medical advice, not a diagnosis, and not a substitute for professional clinical evaluation. The MotionSole measurement software, as software alone, is not an FDA-cleared medical device; any diagnostic, fall-prevention, or device claim is subject to separate regulatory clearance. Reference ranges, thresholds, and effect sizes are drawn from the cited peer-reviewed literature and public frameworks as understood at drafting and are illustrative of the method's design — they must be independently verified against current sources before clinical or regulatory reliance. Apple, Apple Health, and Walking Steadiness are trademarks of Apple Inc.; MotionSole is not affiliated with, endorsed by, or sponsored by Apple Inc., and references to Apple metrics describe interoperability only. CPT/RPM/RTM references reflect general public information and change over time. MotionSole is a measurement, intelligence, and commercialization layer and does not itself diagnose, treat, or prevent disease.