A Prospective Multicenter Longitudinal Cohort Study of the Mymobility Platform: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Prospective Multicenter Longitudinal Cohort Study of the Mymobility Platform (NCT03737149), a randomized na study. The primary outcome is Phase II (RCT): Readmissions.

2. Clinical Question

3. Trial Design

The registry record describes a prospective, multicenter longitudinal study of the mymobility platform. Its overall enrollment is 6559, and its status is completed. The recorded study start is 2018-10-22, and primary completion is recorded as 2025-04-15. The study is categorized as randomized, with no masking and a parallel model. The phase field is listed as NA, while the outcomes and arms distinguish a Phase I pilot, Phase II randomized trial, and Phase 3 correlative phase.

The intervention of interest pairs mobile application-guided education and exercise with activity monitoring from an Apple Watch. The standard-care arm receives patient education and postoperative physical therapy according to local site guidelines and care pathways. This means the comparator reflects site-level usual care rather than a single detailed regimen described in the registry record.

The primary outcome is readmission within 30 days after knee or hip replacement surgery among Phase II participants. Secondary outcomes include joint-replacement-specific knee and hip scores, EQ-5D-5L, manipulation under anesthesia, timed up and go, single-leg stance, subject satisfaction, and urgent care or emergency room visits. The posted secondary results include selected 90-day outcomes. Although the registry record lists 13 outcome measures, it lists no reported analyses.

The record also contains participants from pilot and correlative phases, in addition to the randomized phase. Those phase groups should not be treated as interchangeable randomized comparisons. The registry record does not report the original sample-size justification, the randomization procedure, site-level allocation details, or a full statistical analysis plan.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Only the first 6 of 8 groups are shown.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Subjects enrolled in Phase II (RCT) of the study and had knee or hip replacement surgery.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

Only the first 6 of 9 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Phase II (RCT): Readmissions, measured over 30 Days.

The primary endpoint is the number of participants with a readmission within 30 days after knee or hip replacement surgery. Its stated population is Phase II participants who underwent one of these procedures. The endpoint is therefore a binary participant-level outcome: a participant either had a readmission during the specified period or did not. The posted arm values are counts of participants with readmission, alongside the corresponding group sizes.

Readmission is used as a measure of postoperative healthcare use during a defined follow-up period. It captures an event that can be counted rather than a change in a continuous score, but a count alone does not describe the reason for readmission, its severity, or whether it was related to the rehabilitation approach. The registry record does not report those details for the primary outcome.

The results separate knee and hip groups and distinguish the mobile application-plus-watch intervention from standard physical therapy. The reported risk differences express differences in the estimated proportions with an event, while their confidence intervals describe uncertainty around those estimates. A confidence interval that includes zero is compatible with a range of risk differences in either direction; an interval that excludes zero indicates that zero is outside that particular interval, but does not by itself establish clinical importance or resolve concerns about analysis choices.

The primary result should be interpreted as a comparison of recorded 30-day readmissions in the stated Phase II groups. It does not characterize longer-term recovery, other complications, or the overall experience of rehabilitation.

7. Results Posted in the Registry

• Phase II (RCT): Mymobility With Apple Watch-Knee: 1.9% (4/210) versus 2.9% (7/245) on control; risk difference -1.0 percentage points (95% CI -3.7 to 1.8), risk ratio 0.67 (0.20–2.25); unadjusted two-proportion z-test p = 0.510.
• Phase II (RCT): Mymobility With Apple Watch-Hip: 2.3% (4/174) versus 2.9% (7/245) on control; risk difference -0.6 percentage points (95% CI -3.6 to 2.5), risk ratio 0.80 (0.24–2.71); unadjusted two-proportion z-test p = 0.725.
• Phase 2 (RCT): Standard of Care Physical Therapy-Hip: 0.5% (1/204) versus 2.9% (7/245) on control; risk difference -2.4 percentage points (95% CI -4.7 to -0.1), risk ratio 0.17 (0.02–1.38); unadjusted two-proportion z-test p = 0.059.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Phase II (RCT): Knee Injury and Osteoarthritis Outcome Score - Joint Replacement (KOOS, JR)

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Phase II (RCT): Mymobility With Apple Watch-Knee: mean 70.00 versus 73.70 on control; difference -3.70 (95% CI -6.55 to -0.85), standardized effect d = -0.28; z-test p = 0.011.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Phase II (RCT): Mymobility With Apple Watch-Knee than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Phase II (RCT): Hip Disability and Osteoarthritis Outcome Score - Joint Replacement (HOOS, JR)

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Phase 2 (RCT): Mymobility With Apple Watch-Hip: mean 81.80 versus 83.50 on control; difference -1.70 (95% CI -4.86 to 1.46), standardized effect d = -0.12; z-test p = 0.292.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Phase 2 (RCT): Mymobility With Apple Watch-Hip and the control. The interval gives the range of effects that remain compatible with the data.

Phase II RCT: EQ-5D-5L

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Phase 2 (RCT): Mymobility With Apple Watch-Knee: mean 0.80 versus 0.90 on control; difference -0.10 (95% CI -0.14 to -0.06), standardized effect d = -0.65; z-test p = <0.001.
  • Phase 2 (RCT): Mymobility With Apple Watch-Hip: mean 0.90 versus 0.90 on control; difference 0.00 (95% CI -0.02 to 0.02), standardized effect d = 0.00; z-test p = 1.000.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Phase 2 (RCT): Mymobility With Apple Watch-Knee than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Phase 2 (RCT): Mymobility With Apple Watch-Hip and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes add different kinds of information to the 30-day readmission endpoint. They include joint-specific measures of function or symptoms, a quality-of-life measure, and other postoperative outcomes listed in the registry record. The posted numerical secondary results focus on 90-day KOOS, JR, HOOS, JR, and EQ-5D-5L. The registry record lists additional outcomes but does not report analyses for them.

Across the posted continuous outcomes, estimates do not all point in the same direction or have the same degree of precision. Some unadjusted intervals exclude zero, while others include it. This mixed pattern does not contradict the primary endpoint: the secondary measures capture different constructs, are assessed at a different time, and are not readmission counts. They should be understood as complementary outcomes rather than interchangeable confirmations of the primary result.

The secondary results carry less weight for an overall conclusion because they are secondary and the registry record does not report multiplicity control. When many outcomes or comparisons are examined, the chance of at least one apparently notable result can increase. A small unadjusted p-value may therefore be less persuasive than a result specified in advance and evaluated under a stated multiplicity plan. The record also lists no reported analyses, leaving the prespecification and analysis choices unclear.

Interpretation is further limited by the absence of reported thresholds for meaningful score changes, missing-data methods, and adjusted analyses. The results describe group averages and estimated contrasts, but do not establish how many individuals experienced meaningful improvement or decline. Nor do they explain whether the observed patterns reflect the rehabilitation approach, baseline differences, variation in local care, or other factors.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Phase II (RCT): Knee Injury and Osteoarthritis Outcome Score - Joint Replacement (KOOS, JR)
• Phase II (RCT): Hip Disability and Osteoarthritis Outcome Score - Joint Replacement (HOOS, JR)
• Phase II RCT: EQ-5D-5L
• Phase II (RCT): Manipulation Under Anesthesia (MUA)
• Phase II (RCT): Timed Up and Go (TUG)
• Phase II (RCT): Single-Leg Stance (SLS) Test
• Phase II (RCT): Subject Satisfaction
• Phase II RCT: Urgent Care Center and Emergency Room Visits

9. Statistical Interpretation

10. Statistical Methods Explained

For the primary endpoint, the registry reports counts of participants with readmission and group sizes. The risk for a group is the proportion of participants in that group who experienced the event. A risk difference compares two such proportions by subtraction. A negative value means the estimated risk in the first named comparison group is lower than in the reference group; a positive value means it is higher. This is a descriptive direction of the estimate, not proof that assignment caused a difference.

The posted primary comparisons include risk differences, confidence intervals, risk ratios, odds ratios, and unadjusted p-values. The risk ratio expresses one group’s event risk relative to the other group’s risk. The odds ratio compares event odds rather than risks. These measures use different scales, so their numerical values are not directly interchangeable. For a relatively uncommon event, risk and odds can be close, but they remain distinct quantities. The registry record does not report an adjusted primary analysis.

A confidence interval gives a range of estimates compatible with the data under the assumptions of the calculation. A narrower interval indicates greater precision; a wider interval indicates more uncertainty. For a risk difference, zero represents no difference between the estimated risks. When the interval contains zero, the data are compatible with a difference in either direction at the interval’s stated confidence level. When it excludes zero, zero is outside that interval, though this alone does not establish the size or clinical relevance of an effect.

What does an unadjusted p-value say?

A p-value describes how unusual the observed data, or data more extreme, would be under a specified null hypothesis and the statistical model used. It is not the probability that the null hypothesis is true, nor is it a measure of the size or importance of a difference. The posted p-values are explicitly unadjusted. They do not account for the possibility of many outcomes or comparisons unless a stated procedure does so; no such procedure is reported in the registry record.

The reported primary p-values and confidence intervals should be considered together. The p-value summarizes compatibility with a null value under a particular test, while the interval conveys a range of plausible effect estimates. A result close to a conventional threshold should not be treated as categorically different from one just on the other side of it. The primary analyses have few readmission events, so the precision of the estimates is limited.

How should the continuous outcomes be read?

The posted 90-day KOOS, JR and HOOS, JR results report group means and standard deviations. A mean is the average score in the group; the standard deviation describes variation among participants. Their comparisons are expressed as mean differences, with confidence intervals and unadjusted p-values. The sign of a mean difference depends on the comparison order used in the registry analysis. The record describes these as scores on a scale but does not provide a threshold for interpreting the importance of a difference.

The EQ-5D-5L results are also reported as means and standard deviations at 90 days. As with the joint-specific scores, the difference in means summarizes the contrast in group averages, not the distribution of every participant’s score. Standard deviations describe dispersion within groups and should not be confused with standard errors or confidence intervals. The registry record does not report adjusted analyses for these outcomes.

Standard errors quantify the sampling uncertainty of estimated means; they are not measures of participant-to-participant variability. The posted values include standard errors for the continuous outcomes. An estimated mean difference is informed by uncertainty in both group means. Statistical precision also depends on group size and within-group variability, so a point estimate should not be interpreted without its interval.

Why does the study structure matter?

The registry record includes a randomized Phase II component but also pilot and correlative phases. Randomized comparisons are interpreted differently from descriptive observations in nonrandomized groups. Counts from the pilot and correlative phases should not be combined with the randomized results as if they arose from the same allocation process. The record does not report enough detail to assess the allocation process, the analysis population, or whether all randomized participants were included in each outcome analysis.

For the primary comparisons, the displayed reference values correspond to the standard-care knee group. In particular, the posted estimates for hip groups also use that reference in the comparison data. That structure matters: an estimate against standard-care knee is not the same contrast as mymobility versus standard care within the hip population. The registry record does not explain the rationale for this reference structure, so readers should preserve the specific comparison represented by each estimate rather than infer a different one.

The registry record lists no reported analyses, and it does not describe a formal statistical analysis plan, missing-data methods, or multiplicity control. Therefore, the posted summary statistics can be described and interpreted on their stated terms, but the full modeling and decision process cannot be reconstructed from the record.

11. Confidence Intervals and Precision

Precision is best judged from the confidence intervals, not from the point estimates alone. For the knee readmission comparison, the estimated risk difference is -0.009 and the 95% confidence interval ranges from -0.037 to 0.018. The interval includes zero and spans negative and positive values, so the estimate does not precisely determine the direction of the risk difference.

The hip intervention comparison has an estimated risk difference of -0.006, with a 95% confidence interval from -0.036 to 0.025. This interval also includes zero and allows for differences in either direction. The hip standard-care comparison has an estimated risk difference of -0.024 and a 95% confidence interval from -0.047 to -0.001. Its interval excludes zero, but its upper end is close to zero. The corresponding unadjusted p-value is 0.059, and no multiplicity adjustment is reported.

Readmission events were uncommon in the posted groups, with counts ranging from 1 to 7. With few events, estimates of event risks and their differences can be sensitive to small changes in the observed counts. The intervals are therefore more informative than a simple comparison of the point estimates. They show that the primary data do not tightly pin down the magnitude of most contrasts.

Confidence intervals do not include every source of uncertainty. They reflect uncertainty under the calculation’s assumptions, not uncertainty from unreported analysis choices, missing data, differences among sites, or potential limitations in outcome ascertainment. The registry record does not report enough detail to assess those sources. The intervals should consequently be read as precision summaries for the posted comparisons, not as a complete account of uncertainty about the study’s conclusions.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning estimates are illustrations based on the observed effect, not the trial’s original design calculation. For these outcomes, the figures are participants per arm, not a total across arms or a total number of events. The registry record does not report the original sample-size assumptions or justification.

The planning illustration assumes a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It considers effects equal to the observed effect and fractions of that observed effect. Each power column describes the approximate number of participants per arm that would be needed to have the stated chance of detecting the selected effect under those assumptions, if that effect were the true one and the model assumptions held. The 80% column corresponds to an 80% chance, and the 90% column to a 90% chance, of detecting the chosen effect using the stated significance level.

Rows that plan for a smaller fraction of the observed effect require more participants per arm. This is expected: a smaller difference is harder to distinguish from sampling variation, so more information is needed to detect it. The calculations are sensitive to the observed effect used as their starting point. When the observed estimate is imprecise, planning from it may produce unstable or optimistic illustrations.

These values are not observed power. They are prospective planning illustrations calculated from the posted summaries and stated assumptions, rather than a measure of what the completed study achieved. They do not establish that the study was adequately sized for its original objectives, because the original design assumptions are not reported in the registry record.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.029; treatment proportion p₁ = 0.019; average p̄ = 0.024.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.2156 = 0.4226.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.2155 = 0.1814.
4. n = (0.4226 + 0.1814)² / (-0.0095)² = 4,021.4, rounded up to 4,022 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
p0 <- 0.0285714285714286                          # control proportion
p1 <- 0.019047619047619                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(3737149)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 4,022 (80% power), 5,383 (90% power)
 75% of observed effect: n per arm = 7,499 (80% power), 10,038 (90% power)
 50% of observed effect: n per arm = 17,655 (80% power), 23,635 (90% power)
power.prop.test: 4021.4 
Simulated power at n = 4,022 per arm: 0.803 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Multiplicity, Missing Data and Analysis Populations

The registry record lists 13 outcome measures and 12 posted secondary outcomes, while it reports no analyses. It does not state whether one outcome was designated as the sole confirmatory endpoint for formal testing, how the secondary outcomes were ordered, or whether any adjustment for multiple outcomes or comparisons was planned. The posted p-values are unadjusted. Without a reported multiplicity strategy, nominal p-values should not be treated as if they account for testing across the full outcome set.

Multiplicity is a general statistical concern when several hypotheses are evaluated. Even when no real differences exist, looking across many comparisons can make some results appear unusual by chance. Adjustment procedures can control specified error rates, but their suitability depends on the analysis plan and the family of tests being considered. The registry record does not report such procedures, so no multiplicity-adjusted interpretation can be made from the posted results.

Missing-data handling is also not reported in the registry record. It does not state how participants with unavailable 30-day readmission information or 90-day scores were handled, whether missingness differed among groups, or whether any imputation or sensitivity analysis was used. The group sizes attached to individual outcomes do not, by themselves, explain why those sizes differ or whether missing observations could affect the comparisons.

The registry record does not define the analysis populations, such as whether the primary result followed an intention-to-treat approach or another population rule. It also does not report adjustment for baseline factors, site effects, or other covariates. These omissions make it difficult to assess whether estimates account for the randomized design and the multicenter setting. The results can be read as the posted group summaries and comparisons, but the full analysis decisions and their robustness cannot be evaluated from the registry record.

15. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: cardiovascular (1.9%), other general adverse event (1.7%), deep vein thrombosis (1.2%), fracture of femur (hip) (1.1%), stiffness (knee) (1.0%).

Adverse-event counts are reported for the pilot, randomized, and correlative phases, with serious events, other events, and deaths listed separately. The randomized phase includes serious adverse events in 13 participants in the mymobility knee group, 11 in the mymobility hip group, 15 in standard-care knee, and 8 in standard-care hip. Other adverse events are also listed by group, as are deaths. The record lists 1 death in the mymobility knee group and 1 in standard-care knee; the other posted group death counts are 0.

These are descriptive counts, not adjusted comparisons of risk. The groups differ in size and include distinct study phases, so counts should be read alongside the corresponding group and phase rather than pooled or compared without context. An adverse event recorded during a study does not, by itself, establish that the intervention caused it. The registry record does not report event relatedness, severity grading details, or a comparative safety analysis.

The listed serious-event terms include Cardiovascular, Other General Adverse Event, Deep Vein Thrombosis, Fracture of Femur (hip), Stiffness (knee), and Hematological, each with its posted percentage. These terms describe reported categories; they do not provide a complete account of clinical circumstances or causality.

16. What the Result Does, and Does Not, Mean

The posted results describe a randomized Phase II comparison embedded in a larger prospective study. For the primary endpoint, they report 30-day readmission counts and estimated risk differences for knee and hip groups. The estimates are accompanied by confidence intervals, which convey substantial uncertainty for the intervention comparisons. One posted hip standard-care contrast has an interval that excludes zero, but its unadjusted p-value is 0.059 and the registry record does not report multiplicity adjustment.

These statistics do not establish that one rehabilitation approach is better or worse. They summarize events and scores observed in the recorded groups under the comparisons listed. A difference in observed outcomes can reflect chance variation, the care approach, characteristics of participants, differences in site practice, or other influences. Although random allocation is recorded, details needed to assess the analysis and allocation process are not reported in the registry record.

The endpoint also has a limited scope. Readmission within 30 days does not capture every dimension of postoperative recovery, and it does not identify the reason for a readmission or whether it was related to rehabilitation. The 90-day scores provide additional outcome perspectives, but their clinical meaning cannot be determined from group averages alone, particularly without reported thresholds for meaningful change and individual-level distributions.

The registry record’s description of the intervention as a possible alternative to standard physical therapy is a study rationale, not a conclusion established by the posted statistics. The results do not show that the application and wearable can replace usual care, nor do they establish an improvement in clinical outcomes. Those interpretations would require a prespecified analysis, appropriate assessment of missingness and multiplicity, and evidence about the clinical importance of the observed differences.

The most defensible reading is therefore descriptive and bounded: the record reports the observed primary and selected secondary outcomes, with uncertainty that varies by comparison. It does not provide enough statistical detail to support a definitive causal or clinical conclusion.

17. Why This Trial Matters Statistically

This study is statistically interesting because it combines a randomized comparison with a wider post-market, multicenter longitudinal program. The record distinguishes a pilot, randomized, and correlative phase, making it important to preserve which participants and outcomes belong to each phase. Results from observational or correlative groups cannot automatically be interpreted as randomized evidence.

The primary endpoint is a relatively uncommon binary event, and the posted group counts are small. In this setting, a few events can have a visible influence on an estimated risk difference. Confidence intervals are essential for judging how much the data constrain the estimate; the event counts alone can encourage overly definite comparisons.

The intervention is also compared with standard care shaped by local site guidelines and pathways. This reflects variation in usual care rather than a single standardized comparator, which matters when interpreting effects across centers. The posted registry information does not explain how site variation was handled analytically.

Finally, the record includes multiple secondary outcomes, several types of measurement, and different follow-up periods. That breadth can be useful for describing recovery, but it raises questions about outcome prioritization, multiplicity, missing data, and analysis populations. Because those methods are not reported, the statistics support cautious reading of the posted contrasts rather than a single decisive claim.

18. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

Several limitations specific to this record constrain interpretation. The study description covers a post-market program with pilot, randomized, and correlative phases, while the primary comparison concerns Phase II. The overall enrollment therefore should not be mistaken for the size of the randomized comparison. The record does not provide a complete account of how participants entered each phase or how the outcome analysis populations were defined.

The standard-care comparator is described as care determined by local site guidelines and care pathways. Variation in those practices could affect outcomes, but the registry record does not report how site differences were measured or handled. It also does not describe the randomization procedure, allocation concealment, or whether analyses accounted for site.

The primary outcome is readmission within 30 days, a limited measure of postoperative experience. The record does not report reasons for readmission or whether events were considered related to the intervention. The posted comparisons also use the standard-care knee group as the reference for the hip-specific estimates. That structure makes it important not to interpret the hip estimates as direct within-hip intervention-versus-standard-care contrasts.

For secondary outcomes, follow-up is 90 days, and the record does not report thresholds for meaningful score differences. It also does not report missing-data methods, multiplicity control, adjusted analyses, or the original sample-size justification. The absence of these details limits assessment of robustness, precision, and the role of chance across multiple outcomes. Open-label allocation is recorded, so participants and study staff were not masked; the record does not describe whether outcome assessment was blinded.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Prospective Multicenter Longitudinal Cohort Study of the Mymobility Platform — NCT03737149.
• Registry record last updated 2026-03-23; status last verified 2026-03.
• Results first posted 2026-03-23.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

22. Record Summary

The registry record describes a completed, randomized, open-label, parallel study of mymobility with Apple Watch compared with standard-of-care physical therapy. The overall study is prospective, multicenter, and longitudinal, with a recorded enrollment of 6559 and phases that include a pilot, randomized trial, and correlative component.

The primary outcome is the count of Phase II participants readmitted within 30 days after knee or hip replacement surgery. Posted primary comparisons include risk differences, confidence intervals, and unadjusted p-values. Selected secondary results report 90-day KOOS, JR, HOOS, JR, and EQ-5D-5L scores. Adverse-event counts are posted across study phases.

The record does not report the original sample-size justification, a full statistical analysis plan, multiplicity procedures, missing-data handling, or analysis populations. The posted estimates are therefore best interpreted descriptively, with their confidence intervals and comparison definitions kept in view.