Mitigation of Major Hip Injury Due to Fall With a Smart Belt: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Mitigation of Major Hip Injury Due to Fall With a Smart Belt (NCT05245097), a non-randomized na study. The primary outcome is Major Hip Injuries Due to Serious Hip-impacting Fall.

2. Clinical Question

3. Trial Design

This was a multi-center, comparative study described in the registry as non-significant risk and adaptive, with retrospective controls. Its allocation is listed as non-randomized, its masking as none, and its model as parallel. The registry record does not explain any adaptive features or report a detailed protocol for them. The study status is completed, and enrollment is recorded as 471.

The intervention group received the Tango Belt. The study description required participants to demonstrate at least 64% adherence during a 14-day run-in to fully enroll. After meeting that threshold, participants were to wear the device continuously for at least 6 months, except during bathing, charging, or as deemed appropriate by clinical staff. The arm description also says the belt could be removed upon request. These details describe the intended use, not the adherence actually achieved by participants; actual adherence results are not reported in the registry record.

The control group was based on retrospective review of a clinical site's electronic medical record. The brief summary says the primary and secondary endpoints were collected from the electronic medical record every 3 months and at the end of the study run time. The primary analysis population is described as intervention participants meeting the adherence threshold and propensity-matched historical controls. Because assignment was not randomized and the controls were historical, the groups may differ in ways that affect comparisons. The matching variables and the extent to which matching balanced the groups are not reported in the registry record.

The study began on 2022-03-29, reached primary completion on 2023-11-03, and is listed as completed. The sponsor is ActiveProtective Technologies, Inc. The registry record does not report a detailed statistical analysis plan, sample-size justification, or interim-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.

Before assignment: Intervention subjects initially enrolled (207) attempted a 14-day run-in period during which adherence to use of the study device was measured. 73 subjects who do not meet the run-in period requirement (64% adherence to wear) were withdrawn from the study resulting in 134 fully enrolled intervention group subjects.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The analysis population consists of all intervention population subjects who demonstrated at least 64% adherence to use of device during run-in period and the propensity matched historical controls.

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.

6. Primary Endpoint

The registry lists the primary outcome as Major Hip Injuries Due to Serious Hip-impacting Fall, measured over 6 months.

The primary endpoint is the percentage of participants with major hip injuries due to serious hip-impacting falls over 6 months. It is expressed as a participant-level percentage, rather than as a count of all falls or all injuries. As described, the endpoint focuses on major hip injury associated with a serious fall that impacts the hip.

This type of endpoint is used to summarize how often a clinically important event occurred in each comparison group over a defined follow-up period. A percentage can be easier to interpret as a proportion of participants experiencing an event than a raw event count, particularly when groups differ in size. It does not, by itself, describe the number of repeated events per participant, the timing of events, or how risk may vary during follow-up.

The registry record identifies a 95% confidence interval as the dispersion measure for the primary endpoint, but the endpoint percentages and their confidence intervals are not reported in the registry record. Therefore, neither the observed event proportions nor the precision of their estimates can be described. The endpoint population is defined as intervention participants who demonstrated at least 64% device adherence in the run-in period and propensity-matched historical controls. That definition is important when interpreting the endpoint: it does not describe all people screened, nor does it establish that the comparison groups were exchangeable as they might be under random assignment.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What a participant percentage represents. The primary endpoint is a percentage of participants with an event. In general, this summarizes the proportion of a defined group experiencing at least one qualifying event within the stated period. A participant-level percentage is different from a total-event rate: a participant with repeated events may still count once in a measure of whether participants experienced an event. The registry record does not provide an event-count definition beyond the primary endpoint description, so details such as handling of repeated falls are not reported in the registry record.

What a confidence interval conveys. The registry record names a 95% confidence interval as the measure of dispersion for the primary endpoint. In general, a confidence interval communicates uncertainty around an estimate under the assumptions of the analysis. A narrow interval indicates greater precision than a wide interval, while an interval that spans a range of plausible values may leave substantial uncertainty about the underlying quantity. The confidence interval itself is not reported in the registry record, and no numerical precision assessment can be made.

Why the design affects comparison. In general, random allocation helps balance both measured and unmeasured characteristics between groups on average. This study is listed as non-randomized, and the comparator is historical, so such balance cannot be assumed. The primary population description mentions propensity-matched historical controls. Propensity methods generally seek to align groups using observed characteristics, but they do not automatically address unmeasured differences. The matching variables, matching algorithm, balance assessment, and handling of unmatched records are not reported in the registry record. It is therefore not possible to evaluate the success of the matching from the registry description.

How adherence affects the target population. The study required participants to meet a minimum adherence of 64% within 14 days to fully enroll. The primary endpoint description includes intervention participants who met that threshold and propensity-matched controls. In general, selecting participants based on early adherence can make the analyzed group differ from all people who were offered or started an intervention. The estimate would apply to the defined analysis population, not automatically to every person at risk of falls. The number of participants who passed the run-in and the adherence distribution are not reported in the registry record.

Planning calculations are not trial results. The registry description of sample-size assumptions specifies an illustrative calculation based on the observed effect, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. It says the effect to detect is a stated fraction of the observed effect; for time-to-event illustrations, the total number of events is used, while other illustrations use participants per arm. These are planning conventions, not observed results or evidence that the study had a particular probability of detecting an effect. The resulting planning values and the fraction-specific estimates are not reported in the registry record. The record does not report the trial's own sample-size justification, so the illustration cannot be treated as the study's original design basis.

Why over-dispersion can matter in general. For count outcomes, a simple statistical model may assume that variability is constrained by the mean. When observed variability exceeds that assumption, over-dispersion can make standard errors too small and confidence intervals too narrow if it is not addressed. Methods that allow extra variability may better reflect uncertainty. This is a general consideration for count data, not a claim about the trial's analysis: the primary endpoint is described as a participant percentage, and the registry record does not report an over-dispersion assessment or an analysis model for the other outcomes.

What is not documented. The registry record does not report the model used for the primary comparison, covariates included in any adjusted analysis, the confidence-interval calculation, missing-data methods, or a multiplicity strategy. The design listing of a parallel model does not supply these analysis details. Without them, a reader cannot verify the analysis assumptions or determine how estimates would respond to adjustment, incomplete follow-up, or multiple testing. The available record therefore supports a description of the endpoint and design, but not a reconstruction of the inferential analysis.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Intervention Group", "Control Group")
n      <- c(134, 264)
events <- c(1, 32)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Intervention Group  134  1  0.7  0.0  4.1  0.1  4.1  0.2  4.1
ARM  Control Group  264  32  12.1  8.4  16.7  8.7  16.6  8.7  16.6

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists 12 outcome measures and 5 analyses. It does not report whether the primary endpoint was designated as the sole confirmatory test, whether secondary outcomes were tested inferentially, or whether any adjustment was made for multiple outcomes or analyses. In general, examining multiple outcomes or conducting multiple analyses can increase the chance of finding an apparently notable result by chance. Whether and how this issue applies depends on the analysis plan, which is not reported in the registry record.

The record does not describe missing-data rates for the primary endpoint or other outcomes, nor does it specify how missing records, incomplete follow-up, or unavailable electronic medical record information were handled. In general, missingness can affect an estimate if participants with unavailable outcomes differ systematically from those with observed outcomes. No missing-data assumptions or sensitivity analyses are reported in the registry record, so the potential influence of missing information cannot be assessed.

The primary population is described as intervention participants meeting the 64% adherence threshold and propensity-matched historical controls. Although the description uses “ITT population,” the specified eligibility conditions make it important to distinguish this analysis population from every participant screened or initially assigned. The registry record does not report the numbers at each analysis stage, the count excluded for failing the adherence threshold, or the exact matched sample size. It also does not describe whether all outcomes used the same analysis population.

The statistical analysis plan, interim-analysis procedures, and sample-size justification are not reported in the registry record. These gaps prevent assessment of prespecification, outcome selection, and the handling of analyses conducted during the study.

12. 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: fall with fracture (21.6%), other (11.1%), infection (1.9%), dislocation (0.4%).

The registry record gives serious-event and other-event counts for two groups, along with deaths. For the Safety Population, it reports 33 affected among 207 at risk for serious events and 67 affected among 207 at risk for other events; 6 deaths are listed. For the Control Group, it reports 66 affected among 264 at risk for serious events and 152 affected among 264 at risk for other events; 7 deaths are listed. These are the registry's reported counts, not a causal comparison.

The record does not define the relationship between the named Safety Population and the intervention group in the same terms as the primary endpoint population. It also does not state whether the event counts represent participants, event episodes, or a particular observation window. The categories should therefore be read as the registry presents them rather than interpreted as rates over a uniform exposure period.

The listed serious-event terms include Fall with Fracture at 21.6%, Other at 11.1%, Infection at 1.9%, and Dislocation at 0.4%. The denominator for these percentages is not reported in the registry record. The deaths are listed without a stated cause or attribution, so the counts alone do not establish whether deaths were related to the device, the study, or other circumstances. Serious-event summaries are distinct from the primary endpoint and cannot replace its missing outcome estimate.

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

The registry record establishes that a completed, non-randomized study evaluated the Tango Belt against retrospective controls for a defined primary endpoint: the percentage of participants with major hip injuries due to serious hip-impacting falls over 6 months. It also describes an adherence threshold, the historical-control approach, safety counts, and the planned use of a 95% confidence interval for the primary endpoint.

It does not report the primary endpoint results. There is no reported percentage for either group, no comparative estimate, no confidence interval, and no p-value. Accordingly, the record does not show the observed size or direction of any difference and cannot establish how precisely that comparison was estimated. No conclusion about the intervention's effectiveness can be drawn from the endpoint information recorded.

The non-randomized design and retrospective controls also constrain what a comparison could mean. Propensity matching is mentioned, but the matching variables and evidence of balance are not reported. In general, matching on observed characteristics cannot rule out differences in unmeasured factors. Thus, even a reported association would need to be distinguished from a causal effect unless the analysis and assumptions supported that interpretation.

The safety counts describe events in the listed groups, but the record does not state event attribution, the denominator for the listed serious-event term percentages, or enough detail to interpret the counts as comparable exposure-adjusted rates. Death counts are not accompanied by causes. Those summaries do not resolve the missing primary outcome data.

In short, the registry record documents the trial's question and broad design, but not the primary results needed to judge the observed comparison. It also leaves key analytic details unreported, including missing-data methods and multiplicity handling. The absence of these details is uncertainty about what can be concluded from the registry record, not evidence that an effect was absent or present.

14. Why This Trial Matters Statistically

This study raises several important statistical issues in a setting where the primary outcome is a participant-level event percentage and the control information is retrospective. The distinction between a randomized and non-randomized comparison is central: without random allocation, differences between groups may reflect factors other than the intervention. Propensity matching is a useful design or analysis tool for measured characteristics, but its adequacy depends on which variables were available and how well the groups aligned. Those details are not reported in the registry record.

The adherence threshold also matters for defining the population to which results would apply. Participants had to demonstrate at least 64% adherence during run-in to fully enroll, and the primary population description includes intervention participants who met that threshold. That makes it important to report how many participants entered the study, met the threshold, and contributed outcome information. Those flow details are not reported in the registry record.

Statistical precision is essential for interpreting an event percentage, but the primary estimate and its 95% confidence interval are not reported. A study completion status and enrollment figure cannot show whether the primary comparison was precise or uncertain. Registry outcome reporting is therefore necessary for readers to assess the estimate rather than infer results from the study's purpose or design.

Finally, the record lists multiple outcomes and analyses without documenting multiplicity or missing-data methods. Such details help readers judge whether results were prespecified and how robust they may be to incomplete records or repeated testing. This trial is statistically instructive because its record clearly identifies the comparison structure while leaving important outcome and analysis information unreported.

15. 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.

The most important trial-specific limitation for interpreting the registry record is that the primary outcome results are not reported. Although the endpoint is defined and a 95% confidence interval is specified as the dispersion measure, no group percentages, contrast, interval, or p-value are included. The comparative result and its precision therefore cannot be assessed.

The comparison is non-randomized and uses retrospective controls from an electronic medical record. The record mentions propensity matching but does not report the variables used, the matching procedure, balance after matching, or the number of controls retained. Differences between historical and intervention groups may remain, and the record does not provide the information needed to evaluate this risk.

The intervention analysis population is conditioned on achieving at least 64% adherence during a 14-day run-in. The record does not report how many participants met this criterion, how adherence was measured, or how adherence developed during the 6-month intended use period. This limits understanding of the analyzed population and of how representative it may be of people who initially begin the intervention.

Other limitations of the available record include the absence of reported missing-data methods, outcome-specific analysis populations, a multiplicity strategy, and detailed statistical models. It also does not provide a sample-size justification for the trial or explain the listed adaptive features. The safety summaries lack event attribution and do not specify the denominator for the serious-event term percentages. These reporting gaps do not establish that the study was improperly conducted; they limit what can be evaluated from the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Mitigation of Major Hip Injury Due to Fall With a Smart Belt — NCT05245097.
• Registry record last updated 2025-06-13; status last verified 2025-05.
• Results first posted 2025-06-13.
• 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.

19. Record Summary

The registry record describes a completed, multi-center, non-randomized parallel study of the Tango Belt with retrospective standard-of-care controls. Enrollment is recorded as 471. The study began on 2022-03-29, with primary completion on 2023-11-03. The intervention involved a device-use adherence threshold of at least 64% during a 14-day run-in, followed by intended use over 6 months.

The primary endpoint was the percentage of participants with major hip injuries due to serious hip-impacting falls during 6 months. The primary analysis population is described as intervention participants meeting the adherence threshold and propensity-matched historical controls. The registry record does not report the primary endpoint estimates or confidence interval, nor does it report key details of matching, missing-data handling, or multiplicity procedures. Safety counts and selected serious-event terms are listed, but attribution and some denominators are not specified.