Longitudinal Outcome in a Veterans Geriatric Multifactorial Falls Assessment Clinic: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Longitudinal Outcome in a Veterans Geriatric Multifactorial Falls Assessment Clinic (NCT02356211), a non-randomized na study. The primary outcome is Number of Participants Who Experienced Falls.

2. Clinical Question

3. Trial Design

The registry describes a prospective controlled study of a Geriatric Multifactorial Falls Assessment Clinic, with outcomes compared against an Acute Geriatric Evaluation and Management inpatient discharge control group. The stated follow-up for the clinic patients was 1 year. The registry record gives the primary outcome timeframe as 12 months.

The study is marked non-randomized and unmasked. Its design classification is listed as single group, although the description and arm labels identify a clinic group and a GEM control group. These registry entries indicate that a comparison was described, but not that participants were randomly assigned. The registry explicitly cautions that the arms are not a like-for-like control comparison.

Enrollment is listed as 109. The clinic group is named Treatment, and the control group is named Control. The study status is completed. The recorded start is 2008-08, and primary completion is recorded as 2017-01. The registry lists the phase as NA.

Because allocation was not randomized and the clinic and inpatient-discharge groups differ in setting, group membership may reflect differences in participants or care pathways beyond the falls assessment. The registry record does not provide enough information to characterize or adjust for such differences. It also does not report the planned statistical analysis, sample-size justification, or interim analyses. Those omissions limit how much can be concluded about the design’s ability to support a causal comparison.

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.

Overall Study

Reasons for not completing this period:

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.

Population: Intervention: 2 withdrawals, 1 bedfast, excluded from analysis Control: 2 withdrawals, 8 high functioning, excluded from analysis

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants Who Experienced Falls, measured over 12 months.

The primary endpoint is the number of participants who experienced falls during 12 months. The registry says ascertainment was based on self-recall and telephone interview. This is a participant-level binary outcome: each participant is classified according to whether a fall was reported during the stated follow-up, and the endpoint is expressed as a count of participants with the event.

This type of outcome can summarize whether participants experienced at least one fall over a defined period. It is distinct from the total number of falls: a participant with multiple falls still contributes as a participant who experienced falls, unless a separate recurrent-event outcome is specified. The registry lists one primary outcome measure and does not list an analysis of the total number of falls.

General: binary outcomes are often summarized by event counts and the number of participants assessed. A comparison can then be expressed in terms of the difference or relative contrast between groups, with uncertainty estimates such as confidence intervals. These estimates depend on the underlying observed counts and the analysis method.

The registry record does not report the number of participants who experienced falls in either group, the group denominators for this outcome, or an estimated contrast. Therefore, the endpoint’s definition is available, but its observed result and comparative precision are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What kind of endpoint is being counted?

General: a binary endpoint records whether each participant did or did not experience the specified event during the outcome period. For this study, the event is having experienced falls during 12 months, based on self-recall and telephone interview. The listed endpoint is the number of participants with falls, not the total number of fall episodes. Those quantities answer different questions: participant counts describe how many people experienced the event, while event totals also reflect repeated events in the same person.

For a binary outcome, an analysis commonly begins with the event count and the number of participants whose outcome is known in each group. The proportion with the event can then be estimated, and a group contrast can be expressed as an absolute difference or a relative measure. These are general analytical options, not methods reported as having been used in this study. The registry record does not report the primary outcome counts, denominators, or analysis results.

What does a confidence interval communicate?

General: a confidence interval describes the uncertainty around an estimate under a specified statistical model and procedure. A narrower interval indicates greater statistical precision, while a wider interval indicates less precision. It does not correct a biased comparison, guarantee that the model is appropriate, or account automatically for unmeasured differences between groups. For a non-randomized comparison, the interval’s statistical uncertainty and the possibility of confounding are separate concerns.

No confidence interval for the primary falls outcome is reported in the registry record. Without an estimate and interval, there is no basis for describing the size or precision of a group contrast. Likewise, a p-value, if reported, would address compatibility with a statistical null model; it would not by itself establish that groups were comparable or that a contrast was caused by the clinic assessment.

Why does allocation matter?

General: random assignment can, on average, balance measured and unmeasured participant characteristics across groups. In a non-randomized study, group membership may be associated with factors that also relate to the outcome. Statistical adjustment can address measured variables when they are collected and modeled appropriately, but it cannot guarantee control of unmeasured confounding.

In this record, the clinic group is described as frail elderly Veteran outpatients referred for falls assessment, while the control group came from an inpatient geriatric evaluation and management discharge service. The registry itself warns that the arms are not a like-for-like control comparison. It does not report baseline characteristics or an adjusted analysis, so the extent of any group differences and any adjustment for them are not reported in the registry record.

What do the sample-size illustrations mean?

The registry describes planning illustrations based on an observed effect, with a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. The effect to detect is defined as a stated fraction of the observed effect. These assumptions describe planning calculations; they do not establish that the original study used those assumptions for its design. The registry record does not report the study’s own sample-size justification.

General: a planning sample size estimates how many participants might be needed to detect a specified effect under stated assumptions. It is not a measure of the probability that the completed study’s findings are true. A retrospective calculation based on an observed effect is also not “observed power”; it is better understood as a planning illustration under the chosen assumptions. The event type matters for the calculation. For a binary endpoint, required participants are expressed per arm under the stated illustration, whereas time-to-event planning may use a total event count. No specific calculated planning values or observed primary effect are reported in the registry record.

What can be inferred from the analysis record?

The registry lists one outcome measure and zero analyses. It does not identify a statistical model, adjustment set, confidence-interval method, missing-outcome strategy, or analysis population. These details should not be inferred from the endpoint definition alone. General statistical explanations describe possible ways to analyze a binary outcome; they do not show which method was used in this study.

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("Treatment", "Control")
n      <- c(55, 51)
events <- c(22, 35)
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  Treatment  55  22  40.0  27.0  54.1  28.1  53.2  28.1  53.2
ARM  Control  51  35  68.6  54.1  80.9  55.0  79.7  54.9  79.7

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure: the number of participants who experienced falls during 12 months. It lists zero analyses. No additional outcome-testing plan, statistical hierarchy, or adjustment for multiple comparisons is reported in the registry record. With no reported inferential analyses, there are no reported primary-outcome p-values or confidence intervals to assess for multiplicity.

General: multiplicity arises when several hypotheses or outcomes are tested and the chance of at least one false-positive finding can increase if the analyses are treated independently without an appropriate plan. A prespecified primary outcome and analysis hierarchy can help readers distinguish confirmatory questions from exploratory ones. The registry record does not provide such a hierarchy or state whether other outcomes were considered outside the listed measure.

Missing-outcome information is also not reported in the registry record. The record does not state how many participants completed the telephone interview, how missing or uncertain fall reports were handled, or whether participants were excluded from the outcome analysis. It does not specify an imputation method or a sensitivity analysis. These details matter because an analysis limited to participants with observed outcomes can be misleading if outcome availability is related to fall experience or group membership.

The registry record does not define an intention-to-treat, per-protocol, or other analysis population for the primary outcome. Since allocation was non-randomized, the usual intention-to-treat interpretation associated with randomized assignment cannot simply be presumed. The analysis population and handling of incomplete follow-up are not reported in the registry record, so the endpoint’s denominator and the possible effect of missing data cannot be evaluated.

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.

The registry lists 0 serious adverse events among 55 participants at risk in the Treatment group and 0 among 51 participants at risk in the Control group. It also lists 0 other adverse events among 55 at risk in Treatment and 0 among 51 at risk in Control. These are the recorded event counts in the registry; they do not establish that no events occurred outside the recorded categories or observation process.

The record separately lists 6 deaths in Treatment and 12 in Control. It does not report the timing or causes of these deaths, whether they were considered related to the intervention, or how deaths were incorporated into the falls outcome analysis. The death counts should therefore be read as recorded counts, not as evidence of a causal difference between groups.

Safety comparisons are also constrained by the non-randomized design and the registry’s warning that the groups are not like-for-like. The record does not report a formal comparative safety analysis, uncertainty estimates, or detailed event descriptions. The primary endpoint concerns reported falls; the adverse-event figures do not supply the missing falls outcome results.

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

The record establishes that a prospective study of a geriatric falls-assessment clinic was conducted and that its stated primary question concerned participants experiencing falls during 12 months. It also describes a control group drawn from an inpatient geriatric service. These details clarify the question the study set out to address, but they are not a report of the primary outcome result.

The registry record does not report how many participants experienced falls in either group. It gives no comparative estimate, confidence interval, or statistical test for the falls endpoint. As a result, the observed direction, magnitude, and precision of any difference cannot be determined from this record. No conclusion about the clinic’s effect on falls follows from the objective or design description alone.

The non-randomized comparison further limits causal interpretation. The outpatient clinic population and inpatient discharge control group may differ in ways relevant to falls, and the registry cautions that the groups are not a like-for-like comparison. The record does not provide baseline information or an adjusted analysis that could clarify the influence of those differences.

The safety counts provide a separate description of recorded adverse events and deaths. They do not replace the primary outcome result and do not establish the cause of the deaths or a causal safety contrast. Similarly, planning illustrations based on an observed effect, when used, are not observed power and do not create evidence of an outcome effect.

The appropriate interpretation is therefore narrow: the registry describes the population, clinic, comparator, follow-up period, and outcome definition, but does not report the primary falls result or the analysis needed to evaluate it. The findings should not be characterized as showing benefit, no effect, or harm on falls based on the information in the registry record.

14. Why This Trial Matters Statistically

This study is statistically notable because its question is clinically concrete but its comparison is observational rather than randomized. The registry sets out a 12-month participant-level falls outcome and describes a prospective clinic cohort compared with an inpatient geriatric discharge control group. That structure makes the distinction between an observed association and a causal effect particularly important.

Non-random allocation does not make a comparison uninformative, but it changes what must be considered when interpreting it. Differences in referral, care setting, or participant characteristics may be associated with both group membership and fall outcomes. The registry explicitly warns that the arms are not a like-for-like control comparison. Without baseline characteristics and a reported adjustment strategy, the possible role of such differences remains unresolved.

The endpoint also illustrates why outcome definitions matter. Counting participants who experienced falls differs from counting all falls. The first focuses on the number of people affected at least once over the stated period; it does not describe recurrence or the total event burden. Self-recall and telephone interview are the stated ascertainment methods, while details about completeness and missing reports are not reported in the registry record.

Finally, the record demonstrates the difference between a registered study description and a result that can be statistically interpreted. It identifies the objective, design, outcome, and safety counts, but does not report the primary falls counts or analyses. A clear outcome definition is useful, yet effect size and precision require the observed data and analysis. Keeping those distinctions explicit prevents a study’s stated aim from being mistaken for evidence that the aim was achieved.

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 direct limitation for interpretation is that the primary falls outcome result is not reported in the registry record. The group-specific counts, denominators for the primary endpoint, effect estimate, confidence interval, and p-value are absent. The registry lists one outcome measure and zero analyses, leaving no inferential result to assess.

The comparison is non-randomized. The registry describes referred outpatient clinic patients and an inpatient service discharge control group, and explicitly cautions that the arms are not a like-for-like control comparison. The record does not report baseline characteristics or an adjusted analysis. Potential differences between groups therefore cannot be characterized from the registry information.

Outcome ascertainment relied on self-recall and telephone interview. The record does not report how contact attempts were conducted, how fall reports were verified, or how incomplete and uncertain reports were handled. It also does not give outcome-specific follow-up completion or analysis-population details.

The registry does not report the study’s sample-size justification, statistical analysis plan, interim analyses, multiplicity approach, or handling of missing data. It also does not provide detailed information about the clinic assessment components, participant eligibility criteria, or the timing and causes of deaths. These omissions limit assessment of design choices, endpoint measurement, and safety context. They do not establish that a particular method was or was not used; those details are simply not reported in the registry record.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Longitudinal Outcome in a Veterans Geriatric Multifactorial Falls Assessment Clinic — NCT02356211.
• Registry record last updated 2020-03-10; status last verified 2020-03.
• Results first posted 2019-01-31.
• 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 identifies a completed prospective controlled study of a Geriatric Multifactorial Falls Assessment Clinic. It describes frail elderly Veteran outpatients referred for falls assessment and a control group from an Acute Geriatric Evaluation and Management inpatient discharge service. Allocation is non-randomized, masking is none, and the design classification is single group, although the description names clinic and control groups. Enrollment is listed as 109.

The primary outcome is the number of participants who experienced falls during 12 months, based on self-recall and telephone interview. The primary outcome counts and analyses are not reported in the registry record. Safety listings record 0 serious adverse events and 0 other adverse events in each group, alongside 6 deaths in Treatment and 12 in Control. The record does not report timing, causes, or attribution for the deaths.