Impact of TheraWorx Foam on Symptom Relief in Thumb Arthritis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Impact of TheraWorx Foam on Symptom Relief in Thumb Arthritis (NCT03770091), a randomized phase 3 study. The primary outcome is Numeric Pain Rating Scale.

2. Clinical Question

3. Trial Design

The registry identifies this as a completed, randomized, single-masked, parallel-group Phase 3 trial. It lists enrollment of 40 and reports three treatment assignments: Theraworx foam with a compression wrap, placebo foam with a compression wrap, and Theraworx foam alone. The recorded group sizes for the primary outcome are 15, 13, and 12, respectively. Details about how randomization was generated or concealed are not reported in the registry record.

The parallel design means that participants were assigned to a group rather than being described as switching between treatments. The placebo-and-wrap group serves as the control for the posted pairwise comparisons. Because the foam-alone group does not use a wrap, its comparison with the control combines differences in foam assignment and wrap use. The registry does not report a separate placebo-without-wrap group, so the independent contribution of the wrap cannot be isolated from these comparisons.

The registry gives trial dates of 2018-12-21 for the start and 2020-07-30 for primary completion, and lists the status as completed. The primary outcome is the Numeric Pain Rating Scale mean at 2 weeks. The outcome description explicitly distinguishes this score from change from baseline. Other endpoint timing details and the schedule of assessments are not reported in the registry record.

Single masking is listed, but the identity of the masked participants or study personnel is not reported in the registry record. Information about eligibility criteria, setting, participant characteristics, adherence, treatment duration beyond the outcome timeframe, and handling of withdrawals is also not reported. The record identifies the sponsor as John Fowler. It does not report the trial's original sample-size justification or its prespecified statistical analysis plan, so the posted results should be interpreted using only the methods and outcome details that are recorded.

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

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 Numeric Pain Rating Scale, measured over 2 weeks.

The primary endpoint is the mean Numeric Pain Rating Scale score at 2 weeks. The registry describes a scale from 0, meaning no pain, to 10, meaning maximum pain, with participants rating their pain. A mean summarizes the group’s scores by averaging individual ratings; the accompanying standard deviation describes how spread out those individual scores are around the group mean.

Pain is a direct patient-reported symptom and is relevant to the trial’s stated question about symptom relief in thumb arthritis. A consistent scale also permits the mean scores of the assigned groups to be described and compared. The endpoint is a score at a specified follow-up time, not a change score. That distinction matters: a lower average at 2 weeks describes lower reported pain at that time, but does not by itself describe how much pain changed from each participant’s starting point.

The record reports no baseline pain values alongside this outcome and does not state that the posted means are adjusted for baseline. It also does not report a clinically important difference for this scale. Thus, statistical comparisons can describe the size and uncertainty of differences in group means, but the record alone does not set a threshold for deciding whether a difference would be important to participants.

7. Results Posted in the Registry

• Foam and Compression Wrap: mean 1.70 versus 2.40 on control; difference -0.70 (95% CI -1.75 to 0.35), standardized effect d = -0.50; z-test p = 0.190.
• Foam Alone: mean 3.20 versus 2.40 on control; difference 0.80 (95% CI -0.64 to 2.24), standardized effect d = 0.44; z-test p = 0.277.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is a numeric pain score, and the registry reports a mean and standard deviation for each group. General statistical explanation: a mean describes the center of a group’s scores, while a standard deviation describes their spread. The standard deviations are 1.3 for Theraworx with wrap, 1.5 for placebo with wrap, and 2.1 for Theraworx alone. These measures describe variation among participants, not uncertainty in the group means themselves.

What does the reported ANOVA test?

The registry reports an analysis of variance, or ANOVA, across the three listed groups, with p = 0.6. General statistical explanation: an ANOVA assesses whether the observed group means are compatible with a common mean, given the variation in the data and the assumptions of the analysis. An overall test does not specify which pair of groups might differ; pairwise comparisons are separate questions. The registry does not report the ANOVA model details, an overall effect estimate, or a confidence interval for the overall comparison.

A p-value describes how unusual data at least as incompatible with a null model would be if that model and the test assumptions were correct. It is not the probability that the null model is true, and it does not measure the probability that a treatment works. The reported p = 0.6 is the registry’s result for its overall ANOVA. The pairwise p-values, 0.19 and 0.277, are unadjusted re-calculations from the posted summary statistics, not reported sponsor tests. Each p-value should be interpreted alongside the estimated difference and its uncertainty.

How should mean differences be read?

General statistical explanation: a mean difference is a contrast between two group means. Its sign depends on the order of subtraction. For the Theraworx-and-wrap comparison, the reported estimate is -0.7, reflecting a lower mean score in that group than in the placebo-and-wrap group. For Theraworx alone compared with placebo and wrap, the estimate is 0.8, reflecting a higher mean score in the foam-alone group. In both cases, the unit is points on the stated pain scale.

The re-calculations are described as unadjusted and use the posted summary statistics. They should not be mistaken for adjusted analyses accounting for baseline pain or other participant characteristics. The registry does not report whether such adjusted analyses were planned or performed. The reported confidence intervals accompany these unadjusted estimates; their confidence level is not reported in the registry record.

What does uncertainty in a confidence interval mean?

General statistical explanation: a confidence interval represents a range of values compatible with the data under the method’s assumptions. A narrower interval indicates greater precision, while a wider interval indicates less precision. When an interval for a difference includes zero, the data do not rule out no mean difference at the interval’s stated confidence level. That does not prove there is no difference, and an interval that includes zero may also include differences in either direction. The confidence level and the detailed interval method are not reported in the registry record, so no particular confidence percentage should be inferred.

The pairwise intervals cross zero. For Theraworx with wrap, the reported lower endpoint is -1.748 and the upper endpoint is slightly above zero; for Theraworx alone, the endpoints are -0.641 and 2.241. The intervals show why a point estimate should not be read in isolation: each estimate is only one value among a range of plausible values under the calculation. The group sizes are also modest, with 15, 13, and 12 participants represented in the primary outcome, contributing to limited precision.

Why do group spreads matter?

General statistical explanation: the variability of individual measurements affects how precisely a difference between group means can be estimated. More variation, all else equal, makes it harder to distinguish a mean difference from the natural spread of scores. The reported standard deviations differ across the groups, with the largest recorded for the foam-alone group. The re-calculations use the group summaries; they do not account for unreported features such as baseline adjustment, missing data, or other covariates.

These are continuous-outcome methods. They do not describe the adverse-event counts, which are presented separately as counts in each group. No time-to-event analysis is reported. The registry record does not describe interim analyses, a multiplicity procedure, an analysis population, or the original statistical plan. Those details should not be assumed when interpreting the posted ANOVA and the unadjusted pairwise re-calculations.

10. Confidence Intervals and Precision

The pairwise estimates are uncertain, and both reported confidence intervals include zero. For Theraworx with a compression wrap compared with placebo foam and a wrap, the estimated mean difference is -0.7, with a lower interval endpoint of -1.748 and an upper endpoint slightly above zero. For Theraworx alone compared with the placebo-and-wrap group, the estimated difference is 0.8, with endpoints of -0.641 and 2.241. The intervals therefore do not identify a single precise difference or establish its direction for either comparison.

A confidence interval is a range of values compatible with the observed data under a statistical method and its assumptions. General statistical explanation: narrower intervals indicate greater precision; wider intervals indicate greater uncertainty. Because the intervals cross zero, they include no difference as well as differences in either direction. This does not demonstrate equivalence or prove that the true mean difference is zero. The intervals are based on unadjusted re-calculations from the posted summary statistics.

The registry does not report the confidence level or the detailed method used for the intervals, so a particular confidence percentage should not be assigned to them. The participant counts contributing to the primary outcome are 15, 13, and 12 across the listed groups. The registry does not report whether anyone was excluded from the outcome analysis or how missing measurements were handled. These uncertainties, along with the observed spread in pain scores, matter when judging how much confidence to place in the estimates.

11. 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 values are participants per arm, not total event counts. They are illustrations based on the observed pairwise effects, not the original trial’s design calculation; the trial’s own sample-size assumptions and justification are not reported in the registry record. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and detection of the stated fraction of the observed effect.

The 80% power column gives the planned participants per arm for a design with an 80% chance of detecting the chosen effect if that effect is real and the planning assumptions hold. The 90% power column gives the corresponding participants per arm for a design with a 90% chance. These are design-planning concepts, not probabilities that the observed result is correct. The values are calculated separately for each pairwise comparison, so they depend on the observed effect used for that comparison.

Rows planning for 100%, 75%, and 50% of the observed effect illustrate how the assumed effect size changes the required enrollment. Smaller effects need more participants per arm to achieve the same target power, because they are harder to distinguish from ordinary variation. The planning figures are not observed power for this completed trial; they are illustrations of possible future design sizes under the stated assumptions. They should not be read as evidence about whether the current trial had adequate power under its original plan.

12. 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, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -0.700; pooled standard deviation σ = 1.396.
2. n = 2 × (1.96 + 0.842)² × 1.396² / -0.700² = 62.4, rounded up to 63 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
delta <- -0.7                      # observed difference in means
sigma <- 1.39587303808818                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^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 (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(3770091)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 63 (80% power), 84 (90% power)
 75% of observed effect: n per arm = 111 (80% power), 149 (90% power)
 50% of observed effect: n per arm = 250 (80% power), 335 (90% power)
power.t.test: 63.4 
Simulated power at n = 63 per arm: 0.797 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-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.

13. Analyses Reported by the Sponsor

The registry reports the sponsor’s own overall analysis as an ANOVA across the listed groups, with p = 0.6. It does not report an overall mean difference, confidence interval, or further model details for that analysis. This result addresses an overall comparison and is distinct from the pairwise calculations.

The pairwise estimates are unadjusted re-calculations from the posted group means, standard deviations, and sample sizes. They compare Theraworx with wrap against placebo with wrap, and Theraworx alone against placebo with wrap. Their p-values are 0.19 and 0.277, respectively, and their confidence intervals cross zero. These calculations add pair-specific descriptions but do not replace or override the sponsor’s reported analysis. The registry record does not identify a discrepancy between the reported analysis and the re-calculations.

The registry does not report whether the sponsor’s ANOVA used adjustments, which analysis population it included, or how missing observations were handled. Consequently, the overall p-value and the pairwise re-calculations should be understood as different summaries with different reported levels of detail, rather than as competing versions of the same fully specified analysis.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists five outcome measures and five analyses, while no secondary outcomes are posted. The available results give detail for the primary pain-score endpoint and report an overall ANOVA, but the registry does not describe the complete set of planned hypotheses or which results were designated primary before analysis. It also does not report a procedure for adjusting for multiple outcomes or comparisons.

Multiplicity is the issue that arises when several statistical questions are tested. General statistical explanation: as the number of tests increases, the chance of obtaining at least one apparently unusual result by chance can increase if each test is considered separately. Adjustment methods can address that issue, but none is described in the registry record. The pairwise p-values are explicitly unadjusted re-calculations, and their interpretation should account for the possibility that they are among multiple comparisons.

The analysis population is not reported in the registry record. In particular, the record does not state whether the primary analysis included all randomized participants, only participants with observed outcome data, or another defined group. The group counts for the reported endpoint are 15, 13, and 12, but the relationship of those counts to withdrawals, exclusions, or the full randomized population is not described.

Missing-data frequency and handling are also not reported in the registry record. There is no account of imputation, sensitivity analyses, or whether missingness differed across groups. The absence of that information does not establish that data were missing; it means the posted record does not permit evaluation of how missing outcome values may have affected the means or comparisons.

Interim analyses, stopping rules, and the prespecified statistical analysis plan are not reported in the registry record. Nor is the original sample-size justification reported. Without those details, it is not possible to assess whether the posted analysis followed a prespecified plan or whether any analysis decisions were made after results were examined. These gaps do not invalidate the reported numbers, but they limit assessment of the analysis process and the robustness of conclusions.

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.

The registry reports serious adverse events, other adverse events, and deaths separately for each group. For Theraworx with a compression wrap, 0 serious adverse events and 0 other adverse events are recorded among 15 participants at risk, with 0 deaths. For placebo foam with a compression wrap, the corresponding figures are 0 serious adverse events and 0 other adverse events among 13 participants at risk, with 0 deaths. For Theraworx alone, the record lists 0 serious adverse events and 0 other adverse events among 12 participants at risk, with 0 deaths.

These are event counts in the registry record, not evidence that an event could not occur or that the groups have identical safety profiles. The record does not provide event descriptions because no serious-event terms are listed, and it does not describe the method or duration of safety monitoring. The figures should therefore be read as the adverse-event counts reported for this trial, within the recorded groups and available follow-up, rather than as a general safety conclusion.

The registry does not report additional context about how adverse events were collected, how severity or relatedness was assessed, or whether participants discontinued because of events. These details are not reported in the registry record.

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

The posted results describe mean pain scores at 2 weeks, not change from baseline. The mean was 1.7 for Theraworx with a compression wrap, 2.4 for placebo with a compression wrap, and 3.2 for Theraworx alone on the scale where 0 is no pain and 10 is maximum pain. These group averages give a concise description of the recorded endpoint, but they do not show how individual participants’ pain changed or how scores were distributed beyond the reported standard deviations.

The unadjusted pairwise estimate for Theraworx with wrap versus placebo with wrap is -0.7, with p = 0.19. The estimate for Theraworx alone versus placebo with wrap is 0.8, with p = 0.277. Both intervals cross zero, and the registry’s overall ANOVA reports p = 0.6. The results therefore do not establish a clear difference in mean pain scores. They also do not establish equivalence: the estimates remain uncertain, and the intervals include values in more than one direction.

The foam-alone comparison is not a clean test of foam against placebo under the same wrap conditions. One group uses Theraworx without a wrap and the comparator uses placebo with a wrap; the observed contrast cannot separate the effect of foam assignment from the difference in wrap use. The foam-and-wrap comparison is more directly aligned in wrap use, but the available results still have uncertainty and do not establish a difference.

The primary measure is pain, not inflammation. The registry’s proposed anti-inflammatory rationale is theoretical and is not tested by the reported endpoint. The record also does not report a threshold for a clinically important change, baseline pain results, longer-term outcomes, or posted secondary outcomes. The findings should be understood as results for the recorded groups and two-week pain measure, not as a conclusion about other outcomes or settings.

No medical conclusion follows from these statistical summaries alone. They describe what was recorded and how uncertain the comparisons are; the registry does not provide enough detail to resolve all questions about clinical importance, missing data, or broader applicability.

17. Why This Trial Matters Statistically

This trial raises several useful statistical interpretation issues in a compact clinical setting. First, the endpoint is a patient-rated continuous score, reported as a mean and standard deviation. That makes the distinction between the group average and the spread of individual scores important. A mean can summarize a group, but it does not reveal the range of individual experiences or the shape of the score distribution.

Second, the outcome is measured at 2 weeks rather than expressed as change from baseline. A post-treatment mean and a change score answer different descriptive questions. Without baseline results or a reported baseline-adjusted model, readers should not interpret the posted means as within-person improvement.

Third, the treatment groups do not form a complete set of matched comparisons. Theraworx with wrap and placebo with wrap differ in foam assignment while sharing wrap use; the foam-alone group differs from the comparator in both foam and wrap. Recognizing which contrast each group comparison represents is necessary before attributing any observed difference to a particular component.

Fourth, the registry reports an overall ANOVA, while the pairwise estimates are unadjusted re-calculations. Overall and pairwise analyses answer related but nonidentical questions. The absence of a reported multiplicity procedure, analysis population, and missing-data approach further limits the degree to which the posted numbers can be treated as a complete prespecified analysis.

Finally, the confidence intervals crossing zero illustrate why a point estimate or p-value alone is not enough. The estimates are compatible with more than one interpretation, and the record does not give a clinical-importance threshold. These are general lessons in reading randomized-trial results: design details, endpoint definition, comparison structure, uncertainty, and reporting completeness all shape what conclusions the statistics can support.

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.

The registry record leaves several trial-specific limitations unresolved. It does not report eligibility criteria, detailed participant characteristics, setting, or the method used to generate and conceal random assignments. It lists single masking without saying who was masked. These omissions make it difficult to assess how representative the participants were or how the trial was implemented.

The primary result is a score at 2 weeks, not a change from baseline. Baseline pain scores are not reported alongside the result, and the record does not state that estimates were adjusted for baseline. The reported outcome therefore cannot describe within-person change or clarify whether groups started with similar pain levels.

The foam-alone group is compared with a placebo group that uses a compression wrap. This comparison does not isolate the effect of foam from the difference in wrap use. The registry also does not report a placebo-without-wrap group. More broadly, adherence, treatment exposure details, and outcomes after the stated timeframe are not reported in the registry record.

Statistical reporting is incomplete. The registry does not report the original sample-size rationale, full analysis plan, analysis population, missing-data handling, or multiplicity adjustment. It gives an overall ANOVA p-value without an effect estimate or confidence interval, and it does not report the confidence level for the pairwise intervals. No secondary outcomes are posted despite the record listing five outcome measures and five analyses.

These are limitations of what can be assessed from the registry record. They do not show that the trial necessarily had a particular bias or that data were missing; the relevant details are simply not reported. The recorded group sizes and uncertain pairwise estimates also mean that the posted comparisons should be read cautiously rather than as precise estimates of effects.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Impact of TheraWorx Foam on Symptom Relief in Thumb Arthritis — NCT03770091.
• Registry record last updated 2021-07-14; status last verified 2021-07.
• Results first posted 2021-07-14.
• 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 identifies NCT03770091 as a completed, randomized, single-masked, parallel-group Phase 3 trial with enrollment of 40. The listed groups used Theraworx foam with a compression wrap, placebo foam with a compression wrap, or Theraworx foam alone. The primary endpoint is mean Numeric Pain Rating Scale score at 2 weeks, not change from baseline.

Reported group means were 1.7, 2.4, and 3.2, respectively. The registry’s overall ANOVA reports p = 0.6. Unadjusted pairwise re-calculations have estimates of -0.7 and 0.8, with intervals crossing zero. The record reports 0 serious adverse events, 0 other adverse events, and 0 deaths in each group. Important details about the original sample-size justification, missing data, analysis population, and multiplicity are not reported in the registry record.