This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Chemoprevention Trial in Familial Adenomatous Polyposis (FAP) Coli Using EPA (NCT00510692), a randomized phase 2, phase 3 study. The primary outcome is Absolute Change in the Number of Polyps Measured in a Focal Area of the Rectum..
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT00510692 |
| Phase | Phase 2, Phase 3 |
| Condition | Familial Adenomatous Polyposis Coli, FAP |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Quadruple |
| Enrollment | 58 |
| Arms in the primary outcome | 2 |
| Lead sponsor | S.L.A. Pharma AG |
| Results posted | Yes |
2. Clinical Question
The trial asked whether six months of eicosapentaenoic acid (EPA) was associated with a change in the number of rectal polyps in people with familial adenomatous polyposis (FAP). The primary measure was the absolute change from baseline in polyp count within a defined focal area of the rectum. The registry describes the study as investigating whether polyp number and size could be reduced; the posted primary endpoint specifically concerns the number of polyps in that focal area.
Population
People with familial adenomatous polyposis coli. The registry reports enrollment of 58; characteristics beyond the condition are not reported in the registry record.
Intervention
EPA as the free fatty acid, at 2g/day: two capsules twice daily for six months.
Comparator
Placebo consisting of medium chain triglycerides, taken as two capsules twice daily for six months.
Primary question
What was the between-group difference in mean absolute change in focal-area rectal polyp count at six months compared with baseline?
The posted results give a mean change of -0.5 polyps in the EPA arm and 0.5 in the placebo arm. The recalculated unadjusted mean difference, defined as EPA minus placebo, is -1.0, with an interval from -1.691 to -0.309. The registry also reports an ANCOVA estimate of -1.06. These are group-level estimates for the specified measure; they do not describe every participant’s experience or establish what explains the observed changes.
3. Trial Design
The registry describes a randomized, quadruple-masked, parallel-group trial with phase listed as phase 2 and phase 3. It is marked completed. The listed start was 2006-11 and primary completion was 2008-04. Enrollment is reported as 58. The sponsor is S.L.A. Pharma AG.
Participants were assigned to EPA or placebo. The EPA arm received the free fatty acid at 2g/day, taken as two capsules twice daily for six months. The placebo arm received medium chain triglycerides, also as two capsules twice daily for six months. Endoscopy and biopsies were included in the intervention descriptions. The registry identifies quadruple masking but does not specify which roles were masked or how masking was maintained.
The primary outcome was the absolute change in polyp number in a defined focal area of the rectum, measured at six months compared with baseline. The posted arm summaries include 23 participants for EPA and 22 for placebo. The outcome description states that 13 subjects lacked photographs required for counting. The stated reasons include video equipment failure, inability to identify identical views of the focal area, and absence of forceps visible for calibration. The registry does not report further detail on how these missing measurements were handled in the analysis.
Four secondary outcomes are listed: percentage change in polyp count in the focal area, change in global rectal polyp burden, relative EPA concentration of total free fatty acids in rectal mucosa, and number of subjects with adverse events. The registry lists one analysis and reports an ANCOVA comparison for the primary outcome. Details of the randomization procedure, allocation concealment, exact masking procedures, and the trial’s original sample-size assumptions are not reported in the registry record.
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
| Stage | 2g/Day Eicosapentaenoic Acid (EPA) | Placebo |
|---|---|---|
| STARTED | 29 | 29 |
| COMPLETED | 27 | 26 |
| NOT COMPLETED | 2 | 3 |
Reasons for not completing this period:
| Reason | 2g/Day Eicosapentaenoic Acid (EPA) | Placebo |
|---|---|---|
| Adverse Event | 1 | 3 |
| Withdrawal by Subject | 1 | 0 |
Analysis population for the primary outcome, as defined in the registry: 13 subjects lacked the photographs required for counting the measurements of polyps. Reasons for lack of photographs varied including failure of video equipment, inability to identify identical views of the focal area and no forceps visible for calibration.
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: The baseline characteristics are presented for the full analysis set which constitutes 55 of the 58 randomised subjects. The full analysis set includes all subjects who were randomised into the study, took at least one dose of study medication provided both at baseline and at least one treatment measurement for efficacy.
| Characteristic | Unit | 2g/Day EPA | Placebo | Total |
|---|---|---|---|---|
| Participants analysed | 28 | 27 | 55 | |
| Age, Continuous | years | 39.5 (SD 11.4) | 42.5 (SD 13.8) | 40.1 (SD 12.6) |
| Age, Categorical: <=18 years | Participants | 0 | 0 | 0 |
| Age, Categorical: Between 18 and 65 years | Participants | 28 | 26 | 54 |
| Age, Categorical: >=65 years | Participants | 0 | 1 | 1 |
| Sex: Female, Male: Female | Participants | 15 | 12 | 27 |
| Sex: Female, Male: Male | Participants | 13 | 15 | 28 |
| Region of Enrollment: United Kingdom | participants | 28 | 27 | 55 |
6. Primary Endpoint
The registry lists the primary outcome as Absolute Change in the Number of Polyps Measured in a Focal Area of the Rectum., measured over 6 months compared to baseline..
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | Change from baseline number of polyps. |
| Endpoint classification | Continuous Endpoint |
The primary endpoint measures the absolute change from baseline in the number of polyps counted in a defined focal area of the rectum, with the follow-up measurement at six months. It is a count-based measure summarized as a mean, so the reported arm values describe average change rather than the distribution of each participant’s change. A negative mean indicates that the measured count was lower at follow-up than at baseline on average; a positive mean indicates that it was higher on average.
A focal-area measure aims to compare counts within a specified rectal region rather than relying only on a broad assessment of total polyp burden. In general, using a defined area can make repeated observations more directly comparable, provided the same area can be identified and assessed consistently. The registry itself notes that consistent views and calibration were concerns: photographs were unavailable for some subjects because of equipment failure, difficulty identifying the same focal-area view, or lack of visible forceps for calibration.
The endpoint is used to quantify change over time and compare the average changes between randomized groups. The registry also lists change in global rectal polyp burden as a secondary outcome, distinguishing that broader measure from the primary focal-area count. The posted primary result does not provide an individual-level distribution or a count of participants whose polyp number increased or decreased. The clinical importance of a particular change is not defined in the registry record.
7. Results Posted in the Registry
- 2g/Day Eicosapentaenoic Acid (EPA): mean -0.50 versus 0.50 on control; difference -1.00 (95% CI -1.69 to -0.31), standardized effect d = -0.85; z-test p = 0.005.
Mean difference: 2g/Day Eicosapentaenoic Acid (EPA)
95% CI: -1.69 to -0.31
Recalculated from the posted summary statistics
8. Statistical Interpretation
For the focal-area polyp count, the EPA arm had a mean change of -0.5 with a standard deviation of 0.9, while the placebo arm had a mean change of 0.5 with a standard deviation of 1.4. The unadjusted recalculation gives a mean difference of -1.0, calculated as the EPA mean minus the placebo mean. Its interval is -1.691 to -0.309, and the unadjusted p-value is 0.005. The negative direction means the average change was lower in the EPA arm than in the placebo arm.
The registry’s reported ANCOVA analysis gives a net mean difference of -1.06, with a 95% confidence interval from -1.78 to -0.35 and p = 0.005. The sponsor analysis and the unadjusted recalculation are similar in direction and magnitude, though they are not identical estimates. The sponsor’s result is the registry’s own analysis; the recalculation is a simple unadjusted comparison using the posted arm summaries. The registry does not report the covariates or other details used in the ANCOVA.
The interval around the recalculated difference does not include zero, and the reported ANCOVA interval also does not include zero. In general, an interval that excludes the null value is consistent with a difference under the analysis assumptions. The p-value describes how unusual a result at least this discrepant from the null would be if the null model and its assumptions held; it is not the probability that the null is true. Neither the interval nor the p-value establishes why the groups differed or whether the difference has clinical importance.
The outcome data require particular care because the registry reports that 13 subjects lacked photographs needed to count polyps. The arm summaries are based on 23 EPA participants and 22 placebo participants, but details about analysis-population definitions and missing-data handling are not reported in the registry record. It is therefore important to interpret the estimate as a result from the posted measurable outcome data, not as a complete description of every enrolled participant.
The posted results address one primary endpoint at one follow-up time. The registry lists four secondary outcomes, but their numerical results are not reported in the record summarized for this analysis. The primary estimate should not be taken to describe polyp size, global polyp burden, mucosal EPA concentration, or adverse events. Those are separate outcomes. Overall, the reported statistics indicate a between-group difference in mean change for the focal-area count, with uncertainty represented by the intervals; they do not by themselves answer broader questions about long-term outcomes or clinical consequences.
9. Statistical Methods Explained
The registry reports a randomized parallel-group design and an ANCOVA analysis for the primary comparison. The posted arm-level summaries also permit a simple unadjusted recalculation of the difference in mean change. These approaches answer related but not identical statistical questions: the recalculation compares the posted means directly, whereas the registry’s ANCOVA result is the sponsor-reported analysis. Details of the sponsor model are not reported in the registry record.
What does the mean change represent?
The endpoint is a continuous summary of change in a count: each participant’s follow-up count in the defined focal area is compared with the baseline count, and the arm results are reported as means. Although the underlying polyp count is a count measure, the posted outcome is summarized using a mean and standard deviation. The mean gives the average direction and magnitude of change in each arm. The standard deviation describes how spread out individual values are around that arm’s mean; it is not the uncertainty in the estimated mean difference.
The EPA mean change is -0.5, with standard deviation 0.9. The placebo mean change is 0.5, with standard deviation 1.4. The unadjusted mean difference is reported as -1.0, with EPA minus placebo as the comparison direction. A negative difference therefore indicates a lower average change in the EPA arm. It is a contrast between group averages, not a statement that every participant in one arm changed in the same direction.
What is an unadjusted recalculation?
In general, a simple unadjusted comparison uses the posted group summaries without accounting for additional variables in a statistical model. It is useful as a transparent check on the scale and direction of a result. Here, the recalculated comparison is accompanied by an interval from -1.691 to -0.309 and an unadjusted p-value of 0.005. It is not a replacement for the analysis reported by the trial sponsor, and it should not be interpreted as if it included adjustments that are not specified in the registry.
The calculation uses the arm means, standard deviations, and sample sizes posted for the primary endpoint. Such summary-statistic calculations do not reveal individual observations, distribution shape, influential values, or whether assumptions are well met. The registry does not provide participant-level data, and it does not report additional diagnostic checks for the comparison.
What does ANCOVA mean in this report?
ANCOVA is a general statistical method for comparing group outcomes while including one or more covariates in a model. Depending on the specified model, this can account for measured covariate differences and produce an adjusted comparison. The registry reports an ANCOVA mean difference (net) of -1.06, with a 95% confidence interval from -1.78 to -0.35 and p = 0.005. The covariates, model specification, and precise analysis population are not reported in the registry record, so the adjusted estimate cannot be reconstructed from the posted summaries alone.
Random allocation is intended in general to create comparable groups on average, while an adjusted analysis can use measured information to refine a comparison. Neither method eliminates uncertainty or automatically resolves missing outcome measurements. The registry’s result should be read with its stated endpoint and available measurement information in mind.
Why might over-dispersion matter for count outcomes?
In general, count outcomes can vary more widely than a simple count model expects; this is called over-dispersion. When present and not handled appropriately, it can make standard errors and intervals misleading. The posted primary outcome is analyzed as a mean change with standard deviations, and the registry reports ANCOVA. It does not report a count-regression model or an assessment of over-dispersion. This general issue is relevant to the type of underlying measure, but it is not evidence that over-dispersion occurred in this trial.
What does the p-value say?
In general, a p-value measures how compatible the observed data are with a specified null hypothesis under the chosen model and assumptions. The reported p-value of 0.005 is not the probability that the treatment has no effect, nor does it express the size or clinical importance of the difference. The effect estimate and interval provide information about magnitude and precision, while the p-value addresses compatibility with the null under the analysis framework.
The registry lists one analysis and five outcome measures, including the primary endpoint and four secondary outcomes. A multiplicity strategy describing whether or how inference across outcomes was controlled is not reported in the registry record. The p-value should therefore be understood as the reported result for this particular comparison, without assuming an unreported adjustment across outcomes.
10. Confidence Intervals and Precision
The recalculated mean difference is -1.0, with an interval from -1.691 to -0.309. The registry’s ANCOVA estimate is -1.06, with a 95% confidence interval from -1.78 to -0.35. Both intervals lie on the negative side of zero, so the posted analyses are consistent with a lower average change in the EPA arm than in the placebo arm for this endpoint. The two intervals come from different analyses and should not be treated as interchangeable.
In general, a confidence interval describes a range of values compatible with the observed data and the assumptions of the method. It conveys uncertainty about the estimated group difference: narrower intervals indicate greater precision, while wider intervals indicate less precision. A confidence interval is not a range containing every participant’s outcome, and it does not mean that there is a specified probability that the fixed true value lies inside this particular calculated interval.
The interval is informative about statistical precision but does not settle clinical importance. The registry does not report a threshold for a clinically important difference in focal-area polyp count. Nor does it report participant-level values that would show how variation was distributed across individuals. The posted standard deviations, 0.9 in the EPA arm and 1.4 in the placebo arm, describe spread within the groups, not the interval around the between-group estimate.
Precision also depends on how outcomes were observed and analyzed. The registry states that 13 subjects lacked photographs required for measurement and gives several reasons for this. Missing measurement information can affect precision and may affect the interpretation of an estimate, depending on why data are missing and how they are handled. The missing-data method and its assumptions are not reported in the registry record. The interval should therefore be read as uncertainty under the analysis used, alongside the documented limitations in measurement availability.
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.
| Effect to detect | Participants per arm, 80% power | Participants per arm, 90% power |
|---|---|---|
| 100% of the observed effect | 22 | 29 |
| 75% of the observed effect | 39 | 52 |
| 50% of the observed effect | 87 | 116 |
The planning figures are participants per arm, not total events. They are illustrative calculations based on the observed effect, rather than the trial’s original design assumptions. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; each planning scenario targets a stated fraction of the observed effect. The original trial’s sample-size assumptions are not reported in the registry record.
For planning at 100% of the observed effect, the figures are 22 participants per arm for 80% power and 29 participants per arm for 90% power. For planning at 75% of the observed effect, they are 39 participants per arm for 80% power and 52 participants per arm for 90% power. For planning at 50% of the observed effect, they are 87 participants per arm for 80% power and 116 participants per arm for 90% power.
In general, power is the chance that a study designed under specified assumptions will detect an effect of the chosen size using the specified statistical criterion. The 80% and 90% columns express different design targets: the higher target generally requires more participants under otherwise similar assumptions. The rows illustrate that smaller effects need more participants to detect than larger effects. These sample-size figures are planning illustrations, not observed power. They do not show the probability that this completed trial’s result is correct or that a future study will reproduce it.
The curve represents the same planning relationship: as the effect targeted becomes smaller, the required number of participants per arm increases under the stated assumptions. Its values should be interpreted as conditional on the observed effect used as the reference and on the planning assumptions, not as a recommendation or as a reconstruction of the trial’s original design.
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 z1−α/2 = 1.960) and the desired power (z1−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
- Observed difference Δ = -1.000; pooled standard deviation σ = 1.171.
- n = 2 × (1.96 + 0.842)2 × 1.1712 / -1.0002 = 21.5, rounded up to 22 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 <- -1 # observed difference in means
sigma <- 1.17116519201039 # 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(510692)
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 = 22 (80% power), 29 (90% power)
75% of observed effect: n per arm = 39 (80% power), 52 (90% power)
50% of observed effect: n per arm = 87 (80% power), 116 (90% power)
power.t.test: 22.5
Simulated power at n = 22 per arm: 0.791 (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
| Method | Estimate | 95% CI | P-value |
|---|---|---|---|
| ANCOVA | Mean Difference (Net) -1.06 | -1.78 to -0.35 | 0.005 |
The sponsor-reported analysis is an ANCOVA estimate of -1.06 for the net mean difference, with a 95% confidence interval from -1.78 to -0.35 and p = 0.005. The simple recalculation from the posted arm summaries gives an unadjusted mean difference of -1.0, an interval from -1.691 to -0.309, and p = 0.005. Both estimates point in the same direction and are similar in magnitude, while reflecting different analysis approaches.
The recalculation is a check based on the posted means, standard deviations, and group sizes. It does not reproduce an adjusted model. ANCOVA can include covariates, but the registry does not report which covariates were used or other model details. For that reason, the sponsor estimate is the appropriate result to cite as the trial’s reported analysis; the recalculation helps readers understand the scale and direction of the result.
The registry does not flag a discrepancy between the posted summary-based result and the sponsor analysis. Their close agreement is reassuring about the broad numerical pattern, but does not establish that all analysis assumptions were met or resolve uncertainty about missing photographs, analysis populations, or multiplicity. Those details are not reported in the registry record.
14. Multiplicity, Missing Data and Analysis Populations
The registry lists five outcome measures: the primary focal-area absolute change in polyp count and four secondary outcomes. The secondary outcomes concern percentage change in focal-area polyp number, global rectal polyp burden, relative EPA concentration of total free fatty acids in rectal mucosa, and the number of subjects with adverse events. The posted numerical primary result is accompanied by one reported analysis. Numerical results for the secondary outcomes are not reported in the registry record summarized for this analysis.
When several outcomes or comparisons are examined, the chance of at least one apparently strong result can increase. In general, multiplicity methods are used to manage inference across a family of tests, for example by adjusting significance thresholds or specifying a hierarchy of outcomes. The registry does not report whether such a strategy was prespecified or used. The primary p-value should therefore be read as the reported value for its comparison, without assuming that it accounts for testing across the listed secondary outcomes.
The record identifies randomized allocation and reports an ANCOVA analysis, but the analysis population is not described in detail. It does not specify whether the primary analysis followed an intention-to-treat principle, which participants were included in the model, or how protocol deviations were handled. These matters are not reported in the registry record and should not be inferred from the arm summaries.
Missing endpoint measurements are a specific concern. The registry states that 13 subjects lacked photographs required for counting, with reasons including video equipment failure, difficulty identifying identical focal-area views, and no forceps visible for calibration. Arm summaries for the primary outcome are reported for 23 EPA participants and 22 placebo participants. The missing-data method, any imputation, and sensitivity analyses are not reported in the registry record. Without those details, it is not possible to assess from the registry alone how the unavailable measurements were incorporated or whether conclusions might change under alternative assumptions.
15. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| 2g/Day Eicosapentanoic Acid (EPA) | 3 | 29 | 10.3% |
| Placebo | 0 | 29 | 0.0% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 0% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| 2g/Day Eicosapentanoic Acid (EPA) | 25 of 29 |
| Placebo | 25 of 29 |
Most frequent serious adverse event terms
| Event term | Organ system | 2g/Day Eicosapentanoic Acid (EPA) | Placebo |
|---|---|---|---|
| Small bowel obstruction | Gastrointestinal disorders | 2 of 29 | 0 of 29 |
| Breast cancer | Neoplasms benign, malignant and unspecified (incl cysts and polyps) | 1 of 29 | 0 of 29 |
Most frequent non-serious adverse event terms
| Event term | Organ system | 2g/Day Eicosapentanoic Acid (EPA) | Placebo |
|---|---|---|---|
| Gastrointestinal | Gastrointestinal disorders | 23 of 29 | 22 of 29 |
| Nervous system disorders | Nervous system disorders | 11 of 29 | 6 of 29 |
| General disorders | General disorders | 7 of 29 | 9 of 29 |
| Infections and infestations | Infections and infestations | 8 of 29 | 7 of 29 |
| Musculoskeletal and connective tissue disorders | Musculoskeletal and connective tissue disorders | 7 of 29 | 8 of 29 |
| Respiratory, thoracic and mediastinal disorders | Respiratory, thoracic and mediastinal disorders | 5 of 29 | 4 of 29 |
| Investigations | Investigations | 1 of 29 | 5 of 29 |
| Injury, poisoning and procedural complications | Injury, poisoning and procedural complications | 4 of 29 | 1 of 29 |
| Skin and subcutaneous tissue disorders | Skin and subcutaneous tissue disorders | 1 of 29 | 3 of 29 |
| metabolism and nutritional disorders | Metabolism and nutrition disorders | 1 of 29 | 2 of 29 |
Serious events with the highest arm-level rate: small bowel obstruction (6.9%), breast cancer (3.4%).
The registry reports serious adverse events for 3 of 29 subjects at risk in the EPA group and 0 of 29 at risk in the placebo group. It lists small bowel obstruction at 6.9% and breast cancer at 3.4% among the top serious adverse-event terms. These are the registry’s reported figures; they should not be interpreted as establishing that the study treatment caused an event.
For other adverse events, the record reports 25 of 29 subjects at risk in each group as affected. The listed adverse-event counts indicate whether subjects were affected, not necessarily the total number of event episodes or their duration. The registry does not provide further detail on event timing, severity beyond the serious classification, recurrence, or causal assessment. Deaths are not reported in the registry record.
These safety figures are descriptive and should be interpreted in the context of the trial’s recorded follow-up and definitions, which are not detailed in the posted summary. They do not by themselves establish comparative safety, explain the listed events, or support conclusions about risk beyond the observed trial record.
16. What the Result Does, and Does Not, Mean
The posted primary results show different average changes in focal-area rectal polyp count between the randomized groups. The EPA arm’s mean change was -0.5, compared with 0.5 in the placebo arm. The unadjusted recalculation estimates the difference as -1.0, and the registry’s ANCOVA analysis reports -1.06. Both reported intervals lie below zero, and both analyses report p = 0.005. These statistics describe the observed group comparison for the specified endpoint and follow-up.
They do not establish that every participant’s polyp count fell with EPA, nor that every participant’s count rose with placebo. The arm means and standard deviations summarize group-level distributions; individual responses are not reported. The primary endpoint concerns count in a defined focal area, not polyp size or the full rectal polyp burden. Those are separate measures, and the registry lists global burden as a secondary outcome without numerical results in the record.
The results also do not establish the clinical importance of the estimated difference. A clinically meaningful threshold is not reported in the registry record. The intervals describe statistical uncertainty under the respective analyses, but do not address every source of uncertainty, including missing photographs and unreported details about analysis populations and missing-data handling.
The trial record concerns a six-month comparison in people with FAP and does not provide evidence about longer-term outcomes in this record. The result should not be extended to other populations, outcomes, or durations without supporting data. Safety counts are separately reported and do not establish whether events were caused by the assigned intervention. Taken together, the posted statistics support a carefully bounded interpretation: the analyzed focal-area count changed differently on average between groups, while clinical meaning, missing-data sensitivity, longer-term effects, and broader applicability remain unresolved by the registry information.
17. Why This Trial Matters Statistically
This trial illustrates why an endpoint’s measurement process is part of its statistical interpretation. The primary outcome is not simply a count recorded at one visit; it is an absolute change in count within a defined focal area between baseline and six months. Repeated measurement depends on identifying comparable views and calibrating the count. The registry explicitly notes missing photographs due to equipment failure, difficulty locating identical views, and lack of visible forceps for calibration. Those details help readers understand the practical limits of the endpoint.
It also provides a useful comparison between a sponsor-reported adjusted analysis and a simple calculation from arm summaries. The ANCOVA estimate and the unadjusted estimate are close in direction and magnitude, but they are not the same method or estimand by default. Reporting both makes clear that summary-based recalculation can check the broad numerical pattern without replacing the prespecified or sponsor-reported analysis. The registry does not provide enough model detail to reproduce the ANCOVA.
The posted values also show how uncertainty and statistical significance should be considered together. The estimates are accompanied by intervals, which communicate plausible values under the analysis assumptions, while the p-value addresses compatibility with a null comparison. Neither alone conveys clinical importance, individual variation, or sensitivity to missing measurements.
Finally, the planning illustrations show how sample-size requirements depend on the effect targeted and the desired power, under stated assumptions. They are not evidence about the power achieved by this completed study. Keeping the planning calculation separate from the original trial design and from observed results is essential for a sound statistical reading.
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 primary endpoint depended on photographs suitable for counting a defined rectal area, and the registry reports that 13 subjects lacked required photographs. The stated causes include equipment failure and difficulty obtaining comparable, calibrated views. Because the handling of these missing measurements is not reported in the registry record, the potential effect of missingness on the estimate cannot be assessed from the posted information.
The primary outcome summaries include 23 participants in the EPA arm and 22 in the placebo arm, while registry enrollment is 58. The record does not explain the relationship between enrollment and the primary analysis population in sufficient detail, or report whether a particular analysis-population principle was used. No inference about the unreported participants’ outcomes is warranted.
The registry gives the ANCOVA estimate but not its covariates, model specification, or diagnostic checks. It also does not describe the original sample-size justification, interim analyses, allocation concealment, or detailed masking procedures. Multiplicity handling across the primary and secondary outcomes is not reported. These omissions limit assessment of the analysis plan and robustness of inference.
The primary endpoint is a focal-area count at six months compared with baseline. The registry does not report a clinically important difference threshold, long-term follow-up results, or numerical results for the listed secondary outcomes in the record. Participant characteristics beyond FAP are also not reported. These limitations constrain judgments about clinical meaning, duration, and applicability to populations not described in the registry.
19. Related Tutorials
20. Related Statistical Calculators
21. Sources
- ClinicalTrials.gov: Chemoprevention Trial in Familial Adenomatous Polyposis (FAP) Coli Using EPA — NCT00510692.
- Registry record last updated 2014-08-22; status last verified 2014-08.
- Results first posted 2014-08-22.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
22. Record Summary
The registry record describes a completed randomized, quadruple-masked, parallel-group trial, with phase listed as phase 2 and phase 3 and enrollment of 58. It compared EPA at 2g/day with a medium-chain-triglyceride placebo for six months in people with familial adenomatous polyposis. The primary outcome was absolute change in polyp count in a defined focal area of the rectum.
The posted arm means were -0.5 for EPA and 0.5 for placebo. The registry’s ANCOVA analysis reported a mean difference of -1.06, with a 95% confidence interval from -1.78 to -0.35 and p = 0.005. A simple unadjusted recalculation gives a difference of -1.0. The registry also reports missing photographs for 13 subjects and serious adverse events affecting 3 of 29 EPA subjects and 0 of 29 placebo subjects. Important details about missing-data handling, analysis populations, model specification, and multiplicity are not reported in the registry record.