Trial of Metformin for Colorectal Cancer Risk Reduction for History of Colorectal Adenomas and Elevated BMI: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Trial of Metformin for Colorectal Cancer Risk Reduction for History of Colorectal Adenomas and Elevated BMI (NCT01312467), a na phase 2 study. The primary outcome is Change in Activated S6serine235 (i.e., the Ratio of pS6serine235/S6serine235).

2. Clinical Question

3. Trial Design

This completed Phase IIa study evaluated metformin hydrochloride in a single group of participants with a history of colorectal adenomas and elevated BMI. The registry lists enrollment of 45. Allocation is recorded as not applicable, the study model is single group, and masking is recorded as none. There is no concurrent control arm described, so the design does not support a randomized comparison between metformin and another treatment or control condition.

The treatment schedule was oral metformin once daily during week 1 and twice daily during weeks 2–12. The planned treatment period was 12 weeks, subject to disease progression or unacceptable toxicity. The registry lists the study start as 2011-03, primary completion as 2014-03, and status as completed. These record details describe the study schedule and status, not the timing or results of an analysis.

The primary outcome concerns change from baseline to 12 weeks in activated S6serine235, a colorectal tissue marker. The outcome description specifies HScore assessment of tissue staining by the study pathologist. The primary analysis is described as a mean and standard deviation of change and is based on 32 participants with evaluable data. Reasons that the evaluable analysis population differs from the enrollment figure are not reported in the registry record.

The registry also lists outcomes concerning colorectal mucosa proliferation markers, serum measures, and safety and tolerability. The specific statistical plan, including any planned adjustment or modeling beyond the stated primary summary, is not reported in the registry record. Because this is a single-group study, changes over time cannot by themselves separate treatment-associated change from other explanations, such as natural variation or changes occurring over the same period.

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:

Analysis population for the primary outcome, as defined in the registry: The analysis is based on 32 participants who have evaluable data.

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: 45 participants were enrolled into the study

6. Primary Endpoint

The registry lists the primary outcome as Change in Activated S6serine235 (i.e., the Ratio of pS6serine235/S6serine235), measured over From baseline to 12 weeks.

The primary endpoint is change from baseline to 12 weeks in activated S6serine235. The registry identifies this marker as the ratio of pS6serine235 to S6serine235 and describes tissue immunostaining assessed with an HScore. The HScore combines the estimated proportions of cells with low, moderate, and high staining intensity using different weights for each intensity category. The endpoint is therefore a continuous tissue measure, summarized as a mean change and standard deviation.

In general, a tissue marker can be used to assess biological activity within the tissue of interest. That rationale does not make the marker a direct measure of cancer incidence or a clinical outcome. The registry’s broader study purpose concerns whether metformin changes protein markers in colorectal tissue, but the numerical primary outcome result is not reported in the registry record.

The endpoint description refers both to a ratio and to HScore analysis of pS6serine235 staining. The record does not clarify further how those descriptions relate in the final analysis. It also does not report the mean change, standard deviation, confidence interval, or a test statistic for the primary endpoint. Consequently, the size, direction, and precision of the estimated change cannot be evaluated from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a continuous primary outcome, summarized by a mean and standard deviation. The outcome is change in activated S6serine235 from baseline to 12 weeks, with tissue staining assessed by HScore. The primary analysis population is described as 32 participants with evaluable data. Although the record identifies the summary measure and population, it does not report the numerical mean change or standard deviation.

What does a mean change describe?

In general, a mean change summarizes the average within-participant difference between a follow-up measurement and a baseline measurement. The sign and size of that mean depend on how change is defined and on the measurement scale. The registry states that change from baseline was analyzed, but it does not provide the numerical result or further details about the sign convention. The mean alone would not show how much individual measurements vary around the average.

What does the standard deviation describe?

In general, a standard deviation describes spread among observed values around their mean. For this endpoint, it would help characterize how variable the participant-level changes were. It is not the same as a standard error or a confidence interval: those quantities address uncertainty in an estimated mean and depend on additional information. The registry identifies standard deviation as the dispersion measure but does not report its value, a standard error, or a confidence interval. As a result, neither the observed spread nor the precision of the mean estimate can be judged from the registry record.

How is the tissue score constructed?

The registry describes HScore as a weighted estimate based on the percentage of cells stained at different intensities. High-intensity staining receives a weight of 3, moderate or median-intensity staining receives a weight of 2, and low-intensity staining receives a weight of 1. The resulting score is intended to combine the amount of staining with its intensity category. These are features of the measurement method, not evidence of the size or direction of the observed endpoint change. The record does not report the underlying cell-level percentages or participant-level scores.

What can a confidence interval add?

In general, a confidence interval presents a range of values compatible with the data and the statistical procedure used, conveying uncertainty around an estimate. It is useful alongside an estimated effect because a mean change alone does not communicate precision. No confidence interval for the primary endpoint is reported in the registry record. A p-value is also not reported, and neither statistic can be reconstructed from the available endpoint description alone.

What does the single-group design imply?

In general, repeated measurements in one group can describe change over time, but they do not provide a concurrent estimate of what would have happened over the same period without the intervention. Because this study is listed as single group, with allocation not applicable and no masking, the registry record offers no randomized between-group contrast. A within-group change, even if numerically reported, would not by itself establish that metformin caused that change.

The study summary specifies once-daily oral metformin during week 1 and twice-daily dosing during weeks 2–12. A detailed statistical plan for handling repeated measurements, deviations from the dosing schedule, or other analytic issues is not reported in the registry record. It is not possible to infer whether an adjusted model, a particular test, or another method was planned beyond the stated mean and standard deviation.

How should planning calculations be read?

In general, sample-size calculations illustrate how many participants might be needed under specified assumptions to detect a chosen effect with a chosen level of statistical power. The registry’s planning assumptions describe a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect expressed as a fraction of the observed effect. Those are planning illustrations, not the original study’s documented design justification. The record does not report the study’s own sample-size justification. Any calculated sample size is not observed power and does not change the interpretation of the observed endpoint data.

The stated calculation assumptions include two arms even though the trial itself is a single-group study. Such hypothetical calculations must not be confused with an actual randomized comparison in this study. The numerical planning outputs and the fractions used are not reported in the registry entries, so no planning value or specific effect fraction can be stated.

What is not available for reanalysis?

The registry record does not report participant-level measurements, summary endpoint results, a test statistic, a confidence interval, or enough information to reproduce an inferential analysis. A new estimate cannot be calculated from the treatment schedule, enrollment information, or outcome definition. Without the endpoint summaries, even a simple unadjusted recalculation is not possible. The statistical methods that can be described are therefore limited to the stated continuous outcome, mean and standard deviation summary, HScore measurement description, analysis population, and planning assumptions.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Prevention (Metformin Hydrochloride)")
n   <- c(32)
m   <- c(0.0228)
sp  <- c(0.444)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Prevention (Metformin Hydrochloride)  32  0.023  0.444  -0.137  0.183

11. Multiplicity, Missing Data and Analysis Populations

The registry lists four outcome measures overall, including the primary endpoint and other measures concerning tissue proliferation, serum markers, and safety and tolerability. It describes one analysis. The record does not report whether a multiplicity adjustment was planned for evaluating several outcomes or several markers. Without that information, the handling of the risk of chance findings across multiple analyses cannot be assessed. The presence of multiple outcome domains should not be interpreted as evidence that any particular outcome met a statistical criterion.

The primary endpoint analysis is based on 32 participants with evaluable data, while enrollment is listed as 45. The record does not explain why those figures differ. It does not report the number or timing of unavailable measurements, reasons for non-evaluability, or whether missingness was related to participant characteristics, treatment, or outcome values. It also does not describe imputation, sensitivity analyses, or other methods for addressing missing data.

In general, missing measurements can affect an estimate if participants with observed data differ systematically from those without them. The extent and direction of any such effect cannot be assessed without information on missingness and the analysis approach. The record does not report whether the primary analysis was based on a prespecified intention-to-treat, per-protocol, or other analysis population. The evaluable-data description should not be taken to establish how participants without evaluable data were handled in other outcomes.

12. Safety Results

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

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: ductal carcinoma in situ, high grade, solid and cribriform type with apocrine features and focal nec (2.2%).

The registry lists 45 participants at risk for serious adverse events and reports one participant affected in that category. It lists 45 at risk for other adverse events and reports 36 affected. These figures describe the registry’s recorded safety summaries; they do not, on their own, establish that an event was caused by metformin.

The serious adverse event term displayed in the registry is ductal carcinoma in situ, high grade, solid and cribriform type with apocrine features and focal necrosis, shown with a value of 2.2%. The record does not provide further case details in the information. The death count is not reported in the registry record.

In general, adverse-event counts should be interpreted with attention to the event definitions, observation period, and whether events are participants or event occurrences. The registry gives at-risk and affected counts, but the information does not clarify event timing, severity details beyond the serious-event classification, or attribution. The listed safety figures are descriptive and should not be read as a comparison with an untreated or control group, which this single-group study does not include.

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

The registry describes a Phase IIa, single-group study of metformin in participants with a history of colorectal adenomas and elevated BMI. Its primary outcome is a continuous tissue marker measured from baseline to 12 weeks. The endpoint definition and measurement approach are described, and the primary analysis population is identified as 32 participants with evaluable data. However, the numerical mean change and standard deviation are not reported in the registry record. The record therefore does not establish whether the marker increased or decreased, how large any change was, or how precisely it was estimated.

Even if a within-participant change were available, a single-group before-and-after result would describe change over time rather than provide a randomized estimate of the difference attributable to metformin. General explanations for change could include the intervention, ordinary biological variation, measurement variability, or other changes over the observation period. A concurrent comparator is not described in the registry record.

The primary endpoint is a tissue biomarker, not a reported measure of colorectal cancer incidence. The registry lists outcomes related to tissue proliferation, serum markers, and safety and tolerability, but numerical results for those outcomes are not reported in the information. The study’s stated focus on colorectal cancer risk reduction does not convert a marker outcome into evidence about cancer prevention.

The safety summary reports one participant affected by a serious adverse event and 36 affected by other adverse events, with 45 at risk in each category. Those descriptive figures do not establish treatment causation or comparative safety. No control group is available for a direct safety comparison.

The appropriate scope of interpretation is therefore limited: the registry describes a short treatment schedule, a biomarker-based primary outcome, an evaluable analysis population, and adverse-event counts. It does not report the primary numerical result or enough inferential information to assess its magnitude and precision. Nor does it report a cancer-incidence result. Conclusions about these unreported outcomes cannot be drawn from the registry record.

14. Why This Trial Matters Statistically

This study illustrates the difference between a biological marker endpoint and a clinical outcome. The primary measure concerns tissue staining associated with activated S6serine235, assessed by HScore. Such a measure can address a pharmacodynamic question about biological change in colorectal tissue. It is not itself a count of colorectal cancers or a direct estimate of cancer risk.

The design also matters to statistical interpretation. A single-group study can describe change over time among participants with evaluable measurements, but lacks a concurrent control group for estimating a comparative treatment effect. This remains true regardless of whether a within-group change is large or small. A randomized comparator can help distinguish intervention-associated differences from other time-related changes; this registry record describes no such comparison.

Another important issue is the difference between enrollment and the primary analysis population. Enrollment is listed as 45, while the primary analysis includes 32 participants with evaluable data. Because reasons for non-evaluability and missing-data methods are not reported, readers cannot determine how this difference may affect interpretation. Transparent reporting of analysis populations and missing-data handling is important for understanding both the estimate and its uncertainty.

Finally, the registry gives the endpoint definition and intended summary statistics but not the numerical primary result. Statistical interpretation depends on both an estimate and information about its variability or precision. Without those results, neither the size of a marker change nor the uncertainty around it can be evaluated. The trial is therefore informative about the question and measurement approach it set out to use, while the registry record does not provide enough outcome detail to quantify the primary finding.

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 limitation for interpreting the posted results is that the registry record does not report the numerical primary endpoint result. The mean change and standard deviation are described as planned summaries but their values are absent. A confidence interval, p-value, or other inferential result is also not reported. The direction, magnitude, and precision of the primary change therefore cannot be assessed.

The design is single group, with no randomized allocation and no masking. There is no concurrent comparator in the registry record, limiting the ability to distinguish change over time from change associated with treatment. The primary analysis includes 32 participants with evaluable data, compared with enrollment of 45, but the reasons for the difference and the handling of unavailable data are not reported.

The registry describes the endpoint both through a ratio and through HScore analysis of pS6serine235 staining. The connection between these descriptions is not further clarified. Details such as measurement reliability, scoring variability, and any procedures to reduce assessment bias are not reported in the registry record. Although the study is unmasked, the record does not describe the steps, if any, used to address possible measurement or analysis bias.

The record lists other outcomes but does not provide numerical results for them in the information. Multiplicity handling and the original sample-size justification are also not reported. The listed safety counts are descriptive, and the record does not provide a concurrent comparator for safety interpretation. These limitations constrain conclusions about the biomarker, other outcomes, and treatment attribution.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Trial of Metformin for Colorectal Cancer Risk Reduction for History of Colorectal Adenomas and Elevated BMI — NCT01312467.
• Registry record last updated 2019-03-05; status last verified 2019-02.
• Results first posted 2015-06-25.
• 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 describes a completed Phase IIa, single-group study of oral metformin hydrochloride among participants with a history of colorectal adenomas and elevated BMI. The regimen was once daily during week 1 and twice daily during weeks 2–12. Enrollment is listed as 45, and the primary endpoint analysis is described for 32 participants with evaluable data.

The primary outcome was change from baseline to 12 weeks in activated S6serine235, assessed using tissue staining and HScore. The registry record does not report the numerical mean change, standard deviation, confidence interval, or p-value. It also lists tissue, serum, and safety outcomes. The safety summary reports one participant affected by a serious adverse event and 36 affected by other adverse events, with 45 at risk in each category. Because there is no concurrent comparator, the record describes a single-group study rather than a controlled treatment comparison.