Ox Bile- Conjugated Bile Acids Sodium in Type II Diabetes Mellitus: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Ox Bile- Conjugated Bile Acids Sodium in Type II Diabetes Mellitus (NCT02871882), a randomized phase 2 study. The primary outcome is Change in Postprandial Glucose.

2. Clinical Question

3. Trial Design

This was a randomized, triple-masked, parallel-group phase 2 trial sponsored by Mayo Clinic. The registry lists the study as completed, with enrollment of 24. The recorded start date is 2016-09-15 and the primary completion date is 2017-10-18. The record does not give a more detailed account of the allocation sequence, concealment procedures, or the identities of the roles covered by triple masking. Those details should not be inferred from the design labels alone.

The intervention was ox bile extract, described as 500 mg tablets taken orally twice daily for 28 (+/- 4) days. The control group received matching placebo tablets on the same schedule. Background therapy in the trial description consisted of DPP4 inhibitors, such as sitagliptin, either alone or in combination with metformin. The registry does not report additional details about how background medicines were managed during the study.

The stated study aims extended beyond the primary glucose outcome. They included insulin sensitivity, postprandial glycemia and incretin levels, gastric emptying, body weight, and fasting serum FGF-19 levels. The record lists a gastric emptying test, a mixed oral glucose tolerance test, and the study drug and placebo among the interventions. Arm descriptions also include waist and hip measurements and blood tests. These broader measurements do not change the definition of the posted primary endpoint.

The group summaries for the primary outcome report 11 participants for ox bile extract and 12 for placebo. The registry enrollment is 24, and the record does not explain how that figure relates to the group counts in the outcome summary. It also does not report the number of participants assessed at each time point, reasons for missing outcome data, or the analysis population used for the primary comparison. The study design labels establish the broad comparison, but they do not answer these implementation questions.

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 Change in Postprandial Glucose, measured over baseline to 1 month.

The primary endpoint is change in postprandial glucose from baseline to one month. The registry defines the measurement as glucose concentration in the bloodstream six hours after eating a meal and gives the unit as mmol/6hr. In general, a post-meal glucose measurement describes a response after eating rather than a fasting value; it can therefore address a different aspect of glucose regulation from fasting measurements. The trial's brief description also identifies postprandial glycemia as one of its study interests.

The posted group summaries report a mean change of -2803.0 for ox bile extract and 629.0 for placebo. The registry describes the outcome summary as a mean with interquartile-range dispersion. It also provides lower and upper accompanying values: -5724.0 to 1098.0 for ox bile extract and -4779.0 to 3814.0 for placebo. The relationship of those bounds to the stated dispersion label is not made clear in the record. The separate spread value is not reported.

Using change from baseline focuses the endpoint on how the measurement shifted over the specified follow-up, rather than on a follow-up value alone. In general, change scores can be useful when the scientific question concerns movement over time, while the interpretation still depends on the measurement definition, analysis method, and handling of missing observations. The registry does not provide further details about the meal used for the measurement, collection procedures, or the timing of the baseline and follow-up assessments beyond the stated timeframe.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the randomized, parallel design mean?

In general, random assignment is intended to make treatment groups comparable on average with respect to both measured and unmeasured characteristics. It does not guarantee that groups will be identical, particularly in a trial with limited enrollment. A parallel-group design means that the assigned groups are compared over the study rather than participants crossing between the study treatments. The registry identifies this study as randomized and parallel. It does not describe the allocation sequence or its concealment, so those details cannot be assessed from the registry record.

The trial is also labeled triple-masked. Masking can help reduce the influence of expectations on treatment delivery, outcome assessment, or interpretation. The particular roles masked are not reported in the registry record. The label therefore describes the stated design but does not show which people were unaware of assignments or how masking was maintained.

What does the ANCOVA result say?

ANCOVA, or analysis of covariance, compares outcomes between groups while adjusting for covariates included in the statistical model. In general, adjustment can account for baseline measurements or other prespecified variables and can improve precision when those variables are related to the outcome. The choice of covariates and the model specification matter: different specifications can yield different adjusted estimates. The registry reports an ANCOVA analysis, but does not report its covariates, the adjusted contrast, or a confidence interval. This limits independent assessment of the model and prevents a direct reading of the size and precision of the adjusted comparison.

The reported p-value is p < 0.05. In general, a p-value describes how compatible the observed data are with a specified null model, under the assumptions of the analysis. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of an effect. The analysis is labeled as superiority, but the p-value without an adjusted estimate does not convey the scale of the group difference. It also does not indicate whether an effect of that size would matter in clinical practice.

How should the arm summaries be read?

The registry reports group mean changes and accompanying lower and upper values. It labels the outcome parameter as a mean and the dispersion as interquartile range, while the separately identified spread is absent. The record does not explain the relationship between the stated dispersion and the accompanying bounds. An interquartile range generally describes the middle half of observed values and is a measure of spread; it is not a confidence interval for a group mean or for a difference between groups. Because the record does not identify the bounds more precisely, they should be described as posted lower and upper values rather than assigned a different statistical meaning.

In general, a confidence interval for a treatment contrast gives a range of effect estimates compatible with the data and model under the interval's assumptions. It is useful for understanding precision and the range of effects that remain plausible. No confidence interval for the sponsor's adjusted contrast is reported in the registry record. The lower and upper values attached to the arm summaries cannot substitute for it, because they are not identified as uncertainty limits for the contrast.

What can be inferred from the planning illustrations?

Planning illustrations based on an observed effect are not observed power and do not describe what happened to participants. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the arms, and a normal approximation, with the effect to detect defined as a stated fraction of the observed effect. In general, such calculations explore what sample size might be needed under chosen assumptions; they do not establish that the original trial was designed with those assumptions. The registry record does not report the trial's own sample-size justification or establish that its design used this calculation approach.

An illustration based on the observed effect is particularly dependent on the stability of that observed estimate. In a small study, the observed effect can be imprecise, so planning around it can produce an uncertain planning target. Such calculations should be understood as conditional scenarios, not as a claim that the study had adequate power or that a result was certain. The actual planning values are not reported in the registry record, and no sample-size figure beyond the stated trial enrollment and outcome group counts is used.

What is not specified about the analysis?

The registry provides one posted primary outcome measure and one posted analysis. It does not state the analysis population, whether the analysis followed randomized assignment regardless of adherence, or how missing observations were handled. It also does not identify the covariates in the ANCOVA, whether the comparison was prespecified in the same form, or whether any sensitivity analyses were conducted. These omissions make it difficult to evaluate the robustness of the reported p-value or to reproduce the adjusted analysis from the group summaries.

General statistical interpretation depends on matching the reported model to the design and outcome, as well as understanding how observations entered the analysis. Here, the direction and scale of the mean changes can be read from the arm summaries, while the sponsor-reported p-value provides an inferential result for the adjusted comparison. Neither component supplies the missing details about model specification, analysis population, or data completeness. The registry record should therefore be read with that distinction in mind.

10. Analyses Reported by the Sponsor

The sponsor's posted analysis is an ANCOVA comparison labeled as superiority, with p < 0.05. The registry does not report the adjusted between-group estimate, a confidence interval for that estimate, or the covariates included in the model. Those omissions mean the sponsor's inferential result can be reported, but its effect size and precision cannot be fully described from the record.

The arm summaries give mean changes of -2803.0 for ox bile extract and 629.0 for placebo. These descriptive values are not the same as an adjusted ANCOVA contrast. A direct unadjusted re-calculation of the between-group result is not reported in the registry record, so there is no separate recalculated estimate to compare with the sponsor's analysis. The group-level lower and upper values do not provide the missing adjusted contrast or its confidence interval.

Accordingly, the sponsor's ANCOVA result is the only reported inferential comparison for the primary outcome in this record. It supports reporting the stated p-value, but not an estimate of the adjusted effect's magnitude or precision. The record does not give enough statistical detail to reproduce the sponsor's model or assess whether alternative specifications would lead to the same conclusion.

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists one primary outcome measure and one posted analysis. It reports no secondary outcomes in the posted results. The study description nevertheless names several broader interests, including insulin sensitivity, postprandial glycemia and incretin levels, gastric emptying, body weight, and fasting serum FGF-19. The absence of posted secondary results means those other aims cannot be evaluated from this outcome record.

The registry does not report whether the investigators adjusted for multiple comparisons, used a hierarchy of outcomes, or otherwise controlled the chance of false-positive findings across analyses. A multiplicity plan is not reported in the registry record. The sponsor's p-value should therefore be read as the result of the listed analysis, without assuming that it was adjusted for any other tests or outcomes.

Missing-data handling is also not reported. The record does not state whether all participants with a baseline measurement contributed to the one-month outcome, how missing values were treated, or whether any imputation or sensitivity analysis was used. The group summaries report 11 participants for ox bile extract and 12 for placebo, while enrollment is recorded as 24. The registry does not explain how those counts relate or whether the summary counts represent the full analysis population.

The analysis population is not reported in the registry record. It is therefore not possible to determine from this information whether the primary analysis included everyone as randomized, only participants with available measurements, or another defined group. Details about adherence and protocol deviations are also not reported. These gaps matter because exclusions or missing measurements can affect the comparability created by randomization and the interpretation of the estimated treatment contrast.

The record also does not describe interim analyses, stopping rules, or a detailed statistical analysis plan. Their presence or absence should not be guessed. In general, prespecification and transparent reporting help readers distinguish planned analyses from exploratory ones and understand how many statistical comparisons informed a conclusion. With those details unavailable, interpretation should remain limited to the outcome summary and ANCOVA result that the registry actually reports.

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 no serious adverse events in either group: the affected count is 0 among 11 participants at risk for ox bile extract and 0 among 12 participants at risk for placebo. It also lists no other adverse events in either group, with 0 affected in each group. Deaths are recorded as 0 in both groups. These are the safety figures posted for the record; they are not a substitute for a detailed account of event monitoring.

A zero affected count means that no events of the listed category were recorded among the participants identified as at risk in that summary. It does not establish that an event is impossible, or that no event could occur in a broader population or over a different observation period. The registry does not provide further information about event definitions, ascertainment procedures, exposure-adjusted follow-up, or the period covered by the safety counts.

The counts should be read descriptively rather than as evidence that the two groups had identical safety profiles. With no affected events listed, the record does not provide event-specific comparisons or estimates of uncertainty. It also does not provide a narrative description of non-serious events. These figures therefore describe what was posted in the registry, not a complete assessment of safety or a basis for individual treatment decisions.

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

The main statistical finding is a sponsor-reported ANCOVA result for change in postprandial glucose, with p < 0.05. The arm summaries report a mean change of -2803.0 for ox bile extract and 629.0 for placebo from baseline to one month. Together, these registry entries describe the posted outcome and the reported inferential test. The record does not provide an adjusted difference between groups or a confidence interval, so it does not show the size or precision of the adjusted comparison.

A statistically significant p-value is not by itself a measure of clinical importance. The clinical meaning of a difference depends on the size and uncertainty of the effect, the outcome's interpretation, and relevant clinical context. The registry does not provide a threshold for a clinically important change in this endpoint. It also does not provide enough model detail to reproduce the ANCOVA result from the arm summaries.

The result concerns a particular population and study setting: overweight or obese people with type 2 diabetes receiving DPP4 inhibitor therapy alone or with metformin, randomized to ox bile extract or matching placebo. It does not establish what would happen in populations outside that description, with different background therapies, or over follow-up beyond the stated baseline-to-one-month primary timeframe. The record does not report details that would support broader generalization.

The trial's description includes other aims, but no secondary outcome results are posted. The primary result therefore does not answer questions about insulin sensitivity, gastric emptying, body weight, incretin levels, or fasting FGF-19. Likewise, the zero adverse-event counts in the registry do not establish the absence of safety risks. They describe the recorded counts in the listed groups, without additional detail about monitoring or follow-up.

In general, a randomized comparison can help estimate differences between assigned groups, but its interpretation depends on outcome completeness, analysis choices, and the uncertainty around the estimate. Here, information about missing data, the analysis population, covariate adjustment, and the adjusted effect estimate is not reported in the registry record. The posted result is therefore a limited statistical account rather than a complete basis for judging the magnitude, robustness, or broader meaning of the outcome.

14. Why This Trial Matters Statistically

This trial is statistically informative as an example of why a p-value and an effect estimate answer different questions. The sponsor reports p < 0.05 from an ANCOVA analysis, while the registry does not report the adjusted difference or a confidence interval. Readers can identify the reported significance result, but cannot use it to judge the adjusted effect's size or precision. That distinction is important whenever a result is presented primarily through a threshold-based test.

The arm-level summaries add descriptive context: the mean change is -2803.0 for ox bile extract and 629.0 for placebo. Yet those values do not recreate the sponsor's adjusted analysis. The record describes dispersion as an interquartile range and also supplies lower and upper values, without clarifying their relationship. This illustrates why clear definitions of summary statistics and uncertainty measures are needed for interpretation and reproducibility.

The record also makes transparent what is unavailable. The analysis population, missing-data handling, ANCOVA covariates, and multiplicity approach are not reported. These are not minor technical details: they influence how readers assess the credibility and scope of an analysis. The absence of posted secondary results further limits conclusions about the trial's broader aims.

The result is specific to a randomized, triple-masked, parallel phase 2 trial with a one-month primary timeframe. The posted safety counts are zero for serious and other adverse events in both groups, but the record does not describe the full monitoring context. Taken together, the study offers a focused example of interpreting a sponsor-reported inferential result alongside incomplete information about effect precision, analysis choices, and outcome reporting.

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 primary outcome record gives mean changes and accompanying lower and upper values, but does not clarify how those bounds relate to the stated interquartile-range dispersion. The separate spread value is absent. This ambiguity limits interpretation of the arm summaries, especially because the bounds should not be mistaken for a confidence interval for the treatment contrast.

The sponsor reports an ANCOVA p-value, but the adjusted estimate, confidence interval, and covariates are not reported. Consequently, the size and precision of the adjusted comparison cannot be determined from the registry record, and the analysis cannot be reproduced from the posted group summaries. The record also does not explain the difference between enrollment of 24 and the outcome group counts of 11 and 12.

Other important analysis details are not reported: the analysis population, handling of missing outcome data, adherence, protocol deviations, and any sensitivity analyses. The registry does not report a multiplicity strategy or a detailed statistical analysis plan. No secondary outcome results are posted, despite the broader study aims. These omissions restrict assessment of how robust the primary result is and how it relates to the trial's other questions.

The primary timeframe is baseline to one month, and treatment is described as lasting 28 (+/- 4) days. The record does not establish what longer-term outcomes might be. It also does not provide details about the meal or measurement procedures used for the postprandial glucose assessment. The safety counts are posted without further detail about event definitions, follow-up, or ascertainment.

Finally, the trial is identified as phase 2, but the registry record does not provide its own sample-size justification. Planning illustrations based on the observed effect are conditional calculations, not evidence that the trial was designed for a particular power target. The posted findings should therefore be interpreted within the limited population, outcome, timeframe, and reporting detail available.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Ox Bile- Conjugated Bile Acids Sodium in Type II Diabetes Mellitus — NCT02871882.
• Registry record last updated 2023-05-31; status last verified 2023-05.
• Results first posted 2023-05-31.
• 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 describes a completed, randomized, triple-masked, parallel phase 2 trial sponsored by Mayo Clinic, with enrollment of 24. It compared ox bile extract, described as 500 mg orally twice daily for 28 (+/- 4) days, with matching placebo in overweight or obese people with type 2 diabetes receiving DPP4 inhibitor therapy alone or with metformin.

The primary outcome was change in postprandial glucose from baseline to one month, defined as glucose concentration six hours after a meal and measured in mmol/6hr. Mean changes were -2803.0 for ox bile extract and 629.0 for placebo. The sponsor reported an ANCOVA superiority analysis with p < 0.05, but the adjusted contrast, confidence interval, and model covariates are not reported.

The record does not describe the analysis population, missing-data handling, or multiplicity approach, and no secondary results are posted. It lists 0 serious adverse events, 0 other adverse events, and 0 deaths in each group.