Ovulation Induction in Women With Clomiphene Citrate Resistant PCOS: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Ovulation Induction in Women With Clomiphene Citrate Resistant PCOS (NCT01909141), a randomized early/phase 1 study. The primary outcome is Ovulation Rate.

2. Clinical Question

The trial’s stated rationale concerns ovulation induction in women described as CC-resistant. Its summary notes that CC may have antiestrogenic effects on endometrial thickening and that letrozole may improve this condition; it also describes insulin sensitizers as relevant to the study rationale. These statements explain the comparison being tested, but they are not findings from this trial.

The secondary outcomes were the number of follicles greater than 18 mm, endometrial thickness, and pregnancy rate. The posted outcome results allow descriptive comparisons for those measures, but they do not replace the primary question. The registry record does not explain how the primary ovulation-rate values were derived or how they relate to the secondary outcomes.

3. Trial Design

The registry describes a randomized, double-masked, parallel trial with enrollment of 100. It lists 50 participants in each medication group. The study is marked completed, with a start date of 2013-08 and primary completion in 2014-02. Cairo University is listed as the sponsor, and the phase is recorded as EARLY PHASE1.

One group received letrozole with pioglitazone and metformin; the other received CC with pioglitazone and metformin. The arm descriptions give medication doses and cycle-day schedules. The registry also lists transvaginal ultrasound, body mass index calculation, day 3 measurements of follicle stimulating hormone, luteinizing hormone, thyroid stimulating hormone, and total testosterone, pretreatment blood urea and serum creatinine, serum estradiol on day 12, and serum progesterone on day 21.

Randomized allocation means that treatment assignment is intended to be determined by chance, which can help make groups comparable at baseline. Double masking indicates that two categories of people were intended to be unaware of assignment; the registry record does not identify those categories or describe how masking was implemented. Parallel design means the arms received their respective regimens as separate groups rather than switching between them.

Further operational details are not reported in the registry record. These include the randomization method, allocation concealment, the identities of the masked parties, the analysis population, adherence information, and how participants who discontinued or had missing measurements were handled. The registry also does not state a statistical analysis plan or sample-size justification. Those omissions limit the ability to assess how closely conduct and analysis followed a prespecified plan.

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 Ovulation Rate, measured over 3 months.

The primary endpoint is titled Ovulation Rate, with the unit described as percentage of all cycles and a timeframe of 3 months. Ovulation is the event the medication combinations are intended to induce, so an ovulation measure addresses the trial’s central biological question more directly than a laboratory or imaging measure alone. Expressing the outcome across cycles could account for repeated opportunities for ovulation during the observation period, but the registry does not define the calculation or specify how cycles contributed to the reported value.

The posted results give values of 93.0 for the letrozole group and 108.0 for the CC group, each with 50 listed in the arm’s sample-size field. The values are not accompanied by a spread estimate or confidence interval. Because the outcome is described as a percentage, values above 100 require clarification about the denominator or whether the recorded values represent something other than percentages. The registry record does not provide that clarification. It also states that the values are missing or not estimable for a two-arm comparison.

As a result, the primary endpoint is identifiable by name and timeframe, but its posted values cannot be interpreted as a clear between-group estimate of ovulation probability. The registry does not report a primary-effect estimate, uncertainty interval, or inferential test for this outcome. The secondary measures offer additional information about follicles, endometrial thickness, and pregnancy, but they answer distinct questions and do not resolve the primary endpoint’s reporting ambiguity.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The posted comparisons for the continuous and binary secondary outcomes are simple unadjusted recalculations from the registry’s arm-level summaries. They are not a substitute for a sponsor-reported analysis. The registry lists no reported analyses for these outcomes. Because the discrepancy flag is false, no disagreement with a sponsor analysis is identified in the record; however, the absence of reported sponsor analyses means there is no registry-based adjusted result to compare with the recalculations.

What does a confidence interval express?

General statistical explanation: a confidence interval describes the range of estimates compatible with the data and the method used, under the method’s assumptions. A narrower interval indicates greater precision; a wider interval indicates less precision. For a difference, an interval that includes zero does not distinguish the observed data from no difference at the confidence level associated with that interval. It does not prove that the groups are identical. An interval that excludes zero indicates a difference under the calculation’s assumptions, but it does not by itself establish clinical importance, freedom from bias, or a causal interpretation beyond the trial design and analysis.

For the continuous outcomes, the reported estimates are differences in means. The sign depends on the comparison’s order: the CC combination is compared with the letrozole combination. Thus, a negative estimate means the CC group’s posted mean is lower, while a positive estimate means it is higher. The confidence intervals quantify uncertainty around those mean differences using the posted standard deviations and group sizes. The p-values are unadjusted and test compatibility with a null difference under the recalculation method. They do not measure the probability that the null hypothesis is true.

How should the binary outcome be read?

General statistical explanation: a risk difference is the difference between the event proportions in two groups. Its units are absolute proportion, not a relative ratio. A value below zero for the CC-versus-letrozole comparison indicates a lower observed event proportion in the CC group. Its confidence interval describes uncertainty in that absolute difference. The registry also posts relative measures for pregnancy, but those are recalculated from the same group summaries and do not constitute independent evidence. Relative measures can be difficult to interpret without considering the underlying event counts and absolute difference.

The outcome counts are 28 and 24 among 50 participants in each group. The recalculated risk difference is -0.08, with a 95% confidence interval from -0.275 to 0.115. The unadjusted p-value is 0.423. These summaries do not show a precise difference: the interval includes no difference and a range of effects in both directions. The registry does not report an adjusted analysis, a covariate model, or how pregnancy status was determined when data were missing.

What is the role of the planning illustrations?

General statistical explanation: a sample-size calculation describes how many participants a hypothetical study might need under specified assumptions. It is not a measure of the power achieved by a completed study. The posted planning illustrations use the observed effect as their starting point and show scenarios based on 100%, 75%, and 50% of that observed effect. They assume a two-sided significance level of 0.05, equal allocation, and a normal approximation. For non-time-to-event outcomes, the counts are participants per arm. These are planning illustrations, not the trial’s documented design justification, and the registry record does not report that the trial was planned using these assumptions.

Such calculations depend strongly on the effect chosen. An observed effect from a small study can be unstable, and using it as the planning target can produce an overly optimistic estimate of the sample size needed for a future study. The scenarios using smaller fractions of the observed effect illustrate that planning for a more modest effect requires more participants per arm. These values should not be called observed power, and they do not tell whether the completed trial had adequate power for its outcomes.

Why does the primary outcome require caution?

The primary result is not accompanied by the ingredients needed for a standard two-arm comparison: a clearly defined event denominator, an interpretable effect estimate, an uncertainty interval, and an inferential test. The values 93.0 and 108.0 appear alongside a percentage unit, but the registry states that a two-arm comparison is not estimable. It is therefore not appropriate to infer a risk difference, calculate a p-value, or construct an interval from those entries. A percentage calculated across cycles would also require clarity about the number of cycles contributed by each participant and the handling of repeated observations. Those details are not reported in the registry record.

More generally, an analysis of repeated cycles may need to account for outcomes from the same participant being related to one another. Treating every cycle as independent could understate uncertainty if within-participant correlation exists. This is a general methodological consideration, not a description of the analysis used in this trial; the registry record does not report the cycle-level analysis method.

10. Multiplicity, Missing Data and Analysis Populations

The registry identifies one primary outcome and three secondary outcomes, but it does not report a statistical analysis plan, a testing hierarchy, or a multiplicity adjustment. When several outcomes are tested, the chance of obtaining at least one apparently noteworthy result by chance can increase. General statistical explanation: adjustment procedures or a prespecified order of testing can help control how results are interpreted across multiple comparisons. Without information about such procedures, the secondary p-values should be treated as unadjusted and interpreted cautiously.

The record also does not describe missing-data handling, exclusions after randomization, or the population used for analysis. It is not reported in the registry record whether all randomized participants were included in the outcome analyses, whether analysis followed assigned treatment, or whether any participants lacked outcome measurements. The listed arm sample sizes do not establish that every participant contributed data to every endpoint.

These omissions matter because missingness can affect both the estimated treatment effect and its uncertainty. General statistical explanation: if missing outcomes are related to participant characteristics or treatment experience, an analysis limited to observed outcomes may not represent the randomized groups as intended. Methods such as imputation or sensitivity analyses can explore some consequences, but no such methods are reported in the registry record.

The registry lists 50 participants in each arm and gives outcome summaries, but it does not explain whether the continuous measures are based on all participants, whether pregnancy status was available for everyone, or how multiple cycles were handled for ovulation. It also provides no reported sponsor analysis for the posted secondary outcomes. The recalculated comparisons therefore remain unadjusted and cannot be assessed against a prespecified analysis approach. No conclusion about the direction or extent of any missing-data or multiplicity bias can be drawn from the registry record.

11. 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.

For each arm, the registry lists 50 participants at risk for serious adverse events and 0 affected; it also lists 50 at risk for other adverse events and 0 affected. These entries describe what is recorded in the adverse-event fields, not a guarantee that no adverse events occurred. The record does not provide event terms or further detail about collection and reporting procedures. Death counts are not reported in the registry record.

Zero recorded events in groups of this size should be read as a limited safety summary, not as proof that the regimens have no risks. General statistical explanation: when an event is uncommon, a study with a limited number of participants may observe no cases even though the underlying event probability is not zero. The precision of a safety estimate depends on the number of participants and the completeness of event ascertainment, among other factors.

The registry does not report exposure-adjusted safety rates, the duration of safety follow-up, severity gradations beyond the serious/other fields, or a detailed account of withdrawals related to adverse events. Without those details, the posted entries support only a narrow description of the recorded counts in the two groups.

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

The results describe a small randomized comparison of two medication combinations in women with CC-resistant PCOS. The registry provides arm-level summaries for several secondary outcomes, but its primary ovulation-rate entries do not yield an interpretable two-arm estimate. As a result, the central comparison cannot be quantified from the posted primary outcome data, and its precision cannot be assessed with a confidence interval.

The secondary results offer estimates with varying degrees of uncertainty. A confidence interval that includes no difference does not prove that the treatments have the same effect; it indicates that the recalculated data do not clearly distinguish the observed difference from zero under the stated method. A confidence interval excluding zero for an unadjusted secondary comparison does not by itself prove a reliable or clinically important treatment effect. The outcome is secondary, the registry does not report multiplicity handling, and no sponsor analysis is posted for comparison.

The study’s design is randomized and double-masked according to the registry, features that can reduce some risks of bias when implemented appropriately. But the registry does not describe the randomization procedure, who was masked, adherence, analysis population, or missing-data approach. These details are necessary for a fuller appraisal of the estimates and their credibility.

The findings do not establish that either combination is more effective, safer, or preferable. They also do not establish that the two combinations are equivalent. The primary outcome’s unclear values and absence of an estimable comparison, alongside the limitations in analysis reporting, leave substantial uncertainty. The registry summaries are most appropriately read as descriptive and exploratory evidence rather than a definitive answer to the trial’s primary question.

13. Why This Trial Matters Statistically

This trial is statistically informative in part because it illustrates the difference between recording an endpoint and reporting an interpretable treatment comparison. The primary outcome is named, its timeframe is stated, and values appear for both arms. Yet the registry does not define the percentage denominator or provide an estimable comparison. Without a clear outcome definition and an effect estimate with uncertainty, the primary question remains unresolved by the posted result.

The secondary outcomes show why endpoint-specific interpretation matters. Continuous measures, participant-level pregnancy counts, and an ovulation measure expressed across cycles have different data structures. Each requires a clear definition, an appropriate analysis, and transparent reporting of uncertainty. A single trial can therefore have usable summaries for some outcomes while leaving its primary outcome difficult to interpret.

The record also highlights the distinction between trial design and analysis reporting. Randomization and masking are recorded design features, but the registry does not provide enough detail to evaluate their implementation or the analysis population. Similarly, sample-size planning illustrations based on observed effects are not evidence about the original design rationale or achieved power. A clear, prespecified statistical plan would help readers distinguish primary confirmatory analyses from exploratory secondary comparisons.

For biostatisticians and clinical researchers, the practical lesson is that outcome definitions, denominators, analysis methods, and uncertainty estimates are essential components of transparent reporting. When they are absent, cautious interpretation is not merely a general preference; it follows directly from the limits of what the recorded results can support.

14. 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 main limitation specific to this trial is the unclear primary outcome reporting. The endpoint is described as a percentage of all cycles, but the values are 93.0 and 108.0, and the registry marks the two-arm comparison as not estimable. The denominator, the number of cycles contributing to each value, and the meaning of values above 100 are not explained. No primary effect estimate, confidence interval, or p-value is reported.

Although enrollment is 100, with 50 listed in each arm, the registry does not state the sample-size justification or whether that enrollment was intended to provide adequate precision for the primary outcome. The planning illustrations are based on observed effects and cannot be treated as the trial’s original design calculation or as achieved power. The record also does not explain whether the listed outcome summaries include all randomized participants.

The registry gives no detail about randomization procedures, allocation concealment, who was masked, adherence, withdrawals, or protocol deviations. The record does not report how missing outcomes were handled, how repeated cycles were analyzed, or whether analyses adjusted for baseline characteristics. These gaps limit assessment of bias and uncertainty, particularly for an outcome measured across cycles.

There are no sponsor-reported analyses for the posted secondary outcomes, and no multiplicity procedure is described. The secondary recalculations are consequently unadjusted. The adverse-event entries are also brief: they give zero affected for serious and other events in each arm, but do not provide event descriptions, follow-up duration, or death counts. These reporting limitations do not show that the study was conducted incorrectly; they mean that the registry record does not contain enough detail to evaluate those aspects fully.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Ovulation Induction in Women With Clomiphene Citrate Resistant PCOS — NCT01909141.
• Registry record last updated 2015-10-20; status last verified 2015-09.
• Results first posted 2015-03-02.
• 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.

18. Record Summary

The registry describes a completed, randomized, double-masked, parallel trial of two medication combinations for ovulation induction in women with CC-resistant PCOS. Enrollment was 100, with 50 participants listed in each arm. The study is recorded as EARLY PHASE1 and lists Cairo University as sponsor.

The primary endpoint was ovulation rate over 3 months. Although values are posted for both groups, the registry does not provide an estimable comparison or clarify the values’ denominator. Three secondary outcomes have posted results: follicle count, endometrial thickness, and pregnancy. Recalculated unadjusted comparisons provide uncertainty estimates for those outcomes, but no sponsor analyses or multiplicity approach are reported.

The record lacks details on the analysis population, missing data, randomization procedures, and statistical plan. Safety fields list zero serious and other adverse events recorded in each arm; death counts are not reported in the registry record. Overall, the posted results support cautious descriptive interpretation, with the primary question unresolved by the available outcome reporting.