European Active Surveillance Study of Women Taking Hormone Replacement Therapy (HRT): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for European Active Surveillance Study of Women Taking Hormone Replacement Therapy (HRT) (NCT00214903), a registered phase not stated study. The primary outcome is Venous Thromboembolism (e.g., Deep Venous Thrombosis and Pulmonary Embolism).

2. Clinical Question

The clinical question is a safety comparison between groups defined by the HRT product newly prescribed. The primary outcome description covers VTE linked to use of either drospirenone and estradiol or other oral continuous combined HRT preparations. The stated broader surveillance focus includes pertinent cardiovascular outcomes, such as venous and arterial thromboembolism, but the named primary endpoint is VTE.

This is not a question about whether one treatment causes an outcome under controlled random assignment. The registry record does not state how treatment selection occurred, and it explicitly indicates that this is not a randomized comparison. Differences between groups could reflect differences in the women prescribed each product, their treatment histories, or other factors, as well as any association with product use. Adjustment methods and information about such factors are not reported in the registry record.

3. Trial Design

This completed study is titled European Active Surveillance Study of Women Taking Hormone Replacement Therapy (HRT). Its stated condition is menopausal symptoms, and its sponsor is the Center for Epidemiology and Health Research, Germany. The study started in 2004-11, and its primary completion date is 2011-05. The enrollment listed in the record is 30597.

The study is described as active surveillance rather than a randomized trial. Its objective was to compare incidence rates of serious adverse events among users of newly prescribed oral continuous combined HRT products. The primary focus was pertinent cardiovascular outcomes, including venous and arterial thromboembolism, in new HRT users for up to 8.5 years. This describes the intended surveillance horizon; it does not establish the actual follow-up duration for each participant.

The two treatment descriptions for the principal question are new users of oral continuous combined HRT containing drospirenone and new users of oral continuous combined HRT containing other progestagens. Allocation is not stated. The record cautions that the arms are not a like-for-like control comparison. It would therefore be misleading to describe the groups as randomized, matched, or otherwise comparable on the basis of the information recorded.

The primary outcome description refers to participants in the ITT study population. It also notes that women could stop hormonal treatment during the study and that woman-years of exposure for each group are provided in addition. The actual woman-year values are not reported in the registry record. Nor are details of the recruitment process, treatment switching, continued outcome surveillance after stopping treatment, or the handling of participants with incomplete follow-up.

The registry record lists two outcome measures and two analyses, but does not report a detailed statistical analysis plan. The status is completed. Completion by itself does not establish that every planned analysis was reported or that all enrolled participants contributed to each analysis.

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

Analysis population for the primary outcome, as defined in the registry: The number of participants refers to the ITT study population. During the course of the study, women could for example stop hormonal treatment at any point of time. Therefore, the woman-years of exposure for each group are provided in addition.

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: At baseline, 33% of women were using DRSP/E2, 44% were using ooccHRT, 13% were using ooHRT, and 10% 'Non-oral HRT'. These proportions only partially reflect the overall exposure in each cohort (AT population) because market authorization for DRSP/E2 was delayed by more than 1.5 years.

6. Primary Endpoint

The registry lists the primary outcome as Venous Thromboembolism (e.g., Deep Venous Thrombosis and Pulmonary Embolism), measured over within 8.5 years.

The primary endpoint is the number of participants experiencing venous thromboembolism, with deep venous thrombosis and pulmonary embolism given as examples. The measurement unit is participants, the parameter is a number, and the stated timeframe is within 8.5 years. The outcome description relates VTE to use of drospirenone and estradiol or other oral continuous combined HRT preparations.

VTE is used as a safety outcome because the study’s stated focus is on pertinent cardiovascular outcomes in HRT users, and VTE is one of the specific outcomes named in the record. Counting participants with an event gives an understandable measure of how many people experienced the outcome during the defined observation period. It does not, by itself, describe how long each person was observed or the rate of events over exposure time.

General statistical context: a participant count and an incidence rate answer different questions. A rate uses event information in relation to person-time, which can help account for different observation durations. This distinction matters in a study where participants could stop hormonal treatment and where woman-years of exposure are described as an additional measure. The actual VTE participant counts by group and the corresponding exposure values are not reported in the registry record, so the endpoint’s comparative magnitude and precision cannot be assessed from the recorded information.

The endpoint is not a measure of every serious adverse event, nor does the broad set of serious-event terms listed in the safety record substitute for group-specific VTE results. The registry record does not report an effect estimate or confidence interval for the primary endpoint.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical methods determine how outcomes are counted, how groups are compared, and how uncertainty is expressed. The registry record identifies a participant-count endpoint and describes the study as an active surveillance study. It does not report the statistical model, adjustment variables, hypothesis-testing procedure, confidence intervals, or other details needed to reconstruct the primary analysis.

What does a participant count tell the reader?

A count records the number of participants meeting an outcome definition during the stated observation period. Counts are straightforward to interpret, but they depend on how many people are observed and for how long. If groups have different sizes or different follow-up, counts alone do not provide a fair comparison of event frequency. The primary endpoint is described in terms of participants, while the study description also highlights incidence rates and woman-years. That signals the importance of keeping participant counts separate from rates based on exposure time.

General statistical context: a rate relates the number of events to accumulated person-time. Person-time can accommodate participants being observed for different lengths of time, provided the exposure and follow-up definitions are appropriate. A rate is still an estimate subject to uncertainty, and it depends on the analysis choices and data quality. Although the registry record says woman-years are provided in addition, their values are not reported in the registry record available for this account. No rate can be interpreted without the actual numerator, denominator, and relevant analysis definition.

Why does non-random allocation matter?

Random allocation, when used and implemented appropriately, can balance measured and unmeasured participant characteristics across groups on average. The registry record does not state that allocation was randomized; it specifically warns that the arms are not a like-for-like control comparison. In an observational comparison, treatment choice may be related to participant characteristics or clinical circumstances that also relate to outcomes. This can create confounding.

General statistical context: statistical adjustment can account for measured factors included in a model, but it cannot automatically remove differences that were not measured or modeled. To evaluate adjustment, readers need to know which factors were included, how they were measured, how missing values were handled, and what model was used. Those details are not reported in the registry record. No adjusted or unadjusted comparative VTE result is available in the information recorded.

How should uncertainty be assessed?

General statistical context: a confidence interval communicates the precision of an estimated quantity. A narrow interval indicates greater precision under the chosen model than a wide interval, though precision does not resolve bias or make an observational comparison causal. A hypothesis-test p-value, if reported, addresses compatibility between observed data and a specified null hypothesis under model assumptions; it does not measure the probability that a treatment is effective or that the null hypothesis is true. The registry record does not report a VTE confidence interval or comparative p-value.

Counts for binary outcomes can also be analyzed using models that estimate differences or ratios in event occurrence. The appropriate measure depends on the study design, follow-up, and intended interpretation. Because the endpoint includes a timeframe and the study emphasizes exposure duration, a rate-based or time-to-event approach could be considered in general. The record does not state which approach was used for the primary analysis, so no particular model should be attributed to the investigators.

What is the role of the sample-size illustrations?

The record describes planning illustrations based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is expressed as a stated fraction of the observed effect. These assumptions describe a planning exercise; they are not evidence that the study was designed using those assumptions, and the illustrations are not observed power.

General statistical context: a sample-size calculation asks how much information a hypothetical study might need under specified assumptions. Its output depends on the assumed effect and analysis method. A calculation based on an observed effect is especially dependent on that estimate, which may itself be uncertain. Planning for a fraction of an observed effect explores a smaller target effect rather than describing an additional observed clinical result. Sample-size illustrations do not compensate for confounding, missing outcome data, or uncertainty in the underlying effect estimate.

The registry record does not report the original design justification, a protocol-based sample-size calculation, an interim-analysis plan, or the detailed statistical plan. Those items should not be inferred from the planning assumptions described in the record. Nor should any sample-size calculation be interpreted as evidence that a treatment effect was detected.

Why are event categories and endpoints not interchangeable?

The safety record reports participants affected by serious adverse events, while the primary endpoint specifically concerns VTE. A broad serious-event count can include many types of outcomes, and it does not reveal how many participants experienced the primary endpoint. The listed categories and percentages also lack reported denominator details in this record. Without a clear definition and an outcome-specific result, those entries cannot be substituted for a VTE analysis.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("DRSP/E2", "ooccHRT", "ooHRT", "Non-oral HRT")
n      <- c(10043, 13384, 4113, 3057)
events <- c(24, 74, 21, 12)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  DRSP/E2  10043  24  0.2  0.2  0.4  0.2  0.4  0.2  0.4
ARM  ooccHRT  13384  74  0.6  0.4  0.7  0.4  0.7  0.4  0.7
ARM  ooHRT  4113  21  0.5  0.3  0.8  0.3  0.8  0.3  0.8
ARM  Non-oral HRT  3057  12  0.4  0.2  0.7  0.2  0.7  0.2  0.7

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists two outcome measures and two analyses. It does not report which outcomes were designated primary beyond the VTE description, how the analyses relate to the outcome measures, or whether any testing hierarchy was specified. A multiplicity adjustment or other approach to controlling the interpretation of multiple statistical tests is not reported in the registry record.

General statistical context: when several outcomes or comparisons are examined, the chance of obtaining an apparently notable result by chance can increase if each is interpreted without regard to the number of tests. A pre-specified hierarchy, adjustment procedure, or clear distinction between confirmatory and exploratory analyses can help readers understand the evidence. These are general considerations, not claims about what was done in this study.

The primary population is described as the ITT study population. The record notes that women could stop hormonal treatment during the study, but it does not explain how treatment discontinuation, switching, withdrawal, or incomplete follow-up affected inclusion in each analysis. It also does not report the amount or pattern of missing outcome or exposure information, or the methods used to address missing data.

General statistical context: missingness can affect estimates when participants with incomplete information differ systematically from those with complete information. The consequences depend on why information is missing and on the analysis assumptions. Without counts of missing data and a description of the handling method, readers cannot judge whether missingness materially changed the findings.

The record’s reference to an ITT population does not, on its own, explain how an observational exposure comparison was defined or how outcomes were attributed when treatment stopped. The precise analysis population, the treatment-exposure rules, and any sensitivity analyses are not reported in the registry record. These omissions limit assessment of robustness and make it inappropriate to infer that all participants were followed or analyzed in the same way.

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 5% reporting threshold.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: cardiovascular system (4.3%), muscoskeletal system & connective tissue (2.3%), digestive system (2.2%), injury, poisoning, accidents, etc. (2.1%), neoplasms, malignant and benign (1.9%).

The serious adverse event record lists participants at risk and participants affected for four labels: DRSP/E2, ooccHRT, ooHRT, and Non-oral HRT. The recorded at-risk and affected counts are 10043 and 707 for DRSP/E2; 13384 and 1998 for ooccHRT; 4113 and 576 for ooHRT; and 3057 and 508 for Non-oral HRT. These are counts, not rates over time.

The categories should be read as safety-record entries, not as the primary VTE outcome. The primary question concerns new users of drospirenone-containing oral continuous combined HRT compared with users of other progestagens. The record does not establish how each of the four serious-event labels maps to those two groups. Nor does it state the definition or observation period underlying each safety count in enough detail to support a direct comparative interpretation.

The listed serious-term percentages are cardiovascular system at 4.3%, muscoskeletal system & connective tissue at 2.3%, digestive system at 2.2%, injury, poisoning, accidents, etc. at 2.1%, neoplasms, malignant and benign at 1.9%, and psychiatric and neurological disorders at 1.0%. Their denominator and precise calculation are not reported in the registry record. They are not VTE-specific findings and do not establish that HRT caused the events.

Because women could stop hormonal treatment and actual woman-years are not reported in the registry record, the counts should not be treated as exposure-adjusted rates. They describe recorded safety information, but do not by themselves establish comparative risk or causation.

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

The record documents a completed active surveillance study of women taking HRT, with a stated primary focus on VTE in new users of oral continuous combined HRT. It specifies the endpoint, the intended treatment comparison, and a surveillance horizon of up to 8.5 years. It also gives serious adverse event counts for four treatment labels and lists several serious-event categories.

Those details do not establish the primary VTE finding. Group-specific VTE participant counts, incidence rates, exposure values, comparative estimates, and measures of uncertainty are not reported in the registry record. As a result, the direction, magnitude, and precision of any VTE difference cannot be assessed from the recorded information available for this analysis.

The serious adverse event counts are not interchangeable with the VTE endpoint. They cover a broader safety record, and the mapping between their four labels and the two groups in the primary question is not reported. Counts alone are not rates, particularly when participants could stop treatment and follow-up duration may differ. The actual woman-years of exposure are not reported in the registry record.

The study is not described as randomized, and the record cautions that the arms are not a like-for-like control comparison. Even if comparative results were available, an observational contrast would require careful consideration of treatment selection, confounding, follow-up, and outcome ascertainment. The adjustment strategy and relevant sensitivity analyses are not reported.

General statistical context: a lack of a reported estimate is not evidence that two groups have the same outcome. Conversely, counts from a safety record do not demonstrate that one product increases or reduces risk. Statistical significance, clinical importance, and causality are different questions. The record does not report enough primary-outcome results to answer those questions for VTE.

The most defensible conclusion is limited: the registry record describes a surveillance study designed to examine serious adverse events, with VTE as the named primary endpoint, but does not report the comparative VTE results needed to quantify or interpret that endpoint.

14. Why This Trial Matters Statistically

This study illustrates why a clinical question and a statistical result are not the same thing. The record clearly describes the comparison of interest and names a participant-based VTE endpoint within 8.5 years. Yet without the actual VTE counts, exposure values, and comparative estimate, readers cannot determine what the primary analysis found. A well-defined endpoint is necessary for interpretation, but it is not a substitute for results.

The active surveillance setting also highlights the difference between event counts and rates. Women could stop treatment, and the record specifically points to woman-years of exposure as additional information. When observation time varies, exposure-adjusted measures may be important for comparing incidence. The actual exposure values are not reported in the registry record, so the intended rate comparison cannot be evaluated from the available figures.

The non-randomized design is another central statistical feature. The record states that allocation is not stated and warns that the groups are not a like-for-like control comparison. That warning matters because observed differences between product groups may reflect participant characteristics or other factors associated with prescribing, not solely the product. Readers need details on design, adjustment, and analysis to judge how such differences were addressed; those details are not reported.

Finally, the broad serious adverse event counts demonstrate why outcome definitions and denominators must be explicit. Such counts can describe recorded safety information, but they do not answer the endpoint-specific question unless the outcome definition, group mapping, follow-up, and analysis are clear. This record is therefore useful for identifying the surveillance objective and the limits of the reported statistics, while not supporting a numerical conclusion about comparative VTE occurrence.

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 registry record does not report the primary VTE results by treatment group, incidence rates, woman-years, comparative effect estimate, confidence interval, or p-value. These omissions prevent assessment of the primary endpoint’s magnitude and precision. Although woman-years are described as an additional measure, their actual values are not reported in the registry record.

The study is not described as randomized, allocation is not stated, and the record explicitly cautions that the arms are not a like-for-like control comparison. Details of treatment selection, participant characteristics, confounding control, and any adjusted analyses are not reported. The information available therefore cannot establish whether observed group differences, if any, would be attributable to treatment rather than other differences between groups.

The safety entries use four labels, while the primary question describes two groups. The relationship between these labels and the primary comparison is not reported. The record also does not specify the denominator or calculation behind the serious-term percentages. Those figures cannot be interpreted as group-specific VTE rates.

The primary endpoint is described for an ITT study population, and the record notes that women could stop hormonal treatment. It does not provide the detailed follow-up rules, handling of discontinuation or switching, missing-data information, or analysis-population definitions needed to assess how exposure and outcome data were handled. The actual follow-up duration for participants is also not reported; the stated timeframe of up to 8.5 years does not establish equal observation for everyone.

The record lists two outcome measures and two analyses, but does not report multiplicity procedures, a full statistical analysis plan, protocol-based sample-size justification, or interim-analysis details. The planning assumptions described in the record should not be mistaken for the study’s original design plan or for evidence of observed power. These limitations restrict both causal interpretation and evaluation of statistical robustness.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: European Active Surveillance Study of Women Taking Hormone Replacement Therapy (HRT) — NCT00214903.
• Registry record last updated 2014-12-01; status last verified 2014-11.
• Results first posted 2014-11-14.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

19. Record Summary

NCT00214903 is a completed active surveillance study titled European Active Surveillance Study of Women Taking Hormone Replacement Therapy (HRT), sponsored by the Center for Epidemiology and Health Research, Germany. It concerns menopausal symptoms, lists enrollment of 30597, started in 2004-11, and has a primary completion date of 2011-05.

The objective was to compare serious adverse event incidence rates among users of newly prescribed oral continuous combined HRT, with a primary focus on cardiovascular outcomes. The named primary endpoint is the number of participants with VTE, including deep venous thrombosis and pulmonary embolism, within 8.5 years. The intended comparison is between new users of drospirenone-containing products and users of products containing other progestagens.

The record identifies the primary population as ITT and notes that women could stop treatment. It also states that woman-years are provided in addition. Allocation is not stated, and the groups are not described as a like-for-like control comparison. Serious adverse event counts appear for DRSP/E2, ooccHRT, ooHRT, and Non-oral HRT, but group-specific VTE findings, exposure values, comparative estimates, and uncertainty measures are not reported in the registry record.