Long Term Study to Investigate the Efficacy & Safety of D961H (Esomeprazole) for the Prevention of NSAIDs-induced Ulcer: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Long Term Study to Investigate the Efficacy & Safety of D961H (Esomeprazole) for the Prevention of NSAIDs-induced Ulcer (NCT00595517), a non-randomized phase 3 study. The primary outcome is Number of Participants Without Gastric and/or Duodenal Ulcer Throughout the Treatment Period.

2. Clinical Question

The clinical question combines an outcome about ulcer occurrence with a study purpose centered on safety and tolerability. The brief summary says safety and tolerability were to be evaluated through adverse events, clinical laboratory values, and vital signs. The listed secondary outcomes count participants without gastric and/or duodenal ulcer through follow-up periods of up to 4 weeks, 12 weeks, and 24 weeks after treatment. Their results are not reported in the registry record.

This distinction matters for interpretation. A single-group study can describe outcomes observed among participants receiving the intervention, but without a suitable concurrent comparator it cannot isolate the effect of treatment from other explanations. The registry record also does not provide the detailed population description or analysis methods needed to determine precisely how the primary outcome was assessed.

3. Trial Design

This is a phase 3, completed, non-randomized, single-group study with no masking. The registry record lists enrollment of 395 and esomeprazole 20 mg once daily as the only intervention. The study began in 2007-10, and primary completion is listed as 2009-09. Treatment was described as lasting up to 52 weeks.

Because there is one study group and no random allocation, there is no randomized control group against which to compare ulcer outcomes or adverse events. The recorded design is therefore suited to describing what was observed among participants receiving esomeprazole, but it does not establish what would have happened to comparable participants under another treatment or without the study intervention. The registry record does not report a separate control condition.

The brief summary says the study assessed safety and tolerability by evaluating adverse events, clinical laboratory values, and vital signs. The primary outcome is the number of participants without gastric and/or duodenal ulcer throughout treatment. Secondary outcomes concern the number without gastric and/or duodenal ulcer up to 4 weeks, 12 weeks, and 24 weeks after treatment. The registry record does not report numerical results for these ulcer outcomes.

The adverse-event information lists a group of 130 participants at risk for serious adverse events and 130 at risk for other adverse events. These denominators differ from the overall enrollment of 395. The registry record does not explain the relationship between enrollment and the safety denominators, such as which participants were included in each safety set or why the denominators differ. It also does not report the analysis populations or the handling of participants who did not complete treatment.

Although sample-size planning illustrations accompany the posted results, their assumptions describe hypothetical two-arm planning rather than the actual single-group design. They should not be interpreted as the trial's design rationale or as observed power. The registry record does not report the original sample-size justification.

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.

Before assignment: Out of 395 enrolled participants, 130 participants were registered and 265 participants were not registered. The major reasons of no registration were 'Incorrect enrollment' (247 participants) and 'Voluntary discontinuation by participant' (18 participants).

Overall Study

Reasons for not completing this period:

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 Number of Participants Without Gastric and/or Duodenal Ulcer Throughout the Treatment Period, measured over up to 52 weeks.

The primary endpoint is the number of participants without gastric and/or duodenal ulcer throughout the treatment period, described as up to 52 weeks. It is a count of participants meeting a defined clinical status rather than a measure of the size or severity of an ulcer. The registry record does not report a more detailed endpoint definition, the assessment schedule, or the number of participants who met the endpoint.

Counting participants without an ulcer can describe how often the specified ulcer-free status was observed during the stated period. Such an outcome is relevant to the prevention question because it focuses on whether gastric and/or duodenal ulcer was present over treatment. The endpoint title does not clarify whether a participant had to remain ulcer-free at every assessment, whether one assessment determined status, or how missing assessments were handled. Those details are not reported in the registry record.

In general, a count is easiest to interpret when the denominator and the rules for determining outcome status are clear. The posted primary outcome does not include a denominator, a numerical result, or a statistical comparison. Without those details, readers cannot estimate the observed proportion, assess its precision, or compare it with an alternative treatment. The three listed secondary outcomes extend the ulcer-free assessment to follow-up periods after treatment, but their numerical results are also not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What the design can estimate. This study is listed as single-group and non-randomized. In general, a single-group study can describe outcomes among the participants observed under the study conditions. It cannot by itself separate an intervention effect from differences in participant characteristics, the natural course of disease, changes in care, or other influences. Random allocation in a comparative study is generally used to make treatment groups more comparable on average; this study did not use random allocation and does not list a concurrent comparator.

What the primary outcome represents. The primary outcome is a number of participants without gastric and/or duodenal ulcer throughout treatment, up to 52 weeks. In general, a binary outcome classifies each participant into one of two states, such as meeting or not meeting an outcome definition, and a count records how many participants meet one state. Interpreting such a count requires a clear denominator and rules for classifying each participant. The registry record does not provide the primary count, its denominator, a detailed assessment rule, or the result of a statistical analysis.

Precision and uncertainty. In general, a confidence interval expresses a range of values compatible with the data and the assumptions of the analysis. A narrower interval indicates greater precision, while a wider interval indicates less precision. A point estimate without an interval can conceal substantial uncertainty, especially when the number of observed outcomes or the completeness of follow-up is unclear. No confidence interval is reported for the primary outcome, and the registry record does not report an inferential analysis for it. Statistical precision therefore cannot be assessed from the posted primary result.

Comparative tests and causal interpretation. In general, a test of a treatment difference requires a defined comparison and a model or procedure appropriate to the outcome and design. A p-value, when reported, measures how compatible data are with a specified null hypothesis under the analysis assumptions; it is not a measure of clinical importance or proof of causation. No comparator or analysis result is reported for the primary endpoint in this record. There is no basis for interpreting a comparative p-value or treatment effect from the registry information.

Count outcomes and dispersion. In general, count data can have more variability than a simple model assumes. Over-dispersion means that observed variation is greater than expected under a model such as a basic Poisson model. When it is present, standard errors from an inadequately specified model can be too small, producing intervals that are too narrow and tests that overstate evidence. Model choice should reflect the outcome distribution and study design. The primary outcome is described as a number of participants, but no count model, dispersion assessment, or analysis method is reported. It would be inappropriate to infer that a particular model was used.

Time and repeated assessment. The primary outcome covers treatment up to 52 weeks, while secondary outcomes refer to ulcer-free status through follow-up periods of up to 4 weeks, 12 weeks, and 24 weeks after treatment. In general, repeated or time-based assessments require a clear definition of the assessment window and the way observations over time are combined. A time-to-event analysis is different from a count of participants meeting a status definition: it uses information about when an event occurs and can account for differing follow-up under stated assumptions. The primary endpoint is described as a participant count, not a time-to-event measure. The registry record does not report the detailed timing or analysis rules for these outcomes.

Planning illustrations. The sample-size illustrations are described as planning calculations based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They describe detecting a stated fraction of an observed effect. In general, such calculations depend on assumptions about the comparison, outcome, effect size, and error rates. They are not estimates of actual statistical power after the study, and they do not show that the trial was designed using those assumptions. Here, the actual trial is single-group, and no randomized comparison is listed. The registry record does not report the original sample-size justification. The planning illustrations should not be treated as a substitute for a reported analysis or as evidence of an observed treatment effect.

Analysis reporting. The registry record lists no analyses. It does not report a statistical analysis plan, the test or model used, adjustment variables, confidence intervals, or p-values for the listed outcomes. General statistical methods can clarify what these items would mean, but they cannot supply missing trial results or establish which methods were used.

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("Esomeprazole 20mg")
n      <- c(130)
events <- c(125)
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  Esomeprazole 20mg  130  125  96.2  91.3  98.7  91.3  98.3  91.3  98.3

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists one primary outcome and three secondary ulcer outcomes, assessed through follow-up periods of up to 4 weeks, 12 weeks, and 24 weeks after treatment. It does not report an analysis for these outcomes. The record also does not state whether there were additional planned comparisons, whether the outcome hierarchy was prespecified, or whether any adjustment for multiple testing was planned. Those details are not reported in the registry record.

In general, when several outcomes or repeated comparisons are tested, the chance of finding at least one apparently unusual result can increase. A multiplicity strategy may define a primary analysis, adjust error rates, or treat secondary analyses as exploratory. Without a stated plan and results, it is not possible to determine how multiplicity was addressed or to interpret any unreported analysis as confirmatory.

The registry record does not report missing outcome counts, participant flow by analysis population, reasons for missing assessments, or methods used to handle missing data. In general, missing data can affect both the number included in an analysis and the result, particularly when the likelihood of missingness is related to participant status or outcome. Complete-case analysis, imputation, and sensitivity analysis make different assumptions; no such approach is specified in this record.

The relationship between overall enrollment of 395 and the safety denominators of 130 is also not explained. The analysis populations for the ulcer outcomes are not reported in the registry record. Without that information, the denominator used for the primary and secondary outcomes cannot be verified, and the completeness of follow-up cannot be assessed.

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

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: rheumatoid arthritis aggravated (2.3%), osteoarthritis deterioration (1.5%), pyelonephritis (1.5%), pain in extremity (0.8%), spondylolisthesis (0.8%).

The adverse-event information lists 130 participants at risk for serious adverse events, of whom 14 were affected. For other adverse events, it lists 130 participants at risk, with 123 affected. These counts describe the registry-listed safety group; they are not a comparison between treatment groups. The record does not explain why the safety denominators differ from the overall enrollment of 395 or how participants were selected for the safety group.

The most frequent serious terms listed are rheumatoid arthritis aggravated at 2.3%, osteoarthritis deterioration at 1.5%, pyelonephritis at 1.5%, pain in extremity at 0.8%, spondylolisthesis at 0.8%, and erysipelas at 0.8%. These are registry-listed percentages. The record does not describe whether terms could overlap within participants or the method used to select the listed terms. Deaths are not reported in the registry record.

In general, an adverse event occurring during a study is not, by itself, evidence that the intervention caused it. Causal assessment depends on clinical review and study design, and a comparative safety assessment needs an appropriate comparator. Neither a comparator nor a detailed causality assessment is reported. The figures should be read as descriptive counts and terms, not as estimates of excess risk attributable to esomeprazole.

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

The registry record describes a phase 3 study of esomeprazole 20 mg once daily in a single group, with treatment lasting up to 52 weeks. Its primary outcome is the number of participants without gastric and/or duodenal ulcer throughout treatment. The posted results do not report that number. The listed secondary ulcer outcomes also have no numerical results in the registry record. As a result, the posted information does not permit an estimate of ulcer-free status or its statistical precision.

The safety data provide counts for a group of 130 participants at risk: 14 affected by serious adverse events and 123 affected by other adverse events. These are descriptive figures without a concurrent comparator. They do not establish that the events were caused by treatment, nor do they indicate how the same participants would have fared under another treatment or without the intervention.

In general, an observed outcome in a single group is not the same as a treatment effect. A treatment effect is a contrast between outcomes under alternative treatment conditions, and causal interpretation relies on an appropriate design and analysis. This study is listed as non-randomized and single-group, so the record does not provide a randomized comparison. The absence of reported analysis results further limits assessment of uncertainty.

The record also does not report the outcome denominators, analysis populations, missing-data methods, or detailed endpoint rules. Those omissions make it difficult to judge how complete and comparable the outcome assessments were. The sample-size planning illustrations are hypothetical calculations, not observed power and not evidence that the study detected an effect. Overall, the record describes the study question and some safety counts, but does not report the primary ulcer result or support a comparative conclusion.

14. Why This Trial Matters Statistically

This trial is statistically notable because its stated prevention question is paired with a single-group, non-randomized design. That design can provide descriptive information about participants observed during treatment, but it cannot provide a randomized comparison. Recognizing this distinction helps separate a study's clinical aim from what its design can establish.

The primary outcome is a count of participants without gastric and/or duodenal ulcer through treatment, up to 52 weeks. Yet the registry record does not report the result, denominator, or inferential analysis. This makes the study a useful example of why endpoint definitions and outcome reporting matter: a clearly named outcome does not by itself show what was observed or how precisely it was estimated.

The safety figures also illustrate the importance of denominators and analysis populations. Overall enrollment is 395, whereas the listed adverse-event group has 130 participants at risk for each adverse-event category. The reason for this difference is not reported in the registry record. Without a clear account of who contributes to each analysis, counts are harder to interpret in relation to the enrolled population.

Finally, planning calculations should be distinguished from the trial's actual design and findings. The accompanying sample-size illustrations assume a two-arm comparison, while the recorded trial is single-group. They are planning illustrations, not observed power. This distinction is broadly important in biostatistics: calculations based on hypothetical assumptions cannot replace a reported analysis of the actual study design and outcome data.

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 central limitation for interpretation is that the primary outcome result is not reported in the registry record. The same is true for the listed secondary ulcer outcomes. There is therefore no reported numerical ulcer result to assess, and no reported interval or test to describe its precision.

The study is listed as non-randomized and single-group, with no masking and no concurrent comparator. This prevents a like-for-like randomized comparison. Even if an outcome result were available, the design would not by itself distinguish the intervention's contribution from other influences on outcomes over time.

Important details about endpoint assessment are not reported in the registry record. These include the precise rules for determining ulcer-free status, the assessment schedule, the denominator for each outcome, and the handling of missing assessments. The analysis populations, participant flow, reasons for discontinuation, and missing-data methods are also not reported.

The adverse-event denominators of 130 are not reconciled with the enrollment of 395. The record does not describe the safety population or how adverse events were collected and attributed. It also does not report deaths. These gaps limit interpretation of the safety counts and prevent comparison with another group.

The registry record does not report a statistical analysis plan, outcome-specific analyses, confidence intervals, p-values, interim analyses, or the original sample-size justification. The presence of planning illustrations does not resolve these omissions; the illustrations are not the study's reported analysis and do not represent observed power. These are limitations of the information available in the registry record, rather than claims about analyses that may or may not have occurred outside it.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Long Term Study to Investigate the Efficacy & Safety of D961H (Esomeprazole) for the Prevention of NSAIDs-induced Ulcer — NCT00595517.
• Registry record last updated 2012-09-14; status last verified 2012-08.
• Results first posted 2012-09-14.
• 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

NCT00595517 is a completed phase 3, non-randomized, single-group study of esomeprazole 20 mg once daily. It enrolled 395 participants and is described as addressing safety and tolerability in patients with a history of gastric and/or duodenal ulcers receiving daily NSAID therapy. The primary outcome was the number of participants without gastric and/or duodenal ulcer throughout treatment, up to 52 weeks.

The registry record does not report the numerical primary or secondary ulcer outcomes, and it lists no analyses. Safety information lists 14 participants with serious adverse events and 123 with other adverse events, each among 130 at risk. The relationship between these denominators and total enrollment is not reported. The single-group design does not provide a randomized comparator, so the posted information is descriptive rather than a comparative treatment-effect analysis.